1. Fang et al., \u201cRCA-U-Net: Residual Channel Attention U-Net for Fast Tissue Quantification in Magnetic Resonance Fingerprinting\u201d.<\/strong> \u56fe1\uff1a\u4e0d\u540c\u65b9\u6cd5\u7684T2 map\u9884\u6d4b\u7ed3\u679c\u3002DM: Dictionary Matching. TCNN: Temporal CNN. SCQ: \u4f20\u7edfU-Net. Proposed: Residual Channel Attention U-Net (RCA-U-Net). \u56fe\u50cf\u53f3\u4e0b\u89d2\u7684\u6570\u5b57\u4e3a\u5e73\u5747\u8bef\u5dee\u3002 \u56fe2\uff1a\u6240\u63d0\u51fa\u7f51\u7edc\u7684\u6846\u67b6\u56fe\u3002<\/p>\n\n\n\n \u9996\u5148\uff0c\u4e09\u79cd\u4e0d\u540c\u7c7b\u578b\u7684\u6b20\u91c7\u6837\u5f25\u6563\u78c1\u5171\u632f\u56fe\u50cf\u88ab\u8f93\u5165\u5230\u4e09\u4e2a\u521d\u7ea7\u5b50\u7f51\u7edc\u4e2d\u8fdb\u884c\u521d\u6b65\u7684\u8d85\u5206\u8fa8\u7387\u91cd\u6784\u3002\u968f\u540e\uff0c\u5b50\u7f51\u7edc\u7684\u8f93\u51fa\u88ab\u878d\u5408\u5e76\u8f93\u5165\u5230\u4e0b\u4e00\u7ea7\u7684\u4f18\u5316\u7f51\u7edc\u4e2d\u3002\u6700\u540e\uff0c\u4f18\u5316\u7f51\u7edc\u8f93\u51fa\u9ad8\u5206\u8fa8\u7387\u5f25\u6563\u78c1\u5171\u632f\u56fe\u50cf\u3002<\/p>\n\n\n\n 4. Liu et al.,\u201cMulti-Stage Image Quality Assessment of Diffusion MRI via Semi-Supervised Nonlocal Residual Networks\u201d.<\/strong> \u56fe3\uff1a\u5207\u7247\u548c\u4f53\u7d20\u8d28\u91cf\u8bc4\u4f30\u7f51\u7edc\u67b6\u6784\u56fe\u3002<\/p>\n\n\n\n 5.\u00a0\u00a0 \u00a0Pan et al.,\u201cDisease-Image Specific Generative Adversarial Network for Brain Disease Diagnosis with Incomplete Multi-Modal Neuroimages\u201d.<\/strong> \u56fe4\uff1a\u63d0\u51fa\u7684\u56fe\u50cf\u751f\u6210\u548c\u75be\u75c5\u8bca\u65ad\u7684\u7edf\u4e00\u6a21\u578b\uff0c\u5305\u62ec (1) \u7528\u4e8e\u75be\u75c5\u8bca\u65ad\u7684\u795e\u7ecf\u7f51\u7edc(DSNN)\u548c (2) \u5177\u6709\u7279\u5f81\u4e00\u81f4\u6027\u7ea6\u675f\u7684\u751f\u6210\u5bf9\u6297\u7f51\u7edc(FGAN)\u3002RNB: \u6b8b\u5dee\u7f51\u7edc\u6a21\u5757\u3002 \u56fe5\uff1aCoCa-GAN\u65b9\u6cd5\u7ed3\u6784\u56fe\uff0c\u8f93\u5165\u56fe\u50cfXS\u4e3aT1w MRI\uff0c\u8f93\u51fa\u5176\u4ed6\u4e09\u4e2a\u6a21\u6001\u3002<\/p>\n\n\n \u56fe6\uff1a\u91c7\u7528CoCa-GAN\u7684\u4e09\u79cd\u53d8\u5f0f\u5f97\u5230\u7684\u56fe\u50cf\u751f\u6210\u7ed3\u679c\u3002\u7b2c\u4e00\u884c\uff1aGround Truth\uff1b\u7b2c\u4e8c\u884c\uff1a\u4e0d\u91c7\u7528\u8fb9\u7f18\u548c\u80bf\u7624\u533a\u57df\u4e0a\u4e0b\u6587\u4fe1\u606f\uff1b\u7b2c\u4e09\u884c\uff1a\u4ec5\u91c7\u7528\u8fb9\u7f18\u4fe1\u606f\uff1b\u7b2c\u56db\u884c\uff1a\u91c7\u7528\u8fb9\u7f18\u4e0e\u80bf\u7624\u533a\u57df\u4e0a\u4e0b\u6587\u4fe1\u606f\uff0c\u53ef\u4ee5\u5f97\u5230\u66f4\u52a0\u771f\u5b9e\u51c6\u786e\u7684\u591a\u6a21\u6001\u8111\u80f6\u8d28\u7624MRI\u56fe\u50cf\u3002 \u56fe7\uff1a\u63d0\u51fa\u7684\u56fe\u50cf\u914d\u51c6\u65b9\u6cd5\u7531\u4e09\u4e2a\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u7b97\u6cd5\u548c\u4f20\u7edf\u7684\u914d\u51c6\u7b97\u6cd5ANTs\u7ec4\u6210\u3002<\/p>\n\n\n \u56fe8\uff1a\u7531ANTs\u548c\u6240\u63d0\u51fa\u7684\u65b9\u6cd5\u5f97\u5230\u7684\u914d\u51c6\u7ed3\u679c\u3002\u84dd\u8272\u6807\u8bb0\u7684\u662fANTs\u914d\u51c6\u5f97\u5230\u7684\u80bf\u7624\u533a\u57df\uff0c\u9ec4\u8272\u7684\u662f\u6211\u4eec\u63d0\u51fa\u7684\u65b9\u6cd5\u5f97\u5230\u7684\u3002<\/p>\n\n\n\n \u5a74\u5e7c\u513f\u8111\u53d1\u80b2<\/strong><\/p>\n\n\n\n 8.\u00a0\u00a0 \u00a0Wu et al.,\u201cIntrinsic Patch-based Cortical Anatomical Parcellation using Graph Convolutional Neural Network on Surface Manifold\u201d.<\/strong> \u56fe9\uff1a(a) \u4eba\u5de5\u76ae\u5c42\u533a\u57df\u5212\u5206\uff1b(b) \u5229\u7528\u6587\u4e2d\u65b9\u6cd5\u7684\u81ea\u52a8\u533a\u57df\u5212\u5206\uff08\u6ca1\u7528\u5e94\u7528\u56fe\u5272\u4f18\u5316\uff09\uff1b(c) \u5229\u7528\u6587\u4e2d\u65b9\u6cd5\u7684\u81ea\u52a8\u533a\u57df\u5212\u5206\uff08\u5e94\u7528\u56fe\u5272\u4f18\u5316\uff09\uff1b(d) \u5229\u7528\u6587\u4e2d\u65b9\u6cd5\u5728\u6a21\u62df\u975e\u7403\u9762\u62d3\u6251\u5927\u8111\u4e0a\u7684\u81ea\u52a8\u533a\u57df\u5212\u5206\uff08\u6ca1\u7528\u5e94\u7528\u56fe\u5272\u4f18\u5316\uff09\uff1b(e) \u5229\u7528\u6587\u4e2d\u65b9\u6cd5\u5728\u6a21\u62df\u975e\u7403\u9762\u62d3\u6251\u5927\u8111\u4e0a\u7684\u81ea\u52a8\u533a\u57df\u5212\u5206\uff08\u5e94\u7528\u56fe\u5272\u4f18\u5316\uff09\u3002 \u56fe10\uff1a(a) -\uff08d\uff09 \u5355\u4e2a\u88ab\u8bd5\u5728\u4e0d\u540c\u89e3\u6790\u5ea6\u4e0b\u7684\u8111\u533a\u5212\u5206\uff1b\uff08e\uff09-\uff08h\uff09\u7fa4\u4f53\u88ab\u8bd5\u5728\u4e0d\u540c\u89e3\u6790\u5ea6\u4e0b\u7684\u8111\u533a\u5212\u5206\uff1b\u5176\u4e2d\uff0c\uff08a\uff09\u548c\uff08e\uff09\u4e3a\u5c06\u76ae\u5c42\u5212\u5206\u4e3a80\u4e2a\u533a\u57df\u7684\u7ed3\u679c\uff1b\uff08b\uff09\u548c\uff08f\uff09\u4e3a\u5c06\u76ae\u5c42\u5212\u5206\u4e3a150\u4e2a\u533a\u57df\u7684\u7ed3\u679c\uff1b\uff08c\uff09\u548c\uff08g\uff09\u4e3a\u5c06\u76ae\u5c42\u5212\u5206\u4e3a250\u4e2a\u533a\u57df\u7684\u7ed3\u679c\uff1b\uff08d\uff09\u548c\uff08h\uff09\u4e3a\u5c06\u76ae\u5c42\u5212\u5206\u4e3a500\u4e2a\u533a\u57df\u7684\u7ed3\u679c\u3002<\/p>\n\n\n\n \u56fe11\uff1a\u8be5\u6587\u65b9\u6cd5\u6240\u5efa\u5a74\u513f\u5927\u8111\u56fe\u8c31\uff08\u4e0b\u56fe\uff09\u4e0e\u4f20\u7edf\u65b9\u6cd5\u6240\u5efa\u5a74\u513f\u5927\u8111\u56fe\u8c31\uff08\u4e0a\u56fe\uff09\u7684\u5bf9\u6bd4\u3002 \u56fe12\uff1a\u7531\u5927\u8111\u76ae\u5c42\u539a\u5ea6\u4e0e\u9762\u79ef\u53d1\u80b2\u6a21\u5f0f\u5171\u540c\u52fe\u753b\u51fa\u7684\u5a74\u513f\u8111\u533a\u5212\u5206\u3002\u8be5\u5212\u5206\u753125\u4e2a\u8111\u533a\u6784\u6210\uff0c\u6bcf\u4e2a\u8111\u533a\u5bf9\u5e94\u7684\u540d\u79f0\u5728\u865a\u7ebf\u6587\u672c\u6846\u5185\u3002 \u56fe13\uff1a\u7528\u4e8e\u4e0d\u540cMRI\u626b\u63cf\u4eea\u5f97\u5230\u7684\u5927\u8111\u76ae\u5c42\u8868\u9762\u5c5e\u6027\u56fe\u8f6c\u6362\u7684\u6846\u67b6\u56fe\u3002(a) \u4e24\u4e2a\u751f\u6210\u5668\u5206\u522b\u88ab\u7528\u6765\u5b66\u4e60\u4e00\u4e2aMRI\u626b\u63cf\u4eea\u5230\u53e6\u4e00\u4e2aMRI\u626b\u63cf\u4eea\u7684\u8fc1\u79fb\u8fc7\u7a0b\uff1b\u4e24\u4e2a\u5224\u522b\u5668\u88ab\u5206\u522b\u7528\u6765\u9274\u522b\u771f\u5b9e\u7684\u5927\u8111\u76ae\u5c42\u8868\u9762\u5c5e\u6027\u56fe\u548c\u751f\u6210\u7684\u5927\u8111\u76ae\u5c42\u5c5e\u6027\u56fe\uff1b(b) \u751f\u6210\u5668\u8be6\u7ec6\u6846\u67b6\u56fe\uff0c\u6bcf\u4e00\u4e2a\u5377\u79ef\u6846\u5305\u542b\u4e24\u4e2a\u7403\u9762\u5377\u79ef\u5c42\u548c\u4e00\u4e2aBatch Normalization\u548cReLU\u5c42\uff0c \u4e0b\u91c7\u6837\u6846\u8fd8\u5305\u542b\u4e00\u4e2a\u989d\u5916\u7684\u7403\u9762\u6c60\u5316\u5c42\uff0c\u4e0a\u91c7\u6837\u6846\u5305\u542b\u4e00\u4e2a\u989d\u5916\u7684\u7403\u9762\u8f6c\u7f6e\u5377\u79ef\u5c42\uff1b(c) \u5224\u522b\u5668\u7684\u8be6\u7ec6\u6846\u67b6\u56fe\uff0c\u6bcf\u4e2a\u5377\u79ef\u6846\u7531\u7403\u9762\u5377\u79ef\u5c42\u52a0\u4e0aBatch Normalization\u548cReLU\u7ec4\u6210\u3002 \u56fe14\uff1a\u5a74\u513f\u5927\u8111\u590d\u6742\u7f51\u7edc\u7684\u65e9\u671f\u53d1\u80b2\uff1aA. \u5168\u5c40\u7f51\u7edc\u6307\u6807\u7684\u53d1\u80b2\uff1bB. \u8111\u533a\u7ea7\u7f51\u7edc\u6307\u6807\u7684\u53d1\u80b2\u3002 \u56fe15\uff1a\u4e00\u4e2a\u5177\u67094\u4e2a\u8282\u70b93\u4e2a\u65f6\u95f4\u70b9\u7684\u591a\u5c42\u65f6\u5e8f\u7f51\u7edc\u7684\u7b80\u5355\u793a\u4f8b\u3002<\/p>\n\n\n \u56fe16\uff1a\u591a\u5c42\u65f6\u5e8f\u7f51\u7edc\u63ed\u793a\u51fa\u751f\u540e\u524d\u4e24\u5e74\u5927\u8111\u533a\u57df\u589e\u957f\u7684\u53ef\u63a5\u89e6\u6027\u548c\u53ef\u4f20\u64ad\u6027\u3002 \u56fe17\uff1a(A) \u548c (B) \u5206\u522b\u662f\u4e09\u7ef4\u5377\u79ef\u7f51\u7edc\u548c\u4e00\u7ef4\u5377\u79ef\u7f51\u7edc\u3002(C) \u7ec4\u5408\u7684\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u7684\u6846\u67b6\u56fe\u3002 \u56fe18\uff1aDGFLDL\u6a21\u578b\u793a\u610f\u56fe\u3002<\/p>\n\n\n\n \u8001\u5e74\u75f4\u5446\u75c7\u3001\u6291\u90c1\u75c7\u53ca\u766b\u75eb<\/strong><\/p>\n\n\n\n 17.\u00a0\u00a0 \u00a0Zhou et al.,\u201cInter-modality Dependence Induced Data Recovery for MCI Conversion Prediction\u201d.<\/strong> \u56fe19\uff1a\u65b0\u9896\u7684\u5c06\u7f3a\u5931\u6837\u672c\u8865\u5168\u3001\u9690\u8868\u793a\u5b66\u4e60\u548c\u9884\u6d4b\u6a21\u578b\u878d\u4e8e\u4e00\u4f53\u7684\u6a21\u578b\u3002<\/p>\n\n\n \u56fe20\uff1a\u4e0d\u540c\u65b9\u6cd5\u6240\u5f97\u5230\u7684MCI\u8f6c\u5316\u9884\u6d4b\u7ed3\u679c\u3002 \u56fe21\uff1a\u63d0\u51fa\u7684MWAN\u7f51\u7edc\uff0c\u7528\u4e8e\u57fa\u4e8e\u5168\u8111MRI\u56fe\u50cf\u7684\u7aef\u5230\u7aef\u5927\u8111\u75c5\u53d8\u533a\u57df\u81ea\u52a8\u5b9a\u4f4d\u53ca\u591a\u76ee\u6807AD\u75c5\u7a0b\u9884\u6d4b\u3002 \u56fe22\uff1a\u6240\u63d0\u51fa\u7684Intra-ROI Dynamic CapsNet\u65b9\u6cd5\u7ed3\u6784\u56fe\u3002<\/p>\n\n\n \u56fe23\uff1a\u6240\u63d0\u51fa\u7684Inter-ROI Dynamic CapsNet\u65b9\u6cd5\u7ed3\u6784\u56fe\u3002 \u56fe24\uff1a\u4e0e\u5176\u4ed6\u65b9\u6cd5\u76f8\u6bd4\u7684ROC\u548cAUC \u3002<\/p>\n\n\n\n 20.\u00a0\u00a0 \u00a0Zhou et al.,\u201cDeep Multi-modal Latent Representation Learning for Automated Dementia Diagnosis\u201d.<\/strong> \u56fe25\uff1a\u4e0d\u540c\u65b9\u6cd5\u7684\u5bf9\u6bd4\u7ed3\u679c (NC\uff1aNormal Control\uff1bMCI\uff1aMild Cognitive Impairment\uff1bpMCI\uff1aprogressive MCI\uff1bsMCI\uff1astable MCI\uff09\u3002<\/p>\n\n\n\n \u56fe26\uff1a\u7528\u4e8e\u7814\u7a76\u6291\u90c1\u75c7\u795e\u7ecf\u75c5\u7406\uff08Pathophysiological Mechanisms\uff09\u7684\u591a\u5c3a\u5ea6\uff08Multiscale\uff09\u795e\u7ecf\u6a21\u578b\u53c2\u6570\u4f30\u8ba1\u65b9\u6cd5\u3002 \u7259\u9f7f\u6b63\u7578<\/strong><\/p>\n\n\n\n \u56fe27\uff1a\u63d0\u51fa\u7684MeshSNet\u6a21\u578b\uff0c\u5176\u4ece\u539f\u59cb\u76843D\u7f51\u683c\u8868\u9762\u6570\u636e\u4e0a\u5b66\u4e60\u548c\u878d\u5408\u591a\u5c3a\u5ea6\u9ad8\u9636\u51e0\u4f55\u7279\u5f81\uff0c\u4ee5\u5b9e\u73b0\u7aef\u5230\u7aef\u7684\u7259\u9f7f\u81ea\u52a8\u6807\u6ce8\u3002 \u56fe28\uff1a\u989d\u9762\u9aa8\u9abc\u91cd\u5efa\u6d41\u7a0b\u56fe\uff0c\u5927\u81f4\u5206\u4e3a\u4e09\u4e2a\u9636\u6bb5\uff1a1\uff09\u4ece\u60a3\u8005\u8fc7\u5f80\u4e8c\u7ef4\u4eba\u8138\u7167\u7247\u4e2d\u91cd\u5efa\u6b63\u5e38\u4e09\u7ef4\u4eba\u8138\uff1b2\uff09\u7531\u6b63\u5e38\u4eba\u8138CT\u6570\u636e\u96c6\uff08\u672f\u524d\u6536\u96c6\uff09\u4e2d\u5206\u522b\u63d0\u53d6\u4eba\u8138\u76ae\u80a4\u548c\u9aa8\u9abc\uff0c\u5e76\u6784\u9020\u4e00\u4e2a\u5173\u8054\u4e8c\u8005\u7684\u5173\u8054\u6a21\u578b\uff0c\u7136\u540e\u5c06\u91cd\u5efa\u7684\u4e09\u7ef4\u4eba\u8138\u5bfc\u5165\u5173\u8054\u6a21\u578b\u4f30\u8ba1\u60a3\u8005\u6b63\u5e38\u989d\u9762\u9aa8\u9abc\u7684\u521d\u59cb\u5f62\u72b6\uff1b3\uff09\u7ed3\u5408\u4e00\u4e2a\u5f62\u72b6\u5f62\u53d8\u6a21\u578b\u5728\u5f53\u524d\u60a3\u8005\u9762\u90e8\u9aa8\u9abc\u5f62\u72b6\u7684\u57fa\u7840\u4e0a\u4f18\u5316\u521d\u59cb\u4f30\u8ba1\u3001\u83b7\u5f97\u6700\u7ec8\u7684\u6b63\u5e38\u989d\u9762\u9aa8\u9abc\u5f62\u72b6\u6a21\u578b\u3002<\/p>\n\n\n\n \u57fa\u56e0\u4e0e\u75c5\u7406\u7814\u7a76<\/strong><\/p>\n\n\n\n \u56fe29: \u8be5\u65b9\u6cd5\u9884\u6d4b\u7684120\u4f8bGBM\u60a3\u8005\u5168\u56e0\u751f\u5b58\u671f\u6240\u6784\u9020\u7684\u751f\u5b58\u66f2\u7ebf\u3002\u4e0e\u57fa\u4e8e\u5355\u4efb\u52a1CNN\u548c\u653e\u5c04\u7ec4\u5b66\u65b9\u6cd5\uff08RD-RF\uff09\u5f97\u5230\u7684\u66f2\u7ebf\u76f8\u6bd4\uff0c\u8be5\u65b9\u6cd5\u7684\u9884\u6d4b\u7ed3\u679c\u66f4\u8d34\u5408\u771f\u5b9e\u7684\u751f\u5b58\u66f2\u7ebf\u3002 \u56fe30\uff1a\u4e0d\u540c\u65b9\u6cd5\u5728\u539f\u59cb\u6570\u636e (a) \u4e0a\u8fdb\u884cData Harmonization\u7684\u533a\u522b\u3002\u7531\u4e8e\u672c\u6587\u65b9\u6cd5 (c) \u8003\u8651\u4e86\u7c7b\u6807\u7b7e\u3001\u6837\u672c\u91cd\u8981\u6027\u548c\u6570\u636e\u6e90\u91cd\u8981\u6027\u7b49\u4fe1\u606f\uff0c\u5176\u8f93\u51fa\u5206\u7c7b\u8d85\u5e73\u9762\u6027\u80fd\u548c\u53bb\u566a\u65b9\u9762\u5747\u6bd4\u73b0\u6709\u65b9\u6cd5\uff08b\uff09\u6709\u660e\u663e\u7684\u4f18\u52bf\u3002\u56fe\u4e2dSNP\u548cROI\u5206\u522b\u4e3aSingle Nucleotide Polymorphisms\u548cRegion-of-Interest\u7684\u7b80\u5199\uff0c\u84dd\u8272\uff0c\u7ea2\u8272\u548c\u9ec4\u8272\u5206\u522b\u4ee3\u8868Healthy Control (HC), Alzheimer’s Disease (AD) \u548cOutlier, \u7eff\u8272\u76f4\u7ebf\u4ee3\u8868\u5206\u7c7b\u8d85\u5e73\u9762\u3002<\/p>\n\n\n\n \u56fe31\uff1a\u7eb5\u5411SMSI\u5fae\u7ed3\u6784\u6620\u5c04\u7ed3\u679c\u3002\u56fe\u4e2d\u5c55\u793a\u4e86\u67d0\u53d7\u8bd5\u8005\u7684\u7ec4\u7ec7\u5fae\u7ed3\u6784\u5728\u51fa\u751f\u540e\u768454\uff0c146\u548c223\u5929\u91cc\u7684\u53d8\u5316\u3002\u540c\u65f6\u4e5f\u5c55\u793a\u4e86\u53e6\u4e00\u53d7\u8bd5\u8005\u5728\u51fa\u751f\u540e\u7684318\uff0c410\u548c514\u5929\u91cc\u7684\u53d8\u5316\u3002 \u56fe32\uff1a\u6269\u6563\u53c2\u6570\u6620\u5c04\u7ed3\u679c\u3002\u9876\u90e8\u4e3a\u6269\u6563\u5cf0\u5ea6\u6210\u50cf\uff0c\u5e95\u90e8\u4e3a\u672c\u6587\u6240\u63d0\u51fa\u7684\u5fae\u89c2\u6269\u6563\u5cf0\u5ea6\u6210\u50cf\u3002<\/p>\n\n\n\n \u53c2\u8003\u6587\u732e<\/strong> \u5317\u5361\u7f57\u6765\u7eb3\u5927\u5b66\u6559\u5802\u5c71\u5206\u6821\uff08UNC-Cha…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[],"class_list":["post-200","post","type-post","status-publish","format-standard","hentry","category-7"],"_links":{"self":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/posts\/200","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/comments?post=200"}],"version-history":[{"count":0,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/posts\/200\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/media?parent=200"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/categories?post=200"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/tags?post=200"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\u4e3a\u4e86\u52a0\u5febMR Fingerprinting\uff08\u5b9a\u91cfMRI\u6210\u50cf\uff09\u7684\u6570\u636e\u91c7\u96c6\u901f\u5ea6\uff0cFang\u7b49\u4eba[1]\u63d0\u51fa\u4e86\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u56fe\u50cf\u751f\u6210\u6a21\u578b\uff0c\u7528\u66f4\u5c11\u7684\u91c7\u6837\u6570\u636e\u7cbe\u786e\u5730\u9884\u6d4bT1\/T2 MRI\u56fe\u50cf\u3002\u8be5\u6587\u63d0\u51fa\u4e86\u65b0\u9896\u7684Residual Channel Attention U-Net (RCA-U-Net) \u6a21\u578b\uff0c\u8be5\u6a21\u578b\u5728U-Net \u7684\u7ed3\u6784\u4e2d\u52a0\u5165\u4e86\u65b0\u7684Residual Channel Attention Block\uff0c\u4f7f\u751f\u6210\u7684\u56fe\u50cf\uff08\u56fe1\uff09\u6709\u66f4\u9ad8\u7684\u7cbe\u5ea6\u548c\u66f4\u597d\u7684\u7ec6\u8282\u3002\u91c7\u7528Leave-one-out\u4ea4\u53c9\u9a8c\u8bc1\uff0cRCA-U-Net \u6a21\u578b\u7684T1 map\u9884\u6d4b\u8bef\u5dee\u4f4e\u81f32%\uff5e4%\uff0cT2 map\u7684\u9884\u6d4b\u8bef\u5dee\u4f4e\u81f37%\uff5e8%\uff0c\u8fdc\u4f18\u4e8e\u4f20\u7edf\u7684Dictionary Matching\u548cU-Net\u65b9\u6cd5\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-3-15-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
2. Qu et al.,\u201cWavelet-Based Semi-Supervised Adversarial Learning for Synthesizing Realistic 7T from 3T MRI\u201d.<\/strong>
\u76f8\u6bd4\u4e8e3T MRI\u626b\u63cf\u4eea\uff0c7T MRI\u626b\u63cf\u4eea\u80fd\u63d0\u4f9b\u66f4\u9ad8\u7684\u7a7a\u95f4\u5206\u8fa8\u7387\u548c\u66f4\u591a\u7684\u89e3\u5256\u7ec6\u8282\u3002\u7136\u800c7T MRI\u626b\u63cf\u4eea\u9020\u4ef7\u9ad8\u6602\uff0c\u4e0d\u6613\u83b7\u5f97\u3002Qu\u7b49\u4eba[2]\u63d0\u51fa\u4e00\u79cd\u65b0\u9896\u7684\u57fa\u4e8e\u5c0f\u6ce2\u53d8\u6362\u7684\u534a\u76d1\u7763\u5bf9\u6297\u5b66\u4e60\u65b9\u6cd5\u4ece3T MR \u56fe\u50cf\u5408\u62107T MR\u56fe\u50cf\u3002\u4e0e\u73b0\u6709\u57fa\u4e8e\u76d1\u7763\u5b66\u4e60\u76847T MR\u56fe\u50cf\u751f\u6210\u65b9\u6cd5\u9700\u8981\u63d0\u4f9b\u5927\u91cf\u76843T-7T\u914d\u5bf9\u6570\u636e\u4e0d\u540c\uff0c\u8be5\u6587\u7684\u534a\u76d1\u7763\u5bf9\u6297\u6a21\u578b\u80fd\u591f\u5229\u7528\u5927\u91cf\u975e\u6210\u5bf9\u76843T\u548c7T MR\u56fe\u50cf\u6765\u63d0\u53477T MR\u56fe\u50cf\u5408\u6210\u7b97\u6cd5\u7684\u6027\u80fd\u3002\u8be5\u6a21\u578b\u5229\u7528\u8054\u5408\u7a7a\u95f4\u57df-\u5c0f\u6ce2\u57df\u7684\u5faa\u73af\u4e00\u81f4\u5bf9\u6297\u7f51\u7edc\u6765\u5b9e\u73b0\u534a\u76d1\u7763\u5b66\u4e60\uff0c\u5e76\u5c06\u7a7a\u95f4\u57df\u5185\u76847T MR\u56fe\u50cf\u5408\u6210\u4efb\u52a1\u8f6c\u6362\u4e3a\u8054\u5408\u7a7a\u95f4\u57df-\u5c0f\u6ce2\u57df\u5185\u7684\u5c0f\u6ce2\u7cfb\u6570\u9884\u6d4b\u4efb\u52a1\uff0c\u4ee5\u4fc3\u8fdb\u9ad8\u9891\u7ec6\u8282\u4fe1\u606f\u7684\u5408\u6210\u3002\u91c7\u7528Leave-one-out\u4ea4\u53c9\u9a8c\u8bc1\uff0c\u8be5\u7b97\u6cd5\u5728\u4ec5\u4f7f\u752828.5%\u7684\u914d\u5bf9\u6570\u636e\u548c71.5% \u7684\u975e\u914d\u5bf9\u6570\u636e\u7684\u60c5\u51b5\u4e0b, \u5e73\u5747Structural similarity\u503c\u8fbe\u52300.874\uff0c\u4f18\u4e8e\u73b0\u6709\u6700\u4f73\u7684\u5168\u76d1\u77637T\u56fe\u50cf\u751f\u6210\u7b97\u6cd5\u3002
3. Hong et al.,\u201cReconstructing High-Quality Diffusion MRI Data from Orthogonal Slice-Undersampled Data Using Graph Convolutional Neural Networks\u201d.<\/strong>
\u5f25\u6563\u78c1\u5171\u632f\u6210\u50cf\uff08Diffusion MRI\uff09\u6280\u672f\u5728\u8111\u7ec4\u7ec7\u5fae\u7ed3\u6784\u7684\u7814\u7a76\u4e2d\u6709\u7740\u91cd\u8981\u7684\u5e94\u7528\u4ef7\u503c\uff0c\u4f46\u662f\u8fc7\u957f\u7684\u6210\u50cf\u65f6\u95f4\u5236\u7ea6\u7740\u5b83\u7684\u5e7f\u6cdb\u5e94\u7528\u3002\u4e3a\u4e86\u89e3\u51b3\u8be5\u95ee\u9898\uff0cHong\u7b49\u4eba[3]\u63d0\u51fa\u4e86\u4e00\u79cd\u57fa\u4e8e\u6b63\u4ea4\u6b20\u91c7\u6837\u5f25\u6563\u52a0\u6743\u56fe\u50cf\u7684\u8d85\u5206\u8fa8\u7387\u91cd\u6784\u65b9\u6cd5\u3002\u8be5\u65b9\u6cd5\u4ec5\u9700\u4e00\u90e8\u5206\u7b49\u8ddd\u6b20\u91c7\u6837\u7684\u5f25\u6563\u52a0\u6743\u56fe\u50cf\uff0c\u4ece\u800c\u6709\u6548\u5730\u51cf\u5c11\u4e86\u6210\u50cf\u65f6\u95f4\u3002\u8be5\u9879\u7814\u7a76\u5de5\u4f5c\u8bc1\u5b9e\u4e86\u6b20\u91c7\u6837\u5f25\u6563\u52a0\u6743\u56fe\u50cf\u95f4\u7684\u4e92\u8865\u4fe1\u606f\u53ef\u88ab\u7528\u4e8e\u57fa\u4e8e\u56fe\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u7684\u8d85\u5206\u8fa8\u7387\u91cd\u6784\uff08\u6846\u67b6\u5982\u56fe2\u6240\u793a\uff09\u3002\u8be5\u6587\u91c7\u7528\u4e864\u6298\u4ea4\u53c9\u9a8c\u8bc1\uff0c\u6240\u63d0\u51fa\u7684\u8d85\u5206\u8fa8\u7387\u91cd\u6784\u65b9\u6cd5\u4f18\u4e8e\u4f20\u7edf\u7684\u63d2\u503c\u65b9\u6cd5\uff0c\u5e76\u4e14\u6709\u6548\u5730\u7f13\u89e3\u4e86\u90e8\u5206\u5bb9\u79ef\u6548\u5e94\u3002\u5b9e\u9a8c\u7ed3\u679c\u663e\u793a\u6240\u63d0\u51fa\u65b9\u6cd5\u53ef\u4ee5\u53d6\u5f97\u9ad8\u8fbe5\u500d\u6548\u7387\u7684\u6210\u50cf\u52a0\u901f\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-5-13-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\u81ea\u52a8\u4e14\u5feb\u901f\u7684\u5f25\u6563\u78c1\u5171\u632f\uff08Diffusion MRI\uff09\u56fe\u50cf\u8d28\u91cf\u8bc4\u4f30\u5bf9\u4e8e\u5728\u626b\u63cf\u8fc7\u7a0b\u4e2d\u6216\u626b\u63cf\u540e\u5feb\u901f\u505a\u51fa\u91cd\u626b\u63cf\u51b3\u7b56\u81f3\u5173\u91cd\u8981\uff0c\u4f46\u6807\u6ce8\u7684\u6570\u636e\u6570\u91cf\u6781\u5176\u6709\u9650\u4e14\u6807\u7b7e\u5e76\u4e0d\u90fd\u5b8c\u7f8e\u3002Liu\u7b49\u4eba[4]\u63d0\u51fa\u4e86\u4e00\u79cd\u5305\u62ec\u5207\u7247\u7ea7\u3001\u4f53\u7ea7\u53ca\u5bf9\u8c61\u7ea7\u7684\u4e09\u9636\u987a\u6b21\u8d28\u91cf\u8bc4\u4f30\u6a21\u578b\uff0c\u8be5\u6a21\u578b\u91c7\u7528\u4e00\u79cd\u975e\u5c40\u90e8\u6b8b\u5dee\u7f51\u7edc\u5b9e\u73b0\u5207\u7247\u7ea7\u8d28\u91cf\u8bc4\u4f30\uff0c\u91c7\u7528\u4e00\u79cd\u975e\u5c40\u90e8\u7f51\u7edc\u805a\u5408\u5355\u4f53\u4e2d\u6240\u6709\u5207\u7247\u7684\u7279\u5f81\u5b9e\u73b0\u4f53\u7ea7\u8d28\u91cf\u8bc4\u4f30\uff0c\u96c6\u5408\u5355\u5bf9\u8c61\u4e2d\u6240\u6709\u4f53\u7684\u8d28\u91cf\u7ed3\u679c\u5b9e\u73b0\u5bf9\u8c61\u7ea7\u8d28\u91cf\u8bc4\u4f30\u3002\u4e3a\u4e86\u5145\u5206\u5229\u7528\u5c11\u91cf\u7684\u6807\u6ce8\u6570\u636e\u548c\u5927\u91cf\u7684\u672a\u6807\u6ce8\u6570\u636e\uff0c\u91c7\u7528\u534a\u76d1\u7763\u5b66\u4e60\u8bad\u7ec3\u975e\u5c40\u90e8\u6b8b\u5dee\u7f51\u7edc\u548c\u975e\u5c40\u90e8\u7f51\u7edc\u3002\u4e3a\u4e86\u89e3\u51b3\u6570\u636e\u6807\u7b7e\u566a\u58f0\uff0c\u8bbe\u8ba1\u4e86\u4e00\u79cd\u81ea\u8bad\u7ec3\u7b56\u7565\uff0c\u5728\u8bad\u7ec3\u7f51\u7edc\u65f6\u8fed\u4ee3\u5730\u91cd\u65b0\u6807\u8bb0\u548c\u5220\u9664\u6807\u8bb0\u7684\u6570\u636e\u96c6\uff08\u6846\u67b6\u5982\u56fe3\u6240\u793a\uff09\u3002\u8be5\u6587\u63d0\u51fa\u7684\u65b9\u6cd5\u4ec5\u4f7f\u7528\u8f83\u5c0f\u7684\u6837\u672c\u8fdb\u884c\u8bad\u7ec3\uff0c\u5177\u6709\u5f88\u5f3a\u7684\u6cdb\u5316\u80fd\u529b\uff0c\u80fd\u591f\u4ee5\u8fd1\u4e4e\u5b8c\u7f8e\u7684\u7cbe\u5ea6\u8fdb\u884c\u5927\u89c4\u6a21\u7684\u5feb\u901f\u8d28\u91cf\u8bc4\u4f30\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-5-14-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\u56fe\u50cf\u5408\u6210\u6280\u672f\u6709\u671b\u89e3\u51b3\u5728\u57fa\u4e8e\u591a\u6a21\u6001\u6570\u636e\u7684\u75be\u75c5\u8bca\u65ad\u4e2d\u5b58\u5728\u7684\u6570\u636e\u7f3a\u5931\u95ee\u9898\uff0c\u4f46\u73b0\u6709\u7684\u56fe\u50cf\u5408\u6210\u6a21\u578b\u751f\u6210\u7684\u56fe\u50cf\u548c\u771f\u5b9e\u56fe\u50cf\u5f80\u5f80\u5728\u5206\u7c7b\u4efb\u52a1\u4e2d\u6709\u8f83\u5927\u7684\u6027\u80fd\u5dee\u5f02\u3002Pan\u7b49\u4eba[5]\u5c06\u7f3a\u5931\u56fe\u50cf\u751f\u6210\u548c\u75be\u75c5\u8bca\u65ad\u4e24\u4e2a\u95ee\u9898\u8054\u5408\u8d77\u6765\u5e76\u6784\u5efa\u4e00\u4e2a\u7edf\u4e00\u7684\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\u3002\u8be5\u6587\u9996\u5148\u57fa\u4e8e\u5355\u6a21\u6001\u7684\u6570\u636e\u8bad\u7ec3\u4e00\u4e2a\u5305\u542b5\u5c42\u5377\u79ef\u5c42\u7684\u8bca\u65ad\u6a21\u578b\uff0c\u8be5\u6a21\u578b\u6bcf\u5c42\u7684\u7279\u5f81\u90fd\u80fd\u4e0d\u540c\u7a0b\u5ea6\u53cd\u6620\u51fa\u75be\u75c5\u4fe1\u606f\u3002\u7136\u540e\uff0c\u901a\u8fc7\u7ea6\u675f\u751f\u6210\u6a21\u578b\u4f7f\u5176\u751f\u6210\u7684\u56fe\u50cf\u548c\u771f\u5b9e\u56fe\u50cf\u5728\u8bca\u65ad\u6a21\u578b\u4e0a\u7684\u7279\u5f81\u4fdd\u6301\u4e00\u81f4\uff08\u6846\u67b6\u5982\u56fe4\u6240\u793a\uff09\u3002\u8be5\u6587\u5728ADNI\u4e0a\u76841466\u4f8b\u6837\u672c\u4e0a\u8fdb\u884c\u4e86\u6d4b\u8bd5\uff0c\u5b9e\u9a8c\u7ed3\u679c\u8868\u660e\u8be5\u65b9\u6cd5\u4e0d\u4ec5\u80fd\u751f\u6210\u66f4\u52a0\u5408\u7406\u7684\u5927\u8111\u5f71\u50cf\uff0c\u540c\u65f6\u663e\u8457\u63d0\u5347\u4e86\u963f\u5179\u6d77\u9ed8\u75c7\u7684\u81ea\u52a8\u9884\u6d4b\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-5-15-1-1.png\")
<\/figure>\n<\/div>\n\n\n
6.\u00a0\u00a0 \u00a0Huang et al.,\u201cCoCa-GAN: Common-feature-learning-based Context-aware Generative Adversarial Network for Glioma Grading\u201d.<\/strong>
\u591a\u6a21\u6001\u8111\u80bf\u7624MRI\u5f71\u50cf\u53ef\u66f4\u597d\u5730\u534f\u52a9\u8bca\u65ad\u548c\u6cbb\u7597\uff0c\u4f46\u901a\u5e38\u4f1a\u5b58\u5728\u6a21\u6001\u7f3a\u5931\u95ee\u9898\u3002\u4e3a\u89e3\u51b3\u901a\u8fc7T1w MRI\u751f\u6210\u5176\u4ed6\u6a21\u6001MRI\u7684\u56fe\u50cf\u5408\u6210\u95ee\u9898\uff0cHuang\u7b49\u4eba[6]\u63d0\u51fa\u4e86\u65b0\u9896\u7684\u57fa\u4e8e\u5171\u7279\u5f81\u7a7a\u95f4\u5b66\u4e60 (Common feature learning) \u548c\u4e0a\u4e0b\u6587\u4fe1\u606f (Context-aware) \u7684\u4e09\u7ef4\u751f\u6210\u5f0f\u5bf9\u6297\u7f51\u7edc\u6a21\u578b (CoCa-GAN) \u3002\u8be5\u6a21\u578b\u91c7\u7528\u4e00\u4e2a\u7f16\u7801\u5668\u4ea7\u751f\u5171\u7279\u5f81\u7a7a\u95f4\uff0c\u591a\u4e2a\u89e3\u7801\u5668\u4ea7\u751f\u591a\u79cd\u6a21\u6001\u7684\u76ee\u6807\u56fe\u50cf\u3002\u8be5\u6587\u5229\u7528\u5bf9\u6297\u5b66\u4e60\u6765\u8f85\u52a9\u5b66\u4e60\u5171\u7279\u5f81\u7a7a\u95f4\uff0c\u501f\u52a9\u57fa\u4e8e\u8fb9\u7f18\u4fe1\u606f\u548c\u80bf\u7624\u533a\u57df\u4e0a\u4e0b\u6587\u4fe1\u606f\u7684\u7ea6\u675f\u5e2e\u52a9\u635f\u5931\u51fd\u6570\u6536\u655b\uff0c\u5e76\u589e\u5f3a\u5171\u7279\u5f81\u7a7a\u95f4\u5bf9\u56fe\u50cf\u7ec6\u8282\u5c24\u5176\u662f\u80bf\u7624\u533a\u57df\u7684\u8868\u5f81\u80fd\u529b\u3002\u8be5\u6a21\u578b\u8f93\u5165T1w MRI\uff0c\u901a\u8fc7\u8fed\u4ee3\u5f0f\u8bad\u7ec3\u4f7f\u5171\u7279\u5f81\u7a7a\u95f4\u5b66\u4e60\u5230\u591a\u6a21\u6001\u56fe\u50cf\u95f4\u7684\u4e92\u8865\u4fe1\u606f\uff0c\u4ee5\u589e\u5f3a\u4ec5\u4f7f\u7528\u5355\u4e00T1w MRI\u65f6\u7684\u56fe\u50cf\u5408\u6210\u80fd\u529b\uff08\u56fe5\uff09\u3002\u91c7\u7528BraTS2015\u6570\u636e\u96c6\u8fdb\u884c\u5b9e\u9a8c\uff0c\u7ed3\u679c\u663e\u8457\u4f18\u4e8e\u5176\u4ed6\u65b9\u6cd5\uff08\u56fe6\uff09\u3002\u8be5\u65b9\u6cd5\u53ef\u5728\u6709\u9650\u4fe1\u606f\u7684\u60c5\u51b5\u4e0b\uff0c\u901a\u8fc7\u4ea7\u751f\u66f4\u591a\u6a21\u6001\u7684\u56fe\u50cf\u534f\u52a9\u533b\u751f\u5bf9\u8111\u80bf\u7624\u75c5\u4eba\u7efc\u5408\u8bca\u65ad\u548c\u8bc4\u4f30\uff0c\u5e76\u66f4\u52a0\u6709\u6548\u7684\u8fdb\u884c\u6cbb\u7597\u65b9\u6cd5\u89c4\u5212\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-5-16-1-1.png\")
<\/figure>\n<\/div>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-5-17-1-1.png\")
<\/figure>\n<\/div>\n\n\n
7.\u00a0\u00a0 \u00a0Wei et al.,\u201cSynthesis and Inpainting-based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors\u201d.<\/strong>
\u809d\u810f\u80bf\u7624\u7684\u70ed\u6d88\u878d\u624b\u672f\u76ee\u7684\u5728\u4e8e\u5c3d\u53ef\u80fd\u6d88\u878d\u80bf\u7624\u7ec4\u7ec7\u7684\u540c\u65f6\u4fdd\u8bc1\u5468\u56f4\u6b63\u5e38\u7ec4\u7ec7\u4e0d\u88ab\u7834\u574f\u3002\u624b\u672f\u4e2d\u6d88\u878d\u9488\u7684\u7a7f\u523a\u5728\u56fe\u50cf\u5f15\u5bfc\u4e0b\u8fdb\u884c\uff0c\u7cbe\u786e\u7684\u7a7f\u523a\u624b\u672f\u9700\u8981\u5c06\u672f\u524d\u548c\u672f\u4e2d\u7684\u56fe\u50cf\u8fdb\u884c\u914d\u51c6\u3002\u672f\u524d\u548c\u672f\u4e2d\u91c7\u7528\u7684\u5f71\u50cf\u6a21\u6001\u4e0d\u540c\u3001\u809d\u810f\u7b49\u7ec4\u7ec7\u5728\u4e24\u4e2a\u65f6\u95f4\u70b9\u53d1\u751f\u7684\u8f83\u5927\u5f62\u53d8\u7b49\u539f\u56e0\uff0c\u90fd\u589e\u52a0\u4e86\u672f\u524d\u548c\u672f\u4e2d\u5f71\u50cf\u914d\u51c6\u7684\u6311\u6218\u6027\u3002\u672f\u524dMR\uff08pMR\uff09\u5f71\u50cf\u5bf9\u4e8e\u80bf\u7624\u7b49\u8f6f\u7ec4\u7ec7\u5177\u6709\u8f83\u9ad8\u5206\u8fa8\u7387\uff0c\u4f46\u6210\u50cf\u65f6\u95f4\u76f8\u5bf9\u8f83\u957f\uff1b\u672f\u4e2d CT\uff08iCT\uff09\u5f71\u50cf\u6210\u50cf\u65f6\u95f4\u76f8\u5bf9\u8f83\u5feb\uff0c\u53ef\u4ee5\u5b9e\u65f6\u53cd\u9988\u7a7f\u523a\u4f4d\u7f6e\uff0c\u4f46\u662f\u5bf9\u80bf\u7624\u7b49\u8f6f\u7ec4\u7ec7\u5206\u8fa8\u7387\u8f83\u5dee\uff0c\u540c\u65f6\u91d1\u5c5e\u7a7f\u523a\u9488\u4f1a\u4ea7\u751f\u4e25\u91cd\u7684\u4f2a\u5f71\uff0c\u5f88\u53ef\u80fd\u5b8c\u5168\u906e\u6321\u4e86\u80bf\u7624\u672c\u8eab\u3002Wei\u7b49\u4eba[7]\u63d0\u51fa\u57fa\u4e8e\u56fe\u50cf\u5408\u6210\u548c\u4fee\u590d\u7684MR-CT\u56fe\u50cf\u914d\u51c6\u7684\u65b9\u6cd5\uff08\u56fe7\uff09\u3002\u5728\u672f\u524d\u73af\u8282\uff0c\u901a\u8fc7\u57fa\u4e8eCycle-GAN\u7684\u65b9\u6cd5\u628aMR-CT\uff08pMR-pCT\uff09\u8de8\u6a21\u6001\u7684\u914d\u51c6\u95ee\u9898\u8f6c\u53d8\u4e3a Synthesized CT (sCT)-CT\uff08sCT-pCT\uff09\u7684\u540c\u6a21\u6001\u914d\u51c6\u95ee\u9898\u3002\u5728\u672f\u4e2d\u73af\u8282\uff0c\u57fa\u4e8e\u56fe\u50cf\u4fee\u590d\u6709\u6548\u53bb\u9664\u672f\u524dCT\uff08pCT\uff09\u4e2d\u91d1\u5c5e\u7a7f\u523a\u9488\u53ca\u5176\u4f2a\u5f71\u5f97\u5230\u4fee\u590d\u540e\u7684CT\uff08inpCT\uff09\uff08\u8017\u65f6\u4ec5\uff5e2s\uff09\uff0c\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u914d\u51c6\u7f51\u7edc\uff08UR-Net\uff09\u53ef\u4ee5\u57283s\u5de6\u53f3\u5b8c\u6210\uff08inpCT-pCT\uff09\u56fe\u50cf\u914d\u51c6\u3002\u8be5\u6587\u63d0\u51fa\u7684\u65b9\u6cd5\u53ef\u4ee5\u5feb\u901f\u51c6\u786e\u5730\u5b8c\u6210\u672f\u524dMR\u548c\u672f\u4e2dCT\u56fe\u50cf\u7684\u914d\u51c6\uff08\u56fe8\uff09\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-3-16-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-5-18-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\n\n\n\n
\u73b0\u6709\u7684\u5927\u8111\u76ae\u5c42\u611f\u5174\u8da3\u533a\u57df\u5212\u5206\u65b9\u6cd5\u9700\u8981\u9996\u5148\u5c06\u5927\u8111\u76ae\u5c42\uff08\u901a\u5e38\u7531\u4e09\u89d2\u5f62\u7f51\u683c\u8868\u793a\uff09\u901a\u8fc7\u4fdd\u89d2\u548c\u4fdd\u8ddd\u6620\u5c04\u81f3\u7403\u9762\uff0c\u8fdb\u800c\u5728\u7403\u9762\u4e0a\u8fdb\u884c\u533a\u57df\u5212\u5206\uff08\u56e0\u4e3a\u7403\u9762\u5177\u6709\u7b80\u5355\u4e14\u6613\u4e8e\u914d\u51c6\u7684\u4f18\u70b9\uff09\u3002\u8be5\u6620\u5c04\u8981\u6c42\u5927\u8111\u76ae\u5c42\u66f2\u9762\u62d3\u6251\u7b49\u4ef7\u4e8e\u7403\u9762\uff0c\u7136\u800c\u5b9e\u9645\u60c5\u51b5\u4e2d\uff0c\u4e00\u65b9\u9762\u8be5\u6620\u5c04\u8d39\u65f6\u4e14\u96be\u514d\u4ea7\u751f\u7578\u53d8\uff1b\u53e6\u4e00\u65b9\u9762\uff0c\u8be5\u6620\u5c04\u65e0\u6cd5\u5e94\u7528\u4e8e\u5177\u6709\u975e\u7403\u9762\u62d3\u6251\u7684\u975e\u6b63\u5e38\u76ae\u5c42\u66f2\u9762\uff0c\u4f8b\u5982\u505a\u8fc7\u80bf\u7624\u5207\u9664\u624b\u672f\u7684\u5927\u8111\u76ae\u5c42\uff1b\u56e0\u800c\u9650\u5236\u4e86\u73b0\u6709\u76ae\u5c42\u533a\u57df\u5212\u5206\u65b9\u6cd5\u7684\u9002\u7528\u8303\u56f4\u3002Wu\u7b49\u4eba[8]\u63d0\u51fa\u4e00\u79cd\u5728\u539f\u59cb\u76ae\u5c42\u66f2\u9762\u8fdb\u884c\u5927\u8111\u76ae\u5c42\u533a\u57df\u5212\u5206\u7684\u65b9\u6cd5\uff0c\u501f\u52a9\u4e8e\u56fe\u5377\u79ef\u7f51\u7edc\u76f4\u63a5\u5728\u76ae\u5c42\u66f2\u9762\u4e0a\u8bad\u7ec3\u5206\u7c7b\u5668\u6765\u8fdb\u884c\u76ae\u5c42\u533a\u57df\u5212\u5206\uff0c\u907f\u514d\u4e86\u7403\u9762\u6620\u5c04\uff0c\u89e3\u51b3\u4e86\u5bf9\u975e\u7403\u9762\u62d3\u6251\u7684\u5927\u8111\u76ae\u5c42\u533a\u57df\u5212\u5206\u95ee\u9898\u3002\u5b9e\u9a8c\u4e2d\uff0c\u8be5\u6587\u5c06\u6b63\u5e38\u5a74\u513f\u5927\u8111\u6a21\u62df\u5207\u9664\u4e00\u90e8\u5206\u4f7f\u5176\u4e0d\u518d\u5177\u6709\u7403\u9762\u62d3\u6251\uff0c\u8fdb\u800c\u5229\u7528\u6240\u63d0\u65b9\u6cd5\u8fdb\u884c\u76ae\u5c42\u533a\u57df\u5212\u5206\u3002\u901a\u8fc7\u6bd4\u8f83\u672a\u5207\u9664\u5927\u8111\u7684\u5212\u5206\u533a\u57df\u4e0e\u5207\u9664\u4ee5\u540e\u7684\u5212\u5206\u533a\u57df\uff0c\u4e24\u8005\u5728\u672a\u5207\u9664\u533a\u57df\u5177\u6709\u9ad8\u5ea6\u91cd\u5408\u6027\uff0c\u4ece\u800c\u9a8c\u8bc1\u8be5\u6587\u6240\u63d0\u65b9\u6cd5\u6709\u6548\u9002\u7528\u4e0e\u975e\u7403\u9762\u62d3\u6251\u7684\u5927\u8111\u76ae\u5c42\uff08\u56fe9\uff09\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-3-17-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
9.\u00a0\u00a0 \u00a0Taylor et al.,\u201cAutomated Parcellation of the Cortex Using Structural Connectome Harmonics\u201d.<\/strong>
\u7ecf\u5178\u7684\u5927\u8111\u76ae\u5c42\u8111\u533a\u5212\u5206\u901a\u5e38\u5229\u7528\u89e3\u5256\u5b66\u6807\u8bb0\uff08\u6c9f\u56de\u4fe1\u606f\uff09\u6216\u8005\u529f\u80fd\u8fde\u63a5\u4fe1\u606f\uff08\u57fa\u4e8e\u529f\u80fd\u78c1\u5171\u632f\u56fe\u50cf\uff0c\u4ee5\u4e0d\u540c\u76ae\u5c42\u533a\u57df\u7684\u65f6\u95f4\u6d3b\u52a8\u76f8\u5173\u5ea6\u6765\u8fdb\u884c\u8111\u533a\u5212\u5206\uff09\u3002\u5386\u53f2\u6587\u732e\u4e2d\uff0c\u4ee5\u5f25\u6563\u5f20\u91cf\u56fe\u50cf\u4f5c\u4e3a\u51fa\u53d1\u70b9\u6765\u8fdb\u884c\u8111\u533a\u5212\u5206\u7684\u7814\u7a76\u8f83\u5c11\u3002\u4e8b\u5b9e\u4e0a\uff0c\u7531\u5f25\u6563\u5f20\u91cf\u56fe\u50cf\u6240\u6784\u5efa\u51fa\u7684\u5927\u8111\u767d\u8d28\u7ea4\u7ef4\u675f\u63d0\u4f9b\u4e86\u6bd4\u529f\u80fd\u8fde\u63a5\u66f4\u4e3a\u76f4\u63a5\u548c\u53ef\u9760\u7684\u5168\u8111\u7684\u7ed3\u6784\u8fde\u63a5\u4fe1\u606f\uff0c\u4ece\u800c\u4f7f\u5f97\u5229\u7528\u5168\u8111\u7ed3\u6784\u8fde\u63a5\u8fdb\u884c\u5927\u8111\u76ae\u5c42\u7684\u8111\u533a\u5212\u5206\u6210\u4e3a\u53ef\u80fd\u3002Taylor\u7b49\u4eba[9]\u7531\u5f25\u6563\u5f20\u91cf\u56fe\u50cf\u6240\u91cd\u5efa\u7684\u5927\u8111\u7ea4\u7ef4\u675f\u6765\u6784\u5efa\u5927\u5c3a\u5ea6\uff08\u6700\u5c0f\u5355\u4f4dvertex\uff0c\u517164,984\u4e2avertices\uff09\u8111\u76ae\u5c42\u7ed3\u6784\u8fde\u63a5\u77e9\u9635\uff0c\u8fdb\u800c\u5229\u7528\u62c9\u666e\u62c9\u65af\u53d8\u6362\u6765\u63a2\u5bfb\u5168\u8111\u89e3\u5256\u8fde\u63a5\u7684\u591a\u5c3a\u5ea6\u7ed3\u6784\u6027\u4fe1\u606f\uff0c\u627e\u51fa\u76ae\u5c42\u7684\u4e0d\u540c\u7a7a\u95f4\u4f4d\u7f6e\u4e0a\u7684\u76f8\u4f3c\u89e3\u5256\u8fde\u63a5\u60c5\u51b5\uff0c\u4ece\u800c\u5bf9\u5927\u8111\u76ae\u5c42\u8fdb\u884c\u7cbe\u7ec6\u5212\u5206\u3002\u5bf9\u4e8e\u4e0d\u540c\u88ab\u8bd5\u5927\u8111\u96be\u4ee5\u907f\u514d\u7684\u5dee\u5f02\u6027\uff0c\u91c7\u7528\u591a\u5c42\u7f51\u7edc\u5206\u6790\u7684\u65b9\u6cd5\u63a2\u5bfb\u591a\u88ab\u8bd5\u4e4b\u95f4\u76f8\u4f3c\u7684\u7ed3\u6784\u8fde\u63a5\uff0c\u4ee5\u6b64\u8fdb\u884c\u66f4\u52a0\u9c81\u68d2\u548c\u66f4\u5177\u666e\u9002\u6027\u7684\u5927\u8111\u76ae\u5c42\u5212\u5206\uff08\u56fe10\uff09\u3002\u5728HCP\u516c\u5f00\u6570\u636e\u96c6\u4e0a\u7684\u6d4b\u8bd5\u7ed3\u679c\u8868\u660e\uff0c\u8be5\u8111\u533a\u5212\u5206\u7ed3\u679c\u4e0e\u7ecf\u5178\u7684\u6839\u636e\u529f\u80fd\u78c1\u5171\u632f\u56fe\u50cf\u7684\u8111\u533a\u5212\u5206\u5177\u6709\u9ad8\u5ea6\u7684\u76f8\u4f3c\u6027\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-3-18-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
10.\u00a0\u00a0 \u00a0Ahmad et al.,\u201cSurface-Volume Consistent Construction of Longitudinal Atlases for the Early Developing Brains\u201d.<\/strong>
\u5a74\u513f\u5927\u8111\u56fe\u8c31\u5bf9\u4e8e\u7814\u7a76\u5a74\u513f\u5927\u8111\u53d1\u80b2\u5177\u6709\u91cd\u8981\u610f\u4e49\u3002\u4f20\u7edf\u65b9\u6cd5\u901a\u5e38\u5206\u522b\u6784\u5efa\u5927\u8111\u4f53\u6570\u636e\u4e0e\u5927\u8111\u76ae\u5c42\u6570\u636e\u4e24\u79cd\u56fe\u8c31\u3002\u7136\u800c\uff0c\u7531\u4e8e\u4e24\u8005\u5728\u914d\u51c6\u7ed3\u679c\u4e0a\u7684\u4e0d\u540c\uff0c\u5f80\u5f80\u5bfc\u81f4\u4ece\u4e0d\u540c\u89d2\u5ea6\u6784\u5efa\u7684\u5927\u8111\u56fe\u8c31\u5177\u6709\u5dee\u5f02\u6027\u3002Ahmad\u7b49\u4eba[10]\u540c\u65f6\u4ece\u5927\u8111\u4f53\u6570\u636e\u548c\u76ae\u5c42\u6570\u636e\u51fa\u53d1\uff0c\u4ee5\u5927\u8111\u76ae\u5c42\u6570\u636e\u7684\u914d\u51c6\u6765\u5f15\u5bfc\u5927\u8111\u4f53\u6570\u636e\u7684\u914d\u51c6\uff0c\u8fdb\u800c\u5f97\u5230\u4e86\u5927\u8111\u4f53\u6570\u636e\u548c\u76ae\u5c42\u6570\u636e\u4e00\u81f4\u7684\u914d\u51c6\u7ed3\u679c\u3002\u5728\u6b64\u57fa\u7840\u4e0a\uff0c\u8be5\u6587\u9996\u5148\u6784\u5efa\u4e8612\u4e2a\u6708\u5a74\u513f\u7684\u5927\u8111\u4f53\u6570\u636e\u548c\u76ae\u5c42\u6570\u636e\u7684\u56fe\u8c31\uff0c\u5176\u5177\u6709\u4f53\u6570\u636e\u548c\u76ae\u5c42\u6570\u636e\u4e00\u81f4\u7684\u4f18\u70b9\u3002\u800c\u540e\uff0c\u8be5\u6587\u8fdb\u4e00\u6b65\u5c06\u6784\u5efa\u768412\u4e2a\u6708\u7684\u56fe\u8c31\u4f9d\u6b64\u8fc1\u79fb\u523012\u4e2a\u6708\u4e4b\u524d\u7684\u6570\u636e\u4e0a\uff0c\u8fdb\u800c\u6784\u5efa\u51fa\u9010\u6708\u95f4\u9694\u7684\u4ece\u5a74\u513f\u51fa\u751f\u76f4\u523012\u4e2a\u6708\u7684\u56fe\u8c31\u96c6\u5408\uff08\u56fe11\uff09\u3002\u76f8\u6bd4\u4e8e\u4f20\u7edf\u65b9\u6cd5\u6784\u5efa\u7684\u56fe\u8c31\uff0c\u8be5\u6587\u6240\u6784\u5efa\u7684\u5a74\u513f\u56fe\u8c31\u5728\u65f6\u95f4\u8f74\u4e0a\u5177\u6709\u66f4\u597d\u7684\u76f8\u5173\u6027\uff1b\u540c\u65f6\uff0c\u8be5\u6587\u6240\u6784\u5efa\u7684\u4f53\u6570\u636e\u56fe\u8c31\u4e0e\u5927\u8111\u76ae\u5c42\u6570\u636e\u56fe\u8c31\u5177\u6709\u66f4\u597d\u7684\u4e00\u81f4\u6027\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-3-19-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
11.\u00a0\u00a0 \u00a0Wang et al.,\u201cRevealing Developmental Regionalization of Infant Cerebral Cortex Based on Multiple Cortical Properties\u201d.<\/strong>
\u5a74\u513f\u5927\u8111\u5728\u51fa\u751f\u5230\u4e24\u5c81\u4e4b\u95f4\u7684\u5feb\u901f\u53d1\u80b2\u8868\u73b0\u51fa\u7a7a\u95f4\u4e0a\u7684\u5f02\u8d28\u6027\uff0c\u800c\u636e\u6b64\u52fe\u753b\u51fa\u7684\u5927\u8111\u533a\u57df\u5212\u5206\u4e0e\u8111\u76ae\u5c42\u7684\u5fae\u89c2\u7ed3\u6784\u4e0e\u529f\u80fd\u5bc6\u5207\u76f8\u5173\u3002\u8003\u8651\u5230\u4e0d\u540c\u7684\u76ae\u5c42\u5c5e\u6027\u80fd\u591f\u63d0\u4f9b\u4e92\u8865\u7684\u4fe1\u606f\uff0c\u901a\u8fc7\u591a\u4e2a\u89c6\u89d2\uff08\u591a\u4e2a\u76ae\u5c42\u5c5e\u6027\uff09\u52fe\u753b\u51fa\u7684\u5927\u8111\u533a\u57df\u5212\u5206\u5219\u80fd\u66f4\u52a0\u5b8c\u6574\u5730\u523b\u753b\u6b64\u79cd\u7a7a\u95f4\u4e0a\u7684\u5f02\u8d28\u6027\u3002\u56e0\u6b64Wang\u7b49\u4eba[11]\u63d0\u51fa\u4e86\u4e00\u79cd\u591a\u89c6\u89d2\u975e\u8d1f\u77e9\u9635\u5206\u89e3\u65b9\u6cd5\uff0c\u6709\u6548\u5730\u7efc\u5408\u8003\u8651\u591a\u4e2a\u8111\u76ae\u5c42\u5c5e\u6027\u6765\u7efc\u5408\u7ed8\u5236\u5a74\u513f\u5927\u8111\u533a\u57df\u5212\u5206\u3002\u8be5\u65b9\u6cd5\u540c\u65f6\u5f15\u5165\u4e86\u6b63\u4ea4\u7ea6\u675f\u4e0e\u56fe\u7ea6\u675f\uff0c\u4f7f\u5f97\u5f97\u5230\u7684\u4e0d\u540c\u8111\u533a\u5206\u4e92\u76f8\u72ec\u7acb\uff0c\u5e76\u4e14\u6bcf\u4e2a\u8111\u533a\u7a7a\u95f4\u5206\u5e03\u8f83\u4e3a\u96c6\u4e2d\uff0c\u4ece\u800c\u65b9\u4fbf\u540e\u7eed\u7684\u4ee5\u8111\u533a\u4e3a\u5355\u4f4d\u7684\u5206\u6790\uff08\u56fe12\uff09\u3002\u8be5\u6587\u6240\u53d1\u73b0\u7684\u67d0\u4e9b\u8111\u533a\u4e0e\u5148\u524d\u7684\u57fa\u4e8e\u57fa\u56e0\u6216\u9752\u5c11\u5e74\u53d1\u80b2\u7684\u5927\u8111\u8111\u533a\u5212\u5206\u8f83\u4e3a\u4e00\u81f4\uff0c\u8bc1\u660e\u4e86\u8be5\u6587\u901a\u8fc7\u591a\u89c6\u89d2\u975e\u8d1f\u77e9\u9635\u5206\u89e3\u7ed8\u5236\u51fa\u7684\u5a74\u513f\u5927\u8111\u8111\u533a\u5212\u5206\u5728\u795e\u7ecf\u79d1\u5b66\u4e0a\u7684\u610f\u4e49\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-4-10-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
12.\u00a0\u00a0 \u00a0Zhao et al.,\u201cHarmonization of Infant Cortical Thickness using Surface-to-Surface Cycle-Consistent Adversarial Networks\u201d.<\/strong>
\u5728\u795e\u7ecf\u5f71\u50cf\u5206\u6790\u4e2d\uff0c\u4e3a\u4e86\u89e3\u51b3\u4e0d\u540c\u78c1\u5171\u632f\u626b\u63cf\u4eea\u5bf9\u5927\u8111\u6210\u50cf\u7684\u975e\u751f\u7269\u56e0\u7d20\u5f71\u54cd\uff08\u6bd4\u5982\u78c1\u573a\u5f3a\u5ea6\u3001\u5206\u8fa8\u7387\u3001\u54c1\u724c\u7b49\uff09\uff0c\u5bf9\u4e0d\u540c\u626b\u63cf\u4eea\u6240\u83b7\u53d6\u78c1\u5171\u632f\u56fe\u50cf\u8ba1\u7b97\u51fa\u7684\u5927\u8111\u76ae\u5c42\u5c5e\u6027\u8fdb\u884charmonization \u5341\u5206\u6709\u5fc5\u8981\u3002Zhao\u7b49\u4eba[12]\u9996\u6b21\u5c06Cycle-GAN\u7684\u601d\u60f3\u5e94\u7528\u4e8e\u5927\u8111\u76ae\u5c42\u5c5e\u6027\u7684harmonization\u95ee\u9898\u4e0a\u3002\u8be5\u6587\u9996\u5148\u5c06\u5927\u8111\u76ae\u5c42\u6295\u5f71\u5230\u7403\u9762\uff0c\u7528icosahedron\u79bb\u6563\u5316\u7684\u7403\u9762\u6765\u8868\u793a\u76ae\u5c42\u548c\u5176\u5c5e\u6027\u6570\u636e (\u6bd4\u5982\u76ae\u5c42\u539a\u5ea6)\u3002\u7136\u540e\u5229\u7528\u7403\u9762U-Net\u4f5c\u4e3a\u751f\u6210\u5668\uff0c\u5c06\u4e00\u4e2aMRI\u626b\u63cf\u4eea\u5f97\u5230\u7684\u76ae\u5c42\u6570\u636e\u8fc1\u79fb\u5230\u53e6\u4e00\u4e2aMRI\u626b\u63cf\u4eea\u7684\u76ae\u5c42\u7a7a\u95f4\u4e2d\uff0c\u518d\u5229\u7528\u5224\u522b\u5668\u4fc3\u4f7f\u751f\u6210\u5668\u751f\u6210\u7684\u76ae\u5c42\u539a\u5ea6\u5c5e\u6027\u56fe\u5c3d\u91cf\u903c\u8fd1\u53e6\u4e00\u4e2aMRI\u626b\u63cf\u4eea\u5f97\u5230\u7684\u76ae\u5c42\u5c5e\u6027\u56fe\uff08\u56fe13\uff09\u3002\u53cd\u8fc7\u6765\u540c\u7406\u3002\u901a\u8fc7\u540c\u65f6\u8bad\u7ec3\u751f\u6210\u5668\u4e0e\u5224\u522b\u5668\uff0c\u795e\u7ecf\u7f51\u7edc\u5c31\u53ef\u4ee5\u5b66\u5230\u4e00\u4e2aMRI\u626b\u63cf\u4eea\u5230\u53e6\u4e00\u4e2a\u626b\u63cf\u4eea\u7684\u76ae\u5c42\u5c5e\u6027\u8fc1\u79fb\u3002\u8be5\u65b9\u6cd5\u5728\u6a21\u62df\u548c\u771f\u5b9e\u6570\u636e\u7684harmonization\u4e0a\u90fd\u53d6\u5f97\u4e86\u5f88\u597d\u7684\u6548\u679c\uff0c\u5728\u4e2a\u4f53\u5dee\u5f02\u548c\u7fa4\u4f53\u5dee\u5f02\u7684\u4fdd\u7559\u4e0a\u90fd\u4f18\u4e8e\u76ee\u524d\u5e38\u7528\u7684ComBat\u65b9\u6cd5\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-5-19-1-1.png\")
<\/figure>\n<\/div>\n\n\n
13. Jiang et al.,\u201cEarly Development of Infant Brain Complex Network\u201d.<\/strong>
\u5728\u51fa\u751f\u540e\u5230\u4e24\u5c81\u8fd9\u4e00\u9636\u6bb5\uff0c\u5a74\u513f\u5927\u8111\u7684\u7ed3\u6784\u548c\u529f\u80fd\u8fc5\u901f\u53d1\u80b2\u3002\u5176\u4e2d\uff0c\u5bf9\u5a74\u513f\u5927\u8111\u5168\u8111\u529f\u80fd\u7f51\u7edc\u7684\u62d3\u6251\u7ed3\u6784\u7684\u65e9\u671f\u53d1\u80b2\u7814\u7a76\u80fd\u591f\u5e2e\u52a9\u7814\u7a76\u8005\u66f4\u597d\u5730\u8ba4\u8bc6\u590d\u6742\u8ba4\u77e5\u529f\u80fd\u7684\u51fa\u73b0\u548c\u53d1\u5c55\u3002\u7136\u800c\uff0c\u7531\u4e8e\u4f18\u8d28\u5927\u6837\u672c\u7eb5\u5411\u5a74\u513f\u529f\u80fd\u78c1\u5171\u632f\uff08fMRI\uff09\u6570\u636e\u7684\u7f3a\u4e4f\uff0c\u622a\u81f3\u76ee\u524d\uff0c\u4eba\u4eec\u5bf9\u5a74\u513f\u5927\u8111\u529f\u80fd\u7f51\u7edc\u7684\u62d3\u6251\u5c5e\u6027\u7684\u65e9\u671f\u53d1\u80b2\u8f68\u8ff9\u4ecd\u7136\u77e5\u4e4b\u751a\u5c11\u3002\u6b64\u5916\uff0c\u5bf9\u4e8e\u5927\u8111\u7f51\u7edc\u7684\u53d1\u80b2\u548c\u8ba4\u77e5\u529f\u80fd\u7684\u53d1\u80b2\u8fd9\u4e24\u8005\u4e4b\u95f4\u7684\u5173\u7cfb\u7684\u7814\u7a76\u4ecd\u7136\u662f\u7a7a\u767d\u3002Jiang\u7b49\u4eba[13]\u7b2c\u4e00\u6b21\u5229\u7528\u9ad8\u8d28\u91cf\u7684\u5a74\u513f\u7eb5\u5411\u81ea\u7136\u7761\u7720\u72b6\u6001fMRI\u5927\u6570\u636e\uff0c\u901a\u8fc7\u6df7\u5408\u6548\u5e94\u6a21\u578b\uff0c\u7cbe\u786e\u523b\u753b\u4e86\u5a74\u513f\u8111\u7f51\u7edc\u7684\u751f\u7269\u6307\u6807\uff08\u5168\u8111\u7279\u5f81\u548c\u5404\u4e2a\u8111\u533a\u7279\u5f81\uff09\u57280-2\u5c81\u4e4b\u95f4\u7684\u53d1\u80b2\u8f68\u8ff9\uff08\u56fe14\uff09\uff0c\u5e76\u9996\u6b21\u7814\u7a76\u4e86\u8111\u7f51\u7edc\u65e9\u671f\u53d1\u80b2\u4e0e\u91cd\u8981\u8ba4\u77e5\u80fd\u529b\uff08\u63a5\u53d7\u6027\u89c6\u89c9\u80fd\u529b\u4ee5\u53ca\u63a5\u53d7\u6027\u8bed\u8a00\u80fd\u529b\uff09\u7684\u5bc6\u5207\u5173\u7cfb\u3002\u7814\u7a76\u8868\u660e\uff0c\u4e0d\u540c\u4e8e\u4e4b\u524d\u7684\u57fa\u4e8e\u975e\u7eb5\u5411\u5c0f\u6837\u672c\u6570\u636e\u7684\u7814\u7a76\u7ed3\u679c\uff0c\u7f51\u7edc\u7684\u5c40\u90e8\u6548\u7387\u5448\u73b0\u51fa\u5148\u589e\u52a0\u540e\u964d\u4f4e\uff08\u5728\u4e00\u5c81\u5de6\u53f3\u8fbe\u5230\u5cf0\u503c\uff09\u7684\u4e8c\u6b21\u66f2\u7ebf\u5f0f\u7684\u53d1\u80b2\u8f68\u8ff9\uff0c\u8868\u660e\u4e86\u65e9\u671f\u8111\u53d1\u80b2\u4e2d\u9ad3\u9798\u5316\u548c\u4fee\u526a\u4f5c\u7528\u5171\u540c\u5f71\u54cd\u4e0b\u7684\u7f51\u7edc\u7684\u5206\u79bb\u4e0e\u6574\u5408\u7684\u590d\u6742\u5173\u7cfb\u3002\u76f8\u6bd4\u5168\u8111\u53d1\u80b2\u8d8b\u52bf\uff0c\u8111\u533a\u7684\u53d1\u80b2\u5219\u5448\u73b0\u51fa\u660e\u663e\u7684\u7a7a\u95f4\u7279\u5f02\u6027\uff0c\u90e8\u5206\u8111\u533a\u751a\u81f3\u663e\u793a\u4e0e\u5168\u8111\u53d1\u80b2\u8f68\u8ff9\u5b8c\u5168\u4e0d\u540c\u7684\u53d1\u80b2\u8d8b\u52bf\u3002\u7814\u7a76\u540c\u65f6\u53d1\u73b0\u4e86\u4e0e\u65e9\u671f\u89c6\u89c9\u548c\u8bed\u8a00\u80fd\u529b\u76f8\u5173\u7684\u8111\u7f51\u7edc\u53d1\u80b2\u8d8b\u52bf\uff0c\u5bf9\u4e8e\u6df1\u523b\u7406\u89e3\u8111\u7f51\u7edc\u53d1\u80b2\u548c\u884c\u4e3a\u53d1\u80b2\u7684\u6b63\u5e38\u4e0e\u5f02\u5e38\u8f68\u7ebf\u63d0\u4f9b\u4e86\u7b2c\u4e00\u624b\u8d44\u6599\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-4-11-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
14.\u00a0\u00a0 \u00a0Zhou et al.,\u201cMulti-layer temporal network analysis reveals increasing temporal reachability and spreadability in the first two years of life\u201d.<\/strong>
\u4eba\u7c7b\u5927\u8111\u529f\u80fd\u8fde\u63a5\u7ec4\u7684\u65f6\u7a7a\u5206\u6790\u53ca\u5176\u5728\u751f\u547d\u6700\u521d\u51e0\u5e74\u7684\u65e9\u671f\u53d1\u5c55\u5bf9\u4e8e\u751f\u547d\u79d1\u5b66\u7814\u7a76\u81f3\u5173\u91cd\u8981\uff0c\u56e0\u4e3a\u5176\u53ef\u80fd\u4f5c\u4e3a\u91cd\u8981\u795e\u7ecf\u57fa\u7840\u89e3\u91ca\u5728\u8be5\u5173\u952e\u9636\u6bb5\u7684\u5404\u79cd\u9ad8\u7ea7\u8ba4\u77e5\u80fd\u529b\u7684\u4ea7\u751f\u548c\u5feb\u901f\u53d1\u5c55\u3002Zhou\u7b49\u4eba[14]\u63d0\u51fa\u4e86\u4e00\u79cd\u57fa\u4e8e\u591a\u5c42\u3001\u52a8\u6001\u7f51\u7edc\u7684\u65f6\u95f4\u7f51\u7edc\u5206\u6790\u5e76\u5bf9\u5a74\u513f0-2\u5c81\u8fd9\u4e00\u91cd\u8981\u53d1\u80b2\u9636\u6bb5\u7684\u6bcf\u4e2a\u8111\u533a\u91cf\u5316\u4e86\u5176\u65f6\u95f4\u53ef\u5230\u8fbe\u6027\uff08reachability\uff09\u548c\u53ef\u4f20\u64ad\u6027\uff08spreadability\uff09\uff0c\u4ece\u800c\u76f4\u89c2\u5730\u89e3\u91ca\u4e86\u5927\u8111\u5728\u51fa\u751f\u540e\u7684\u65e9\u671f\u53d1\u80b2\u8fc7\u7a0b\u4e2d\u8111\u7f51\u7edc\u7684\u8fde\u63a5\u6539\u53d8\u662f\u5982\u4f55\u589e\u5f3a\u4fe1\u606f\u5728\u7a7a\u95f4\u548c\u65f6\u95f4\u7684\u4ea4\u6362\u6548\u7387\u7684\u3002\u8be5\u65b0\u65b9\u6cd5\u901a\u8fc7\u8ba1\u7b97\u52a8\u6001\u529f\u80fd\u8fde\u63a5\u5e76\u901a\u8fc7\u589e\u52a0\u5c42\u95f4\u8fde\u63a5\u7684\u65b9\u5f0f\u5c06\u6240\u6709\u52a8\u6001\u529f\u80fd\u8fde\u63a5\u7f51\u7edc\u6309\u65f6\u95f4\u987a\u5e8f\u524d\u540e\u76f8\u8fde\uff0c\u5e76\u901a\u8fc7\u65f6\u5e8f\u6027\u8fde\u63a5\u8861\u91cf\u67d0\u4e2a\u5927\u8111\u533a\u57df\u5728\u77ed\u65f6\u95f4\u5185\u4e0e\u5176\u4ed6\u533a\u57df\u76f8\u8054\u7cfb\u7684\u7a0b\u5ea6\uff08\u56fe15\uff09\u3002\u8be5\u7814\u7a76\u5c06\u6b64\u65b9\u6cd5\u548c\u8fd9\u4e24\u4e2a\u65f6\u95f4\u7f51\u7edc\u5206\u6790\u6307\u6807\u5e94\u7528\u5230\u6765\u81ea165\u4e2a\u4e0d\u540c\u7684\u5a74\u513f\u4e0d\u540c\u5e74\u9f84\u9636\u6bb5\u7684932\u4f8b\u9ad8\u65f6\u95f4\u7a7a\u95f4\u5206\u8fa8\u7387\u7684\u9759\u606f\u6001\u529f\u80fd\u78c1\u5171\u632f\u6570\u636e\u4e0a\u3002\u5b9e\u9a8c\u53d1\u73b0\u5927\u90e8\u5206\u663e\u793a\u51fa\u968f\u5e74\u9f84\u589e\u957f\u7684\u53ef\u5230\u8fbe\u6027\u7684\u8111\u533a\u4f4d\u4e8e\u521d\u7ea7\u548c\u9ad8\u7ea7\u89c6\u89c9\u533a\u57df\uff08\u56fe16A\uff09\uff0c\u800c\u53ef\u5230\u8fbe\u6027\u964d\u4f4e\u7684\u533a\u57df\u4e3b\u8981\u96c6\u4e2d\u5728\u53cc\u4fa7\u989d\u53f6\u7736\u56de\u548c\u5de6\u4fa7\u989d\u53f6\u5c9b\u76d6\u90e8 (\u56fe16B)\u3002\u6839\u636e\u53ef\u5230\u8fbe\u6027\u53d1\u80b2\u901f\u5ea6\u5bf9\u6240\u6709\u8111\u533a\u6392\u5e8f\uff0c\u7814\u7a76\u53d1\u73b0\u4e86\u4e00\u4e2a\u4ece\u4e0b\u3001\u540e\u3001\u5185\u4fa7\u5230\u4e0a\u3001\u524d\u3001\u5916\u4fa7\u5927\u8111\u7684\u8fd9\u6837\u4e00\u4e2a\u68af\u5ea6\uff08\u56fe16C\uff09\u3002\u91c7\u7528\u65f6\u95f4\u7f51\u7edc\u5206\u6790\uff0c\u7814\u7a76\u53d1\u73b0\u572845\u79d2\u5185\u53f3\u4fa7\u68ad\u72b6\u56de\uff08\u5177\u6709\u6700\u5927\u53ef\u5230\u8fbe\u6027\u589e\u52a0\u901f\u7387\uff09\u53ef\u4ee5\u901a\u8fc7\u8de8\u65f6\u95f4\u5c42\u8fde\u63a5\u5230\u5927\u90e8\u5206\u8111\u533a (\u56fe16D\u3001E)\uff0c\u8fd9\u8868\u660e\u4e86\u89c6\u89c9\u529f\u80fd\u8fde\u63a5\u7684\u5f3a\u5316\u548c\u6548\u7387\u7684\u63d0\u5347\u57280-2\u5c81\u671f\u95f4\u7684\u5927\u8111\u529f\u80fd\u53d1\u80b2\u4e2d\u8d77\u5230\u4e86\u81f3\u5173\u91cd\u8981\u7684\u4f5c\u7528\u3002\u8be5\u65b9\u6cd5\u53ef\u4ee5\u5e94\u7528\u5728\u5404\u4e2a\u8111\u7814\u7a76\u9886\u57df\uff0c\u662f\u4e00\u79cd\u91cd\u8981\u7684\u3001\u76f4\u89c2\u7684\u3001\u5177\u6709\u9ad8\u5ea6\u53ef\u89e3\u91ca\u6027\u7684\u52a8\u6001\u8111\u7f51\u7edc\u7814\u7a76\u624b\u6bb5\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-10-1-1.png\")
<\/figure>\n<\/div>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-11-1-1.png\")
<\/figure>\n<\/div>\n\n\n
15.\u00a0\u00a0 \u00a0Kam et al.,\u201cA Deep Learning Framework for Noise Component Detection from Resting-state Functional MRI\u201d.<\/strong>
\u529f\u80fd\u78c1\u5171\u632f\uff08fMRI\uff09\u5305\u542b\u5927\u91cf\u566a\u58f0\u548c\u4f2a\u8ff9\uff0c\u4e25\u91cd\u5f71\u54cd\u8ba1\u7b97\u7ed3\u679c\u7684\u51c6\u786e\u6027\u3001\u7a33\u5b9a\u6027\u548c\u53ef\u91cd\u590d\u6027\u3002\u72ec\u7acb\u6210\u5206\u5206\u6790\uff08ICA\uff09\u53ef\u5728\u65e0\u9700\u4efb\u4f55\u6a21\u578b\u6216\u5047\u8bbe\u7684\u524d\u63d0\u4e0b\u63d0\u53d6\u51fafMRI\u6570\u636e\u4e2d\u7684\u7ed3\u6784\u6027\u566a\u58f0\uff0c\u4f46\u8be5\u566a\u58f0\u63d0\u53d6\u624b\u6bb5\u56e0\u7f3a\u5c11\u5ba2\u89c2\u7684\u8bc4\u5224\u6807\u51c6\uff0c\u901a\u5e38\u9700\u8981\u7ecf\u9a8c\u4e30\u5bcc\u7684\u7814\u7a76\u8005\u6d88\u8017\u5927\u91cf\u7684\u4eba\u529b\u548c\u65f6\u95f4\u9010\u4e00\u8bc6\u522b\uff0c\u5728\u5904\u7406\u6d77\u91cf\u6570\u636e\u65f6\u975e\u5e38\u56f0\u96be\u3002\u8fd1\u671f\uff0c\u6709\u7814\u7a76\u8005\u63d0\u51fa\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u81ea\u52a8\u8bc6\u522b\u566a\u58f0\u6210\u5206\uff0c\u4f46\u6bcf\u4e2a\u5206\u7c7b\u5668\u7684\u7ed3\u679c\u9700\u8981\u8f93\u5165\u5230\u53e6\u5916\u7684\u96c6\u6210\u5206\u7c7b\u5668\u4e2d\u4ee5\u5b9e\u73b0\u6700\u4f73\u8bc6\u522b\u6027\u80fd\u3002\u8fd9\u4f7f\u5f97\u6574\u4e2a\u8fc7\u7a0b\u4e0d\u4ec5\u8017\u65f6\uff0c\u800c\u4e14\u65e0\u6cd5\u5f88\u597d\u7684\u8fc1\u79fb\u5230\u5176\u4ed6\u8f83\u4e3a\u5f02\u8d28\uff08\u4ece\u800c\u566a\u58f0\u6a21\u5f0f\u4e5f\u4e0d\u540c\uff09\u7684\u6570\u636e\u96c6\u3002Kam\u7b49\u4eba[15]\u63d0\u51fa\u4e86\u901a\u8fc7\u6df1\u5ea6\u5b66\u4e60\u6765\u81ea\u52a8\u63d0\u53d6\u9759\u606f\u6001fMRI\u6570\u636eICA\u5206\u89e3\u6240\u5f97\u7684\u5404\u4e2a\u6210\u5206\u7684\u65f6\/\u7a7a\u7279\u5f81\u4ece\u800c\u7cbe\u786e\u68c0\u6d4b\u566a\u97f3\u7684\u7aef\u5230\u7aef\u7684\u6846\u67b6\u3002\u8be5\u65b9\u6cd5\u4f7f\u7528ICA\u5c06fMRI\u6570\u636e\u5206\u89e3\u6210\u4e00\u7cfb\u5217\u72ec\u7acb\u7684\u4e09\u7ef4\u7684\u7a7a\u95f4\u56fe\u50cf\u53ca\u5176\u5bf9\u5e94\u7684\u4e00\u7ef4\u65f6\u95f4\u5e8f\u5217\uff0c\u7136\u540e\u5206\u522b\u6784\u5efa\u4e00\u4e2a\u4e09\u7ef4\u548c\u4e00\u7ef4\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u5206\u522b\u63d0\u53d6\u65f6\u95f4\u6216\u7a7a\u95f4\u7279\u5f81\u8fdb\u884c\u566a\u58f0\u8bc6\u522b\u3002\u6b64\u5916\uff0c\u4e3a\u540c\u65f6\u8003\u8651\u65f6\u95f4\u548c\u7a7a\u95f4\u4fe1\u606f\uff0c\u5df2\u5206\u522b\u8bad\u7ec3\u597d\u7684\u4e09\u7ef4\u548c\u4e00\u7ef4\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u6700\u540e\u7684\u5168\u8fde\u63a5\u5c42\u88ab\u7ec4\u5408\u5230\u4e00\u8d77\u5e76\u901a\u8fc7\u4e00\u4e2a\u989d\u5916\u7684\u5168\u8fde\u63a5\u5c42\u548c\u8f93\u51fa\u5c42\u76f8\u63a5\u8fdb\u884c\u7b2c\u4e09\u6b21\u8bc6\u522b\u3002\u8fd9\u6837\u53ef\u5f97\u5230\u4e09\u4e2a\u6df1\u5ea6\u5b66\u4e60\u201c\u51b3\u7b56\u8005\u201d\uff0c\u5206\u522b\u5355\u72ec\u5bf9\u7a7a\u95f4\u56fe\u50cf\u3001\u65f6\u95f4\u5e8f\u5217\u3001\u4ee5\u53ca\u7efc\u5408\u65f6\/\u7a7a\u4fe1\u606f\u8fdb\u884c\u51b3\u7b56\uff0c\u5e76\u6700\u7ec8\u901a\u8fc7\u591a\u6570\u8868\u51b3\u7684\u65b9\u6cd5\u505a\u51fa\u6700\u4f73\u51b3\u7b56\u3002\u8fd9\u4e00\u65b9\u6cd5\u6709\u6548\u5730\u6a21\u62df\u4e86\u6709\u7ecf\u9a8c\u7684\u7814\u7a76\u8005\u5728\u6ca1\u6709\u64cd\u4f5c\u6027\u566a\u58f0\u5b9a\u4e49\u7684\u60c5\u51b5\u4e0b\u8fdb\u884c\u51b3\u7b56\u7684\u8fc7\u7a0b\uff0c\u5728\u9ad8\u5206\u8fa8\u7387\u7684\u5a74\u513f\u5927\u8111fMRI\u6570\u636e\u4e0a\u5f97\u523097.12% \u7684\u51c6\u786e\u7387\uff0c\u8d85\u8fc7\u4e86\u591a\u4e2a\u4eba\u7c7b\u4e13\u5bb6\u5171\u540c\u8bc6\u522b\u7684\u7cbe\u5ea6\u3002\u6b64\u5916\uff0c\u8be5\u65b9\u6cd5\u65e0\u9700\u5176\u4ed6\u8f6f\u4ef6\u53c2\u4e0e\u4fbf\u53ef\u72ec\u7acb\u8fdb\u884c\uff0c\u800c\u4e14\u53ef\u5229\u7528GPU\u5927\u5927\u7f29\u51cf\u8ba1\u7b97\u65f6\u95f4\u3002\u8be5\u65b9\u6cd5\u5df2\u88ab\u5a74\u513f\u8111\u8fde\u63a5\u7ec4\u8ba1\u5212 \uff08Baby Connectome Project\uff09\u91c7\u7528\u5e76\u88ab\u7eb3\u5165\u5176fMRI\u5206\u6790\u6d41\u6c34\u7ebf\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-12-1-1.png\")
<\/figure>\n<\/div>\n\n\n
16.\u00a0\u00a0 \u00a0Hu et al.,\u201cDeep Granular Feature-Label Distribution Learning for Neuroimaging-based Infant Age Prediction\u201d.<\/strong>
\u57fa\u4e8eMRI\u7684\u5a74\u513f\u5e74\u9f84\u9884\u6d4b\u5bf9\u8111\u53d1\u80b2\u5206\u6790\u5177\u6709\u91cd\u8981\u610f\u4e49\uff0c\u5374\u9762\u4e34\u6570\u636e\u4e0d\u8db3\uff0c\u7cbe\u5ea6\u4e0d\u9ad8\u7684\u56f0\u5883\u3002Hu\u7b49\u4eba[16]\u5f15\u5165\u6807\u7b7e\u5206\u5e03\u5b66\u4e60\u8fd9\u4e00\u9488\u5bf9\u5c0f\u6837\u672c\u95ee\u9898\u7684\u65b0\u578b\u673a\u5668\u5b66\u4e60\u8303\u5f0f\uff0c\u4ee5\u89e3\u51b3\u5176\u5728\u5a74\u513f\u5e74\u9f84\u9884\u6d4b\u4e2d\u6807\u7b7e\u6570\u91cf\u5e9e\u5927\u53ca\u6807\u7b7e\u5bf9\u5e94\u6837\u672c\u7a00\u5c11\u7684\u5173\u952e\u95ee\u9898\u4e3a\u76ee\u6807\uff0c\u5efa\u7acb\u4e86\u6df1\u5ea6\u7c92\u5316\u7279\u5f81-\u6807\u7b7e\u5206\u5e03\u5b66\u4e60\u6a21\u578b (DGFLDL)\u3002\u8be5\u6587\u9996\u5148\u63d0\u51fa\u4e86\u7c92\u5316\u6807\u7b7e\u5206\u5e03 (GLD)\uff1a\u901a\u8fc7\u5c06\u76f8\u90bb\u6807\u7b7e\u805a\u96c6\u6210\u4fe1\u606f\u7c92\uff0c\u7531\u4e00\u65cf\u5b9a\u4e49\u5728\u4fe1\u606f\u7c92\u4e0a\u7684\u5206\u5e03\u6765\u5bf9\u6bcf\u4e2aMRI\u8fdb\u884c\u6807\u6ce8\uff0cGLD\u5728\u7c92\u7684\u5c3a\u5ea6\u4e0a\u5b9e\u73b0\u4e86\u4ee4\u6bcf\u4e2aMRI\u4e3a\u4e0e\u4e4b\u5bf9\u5e94\u7684\u3001\u53ca\u5176\u8fd1\u90bb\u7684\u5e74\u9f84\u6807\u7b7e\u540c\u65f6\u63d0\u4f9b\u5f71\u50cf\u4fe1\u606f\u7684\u76ee\u7684\uff0c\u65e2\u8fbe\u6210\u4e86\u4fe1\u606f\u6269\u5145\uff0c\u4e5f\u6709\u6548\u964d\u4f4e\u4e86\u6807\u7b7e\u7684\u6570\u91cf\u3002\u8be5\u6587\u8fdb\u4e00\u6b65\u5229\u7528\u540c\u4e00\u5e74\u9f84\u5bf9\u5e94\u7684MRI\u4e2d\u5b58\u5728\u7684\u591a\u6837\u6027\uff0c\u63d0\u51fa\u4e86\u7c92\u5316\u7279\u5f81\u5206\u5e03 (GFD)\uff0c\u5c06MRI\u7279\u5f81\u53d8\u6362\u4e3a\u7c92\u5316\u7279\u5f81\u7a7a\u95f4\u4e0a\u7684\u5206\u5e03\uff0c\u4ece\u800c\u5c06\u539f\u59cb\u6570\u636e\u96c6\u8f6c\u6362\u4e3aGFD\u4e0eGLD\u4e4b\u95f4\u7684\u6620\u5c04\u5173\u7cfb\uff0c\u5b9e\u73b0\u4e86\u4fe1\u606f\u7684\u4e8c\u6b21\u6269\u5145\u3002\u6700\u540e\uff0c\u91c7\u7528\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u5b8c\u6210\u4e86\u5bf9\u8fd9\u4e2a\u5173\u7cfb\u7684\u5b66\u4e60\uff08\u56fe18\uff09\u3002\u4ee535\uff5e848\u5929\u7684\u5a74\u513fMR\u626b\u63cf\u56fe\u50cf\u4e3a\u5b9e\u9a8c\u6570\u636e\uff0c\u5229\u7528\u8111\u76ae\u5c42\u7ed3\u6784\u7279\u5f81\uff0c\u572810-fold\u4ea4\u53c9\u9a8c\u8bc1\u4e0b\uff0cDGFLDL\u5e74\u9f84\u9884\u6d4b\u7684MAE\u8fbe\u523036.1\u5929\uff0c \u8fdc\u4f18\u4e8e\u4f20\u7edf\u7684\u56de\u5f52\u65b9\u6cd5\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-13-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\n\n\n\n
\u8f7b\u5ea6\u8ba4\u77e5\u529f\u80fd\u969c\u788d\uff08Mild Cognitive Impairment, MCI\uff09\u88ab\u8ba4\u4e3a\u662f\u8001\u5e74\u6027\u75f4\u5446\uff08Alzheimer’s Disease\uff0cAD\uff09\u7684\u65e9\u671f\u9636\u6bb5\u3002\u9274\u4e8eAD\u60a3\u8005\u7684\u4e0d\u53ef\u9006\u7684\u75c5\u7406\u8fc7\u7a0b\uff0c\u7814\u7a76\u548c\u8bc6\u522b\u7a33\u5b9a\u578bMCI\uff08sMCI\uff09\u548c\u8fdb\u5c55\u578bMCI\uff08pMCI\uff09\u5177\u6709\u91cd\u8981\u7684\u4e34\u5e8a\u4ef7\u503c\u3002\u8bb8\u591a\u7814\u7a76\u8868\u660e\u878d\u5408\u591a\u6a21\u6001\u4fe1\u606f\uff08\u4f8b\u5982MRI\u548cPET\uff09\u80fd\u63d0\u9ad8\u8bc6\u522b\u7cbe\u5ea6\uff0c\u4f46\u5982\u4f55\u89e3\u51b3\u5e38\u89c1\u7684\u6a21\u6001\u7f3a\u5931\u95ee\u9898\u4ecd\u7136\u662f\u4e00\u4e2a\u6311\u6218\u3002Zhou\u7b49\u4eba[17]\u63d0\u51fa\u4e86\u4e00\u79cd\u65b0\u9896\u7684\u878d\u5408\u7f3a\u5931\u6a21\u6001\u6570\u636e\u8865\u5168\u3001\u591a\u6a21\u6001\u9690\u8868\u793a\u5b66\u4e60\u3001\u9884\u6d4b\u6a21\u578b\u5b66\u4e60\u4e8e\u4e00\u4f53\u7684MCI\u9884\u6d4b\u6a21\u578b\uff08\u53c2\u89c1\u56fe19\uff09\u3002\u8be5\u65b9\u6cd5\u7684\u4e3b\u8981\u4f18\u52bf\u662f\u5229\u7528\u6570\u636e\u7c7b\u522b\u4fe1\u606f\u6765\u6307\u5bfc\u7f3a\u5931\u6570\u636e\u7684\u8865\u5168\uff0c\u4ee5\u53ca\u5b66\u4e60\u591a\u6a21\u6001\u7684\u9690\u8868\u793a\u6765\u964d\u4f4e\u6a21\u6001\u95f4\u7684\u5dee\u5f02\u6027\u3002\u5b9e\u9a8c\u7ed3\u679c\u5c55\u793a\u4e86\u8be5\u65b9\u6cd5\u5728\u9884\u6d4bMCI\u5411AD\u8f6c\u5316\u7684\u6709\u6548\u6027\uff08\u53c2\u89c1\u56fe20\uff09\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-14-1-1.png\")
<\/figure>\n<\/div>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-15-1-1.png\")
<\/figure>\n<\/div>\n\n\n
18.\u00a0\u00a0 \u00a0Lian et al.,\u201cEnd-to-End Dementia Status Prediction from Brain MRI using Multi-Task Weakly-Supervised Attention Network\u201d.<\/strong>
\u4e34\u5e8a\u5b9e\u8df5\u8bc1\u660e\u8ba4\u77e5\u6d4b\u8bd5\uff08\u5982\u7b80\u660e\u7cbe\u795e\u72b6\u6001\u91cf\u8868MMSE\uff0c\u4e34\u5e8a\u75f4\u5446\u8bc4\u5206\u603b\u548cCDR\u7b49\uff09\u7684\u91cf\u5316\u7ed3\u679c\u5f80\u5f80\u4e0e\u963f\u5c14\u5179\u6d77\u9ed8\u75c7\uff08AD\uff09\u7684\u75c5\u7a0b\u8fdb\u5c55\u8054\u7cfb\u7d27\u5bc6\u3002\u6839\u636e\u524d\u671f\u5927\u8111\u7ed3\u6784\u78c1\u5171\u632f\uff08sMRI\uff09\u56fe\u50cf\u81ea\u52a8\u9884\u6d4b\u4e34\u5e8a\u8bc4\u5206\u7ed3\u679c\uff08Clinical Scores\uff09\u5bf9\u8861\u91cf\u548c\u9884\u6d4bAD\u7684\u75c5\u7a0b\u6709\u91cd\u8981\u610f\u4e49\u3002Lian\u7b49\u4eba[18]\u63d0\u51fa\u4e86\u4e00\u79cd\u7aef\u5230\u7aef\u7684\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\uff08MWAN\uff09\uff0c\u9ad8\u6548\u51c6\u786e\u5730\u5b8c\u6210\u591a\u4e2a\u8ba4\u77e5\u6d4b\u8bd5\u7ed3\u679c\u7684\u540c\u65f6\u9884\u6d4b\uff08\u56fe21\uff09\u3002\u533a\u522b\u4e8e\u4f20\u7edf\u7684\u673a\u5668\u5b66\u4e60\u548c\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\uff0cMWAN \u91c7\u7528\u53ef\u8bad\u7ec3\u7684\u5f31\u76d1\u7763\u6ce8\u610f\u529b\u673a\u5236\uff08Weakly-supervised Attention Module\uff09\u4ece\u5168\u8111 sMRI\u56fe\u50cf\u4e2d\u81ea\u52a8\u5b9a\u4f4d\u4e2a\u4f53\u7279\u5f02\u7684\uff08Subject-specific\uff09\u75c5\u53d8\u533a\u57df\uff0c\u5e76\u4ee5\u6b64\u4e3a\u57fa\u7840\u63d0\u53d6\u9ad8\u9636\u56fe\u50cf\u7279\u5f81\u5e76\u6784\u5efa\u591a\u4efb\u52a1\u56de\u5f52\u6a21\u578b\u3002\u8be5\u6587\u91c7\u75282-fold\u4ea4\u53c9\u9a8c\u8bc1\uff0c\u5728\u591a\u4e2a\u516c\u5f00\u6570\u636e\u96c6\u4e0a\u8fdb\u884c\u4e86\u9a8c\u8bc1\u3002\u5b9e\u9a8c\u7ed3\u679c\u8868\u660e\uff0c\u8be5\u6587\u63d0\u51fa\u7684MWAN\u6a21\u578b\u80fd\u591f\u7cbe\u786e\u5730\u81ea\u52a8\u5b9a\u4f4d\u75c5\u53d8\u533a\u57df\uff0c\u5e76\u53d6\u5f97\u4e86\u4f18\u4e8e\u73b0\u6709\u6df1\u5ea6\u5b66\u4e60\u65b9\u6cd5\u7684\u9884\u6d4b\u7ed3\u679c\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-4-12-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
19.\u00a0\u00a0 \u00a0Jiao et al.,\u201cDynamic Routing Capsule Networks for Mild Cognitive Impairment Diagnosis\u201d.<\/strong>
\u963f\u5c14\u8328\u6d77\u9ed8\u75c5\uff08AD\uff09\u662f\u4e00\u79cd\u6162\u6027\u795e\u7ecf\u9000\u884c\u6027\u75be\u75c5\uff0c\u4f1a\u7ed9\u60a3\u8005\u5e26\u6765\u6781\u5927\u7684\u75db\u82e6\u3002\u5728\u8f7b\u5ea6\u8ba4\u77e5\u969c\u788d\uff08MCI\uff09\u7684\u65e9\u671f\u9636\u6bb5\u5982\u80fd\u53ca\u65f6\u8bca\u65ad\u5219\u53ef\u80fd\u6709\u6548\u51cf\u7f13AD\u7684\u53d1\u5c55\u5e76\u51cf\u8f7b\u60a3\u8005\u75db\u82e6\u3002Jiao\u7b49\u4eba[19]\u63d0\u51fa\u4e86\u4e00\u79cd\u65b0\u9896\u7684\u7528\u4e8eMCI\u8bca\u65ad\u7684\u52a8\u6001\u80f6\u56ca\u795e\u7ecf\u7f51\u7edc(dynamic CapsNet)\uff0c\u5e76\u63d0\u51fa\u548c\u8ba8\u8bba\u4e86\u4e24\u79cdDynamic CapsNet\u7684\u53d8\u4f53\uff0c\u8fd9\u4e24\u79cd\u65b9\u6cd5\u53ef\u5206\u522b\u52a8\u6001\u8868\u793aIntra-ROI\uff08\u56fe22\uff09\u548cInter-ROI\u7684\u9759\u606f\u6001\u529f\u80fd\u78c1\u5171\u632f\u6d3b\u52a8\uff08\u56fe23\uff09\u3002\u6b64\u5916\uff0c\u8be5\u6587\u5728Inter-ROI\u52a8\u6001\u8868\u793a\u6a21\u578b\u4e2d\u91c7\u7528\u4e86\u53ef\u5b66\u4e60\u7684\u52a8\u6001\u201c\u795e\u7ecf\u5143\u8fde\u63a5\u201d\uff0c\u5728Dynamic CapsNet\u7684\u8bad\u7ec3\u671f\u95f4\uff0c\u4e0d\u540c\u4eba\u5de5\u795e\u7ecf\u5143\u4e4b\u95f4\u7684\u8fde\u63a5\u53ef\u4ee5\u52a8\u6001\u5b66\u4e60\u3002\u8be5\u5de5\u4f5c\u4e5f\u662f\u7b2c\u4e00\u6b21\u7528\u7aef\u5230\u7aef\u5b66\u4e60\u7684CapsNet\u8fdb\u884cMCI\u8bca\u65ad\uff08\u56fe24\uff09\u3002\u8be5\u6587\u6240\u63d0\u51fa\u7684Intra-ROI \/ Inter-ROI CapsNet\u7684\u5206\u7c7b\u7cbe\u786e\u5ea6\u4e3a0.729(0.023) \/ 0.773(0.022)\uff0c\u7075\u654f\u5ea6\u4e3a0.799(0.042) \/ 0.771(0.027)\uff0c\u7279\u5f02\u5ea6\u4e3a0.673(0.065) \/ 0.774(0.040)\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-16-1-1.png\")
<\/figure>\n<\/div>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-17-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-18-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\u963f\u5c14\u8328\u6d77\u9ed8\u75c5\uff08AD\uff09\u662f\u4e00\u79cd\u4e25\u91cd\u4e14\u591a\u53d1\u7684\u8001\u5e74\u9000\u884c\u6027\u75be\u75c5\u3002\u7531\u4e8e\u8001\u5e74\u4eba\u5360\u4eba\u53e3\u603b\u6570\u7684\u6bd4\u4f8b\u9010\u6e10\u589e\u5927\uff0cAD\u7684\u53d1\u75c5\u7387\u4e5f\u5728\u4e0d\u65ad\u589e\u52a0\uff0c\u56e0\u6b64AD\u7684\u65e9\u671f\u8bca\u65ad\u548c\u9884\u6d4b\u5c24\u4e3a\u91cd\u8981\u3002\u8bb8\u591a\u73b0\u6709\u65b9\u6cd5\u5747\u91c7\u7528\u878d\u5408\u591a\u6a21\u6001\u6570\u636e\uff08\u4f8b\u5982MRI\u548cPET\uff09\u6765\u63d0\u9ad8\u8bca\u65ad\u7cbe\u5ea6\uff0c\u4f46\u4ecd\u7136\u9762\u4e34\u4e00\u4e9b\u6311\u6218\u3002\u9996\u5148\uff0c\u591a\u6a21\u6001\u6570\u636e\u878d\u5408\u548c\u57fa\u4e8e\u591a\u6a21\u6001\u6570\u636e\u7684\u8bca\u65ad\u6a21\u578b\u5b66\u4e60\u5f80\u5f80\u88ab\u5206\u5f00\u6267\u884c\uff0c\u8fd9\u5ffd\u7565\u4e86\u5b83\u4eec\u4e4b\u95f4\u7684\u76f8\u5173\u6027\uff1b\u5176\u6b21\uff0c\u5982\u4f55\u6709\u6548\u5730\u878d\u5408\u591a\u6a21\u6001\u6570\u636e\u5e76\u964d\u4f4e\u6570\u636e\u95f4\u7684\u5197\u4f59\u4fe1\u606f\u5e76\u63d0\u9ad8\u5206\u7c7b\u7cbe\u5ea6\u4ecd\u975e\u5e38\u56f0\u96be\u3002Zhou\u7b49\u4eba[20]\u63d0\u51fa\u4e86\u4e00\u79cd\u65b0\u7684\u878d\u5408\u591a\u6a21\u6001\u878d\u5408\u3001\u6df1\u5ea6\u9690\u8868\u793a\u5b66\u4e60\u548c\u9884\u6d4b\u6a21\u578b\u5b66\u4e60\u4e8e\u4e00\u4f53\u7684\u75be\u75c5\u8bca\u65ad\u65b9\u6cd5\u3002\u8be5\u65b9\u6cd5\u57fa\u4e8e\u6df1\u5ea6\u77e9\u9635\u5206\u89e3\u6765\u63d0\u53d6\u6bcf\u4e2a\u6a21\u6001\u7684\u9ad8\u9636\uff08High-level\uff09\u7279\u5f81\uff0c\u5e76\u4f7f\u5f97\u591a\u6a21\u6001\u6570\u636e\u5171\u4eab\u8fd9\u4e9b\u9ad8\u9636\u7279\u5f81\u6765\u6df1\u5ea6\u6316\u6398\u591a\u6a21\u6001\u56fe\u50cf\u4e4b\u95f4\u7684\u76f8\u5173\u6027\u3002\u5728ADNI\u6570\u636e\u96c6\u4e0a\u7684\u5b9e\u9a8c\u7ed3\u679c\u9a8c\u8bc1\u4e86\u8be5\u6587\u63d0\u51fa\u7b97\u6cd5\u7684\u6709\u6548\u6027\uff08\u53c2\u89c1\u56fe25\uff09\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-6-19-1-1.png\")
<\/figure>\n<\/div>\n\n\n
21.\u00a0\u00a0 \u00a0Li et al.,\u201cIdentification of Abnormal Circuit Dynamics in Major Depressive Disorder via Multiscale Neural Modeling of Resting-state fMRI\u201d.<\/strong>
\u4f20\u7edf\u7684\u9759\u606f\u6001\u529f\u80fd\u78c1\u5171\u632f\u96c6\u4e2d\u7814\u7a76\u4e0d\u540c\u8111\u533a\u4e4b\u95f4\u7684\u529f\u80fd\u540c\u6b65\u6027\u3002\u8fd9\u4e00\u65b9\u6cd5\u7684\u6700\u5927\u5f31\u70b9\u662f\u65e0\u6cd5\u63d0\u4f9b\u5927\u8111\u8ba4\u77e5\u529f\u80fd\u5728\u795e\u7ecf\u56de\u8def\u5c42\u9762\u7684\u673a\u5236\u6027\u7406\u89e3\u3002\u4e3a\u4e86\u7a81\u7834\u8fd9\u4e00\u5c40\u9650\uff0cLi\u7b49\u4eba[21]\u5c06\u8ba1\u7b97\u795e\u7ecf\u79d1\u5b66\u4e0e\u4f20\u7edf\u8fde\u63a5\u7ec4\u5b66\u7ed3\u5408\u5728\u4e00\u8d77\u5efa\u7acb\u4e86\u591a\u5c3a\u5ea6\u795e\u7ecf\u6a21\u578b\u53c2\u6570\u4f30\u8ba1\u65b9\u6cd5\uff08\u56fe26\uff09\u3002\u8fd9\u4e00\u65b9\u6cd5\u7684\u6700\u5927\u4f18\u70b9\u662f\u53ef\u4ee5\u5c06\u5fae\u89c2\u795e\u7ecf\u56de\u8def\u7684\u76f8\u4e92\u4f5c\u7528\u4e0e\u5b8f\u89c2\u7f51\u7edc\u7684\u52a8\u6001\u53d8\u5316\u6709\u673a\u6574\u5408\uff0c\u5e76\u4e14\u53ef\u4ee5\u4f30\u7b97\u8111\u533a\u5185\u90e8\u4ee5\u53ca\u8111\u533a\u4e4b\u95f4\u7684\u591a\u5c3a\u5ea6\u6709\u5411\u8fde\u63a5\u7684\u5f3a\u5ea6\u3002\u8be5\u6587\u628a\u8fd9\u4e00\u65b9\u6cd5\u5e94\u7528\u523066\u4e2a\u521d\u6b21\u53d1\u75c5\u5c1a\u672a\u7528\u836f\u7684\u6291\u90c1\u75c7\u75c5\u4eba\u548c66\u4e2a\u5065\u5eb7\u5bf9\u7167\u7684\u9759\u606f\u6001\u529f\u80fd\u78c1\u5171\u632f\u6570\u636e\uff0c\u5e76\u5bf9\u5927\u8111\u7684\u591a\u4e2a\u9ad8\u7ea7\u8ba4\u77e5\u7f51\u7edc\u8fdb\u884c\u5efa\u6a21\u3002\u7814\u7a76\u53d1\u73b0\u6291\u90c1\u75c7\u75c5\u4eba\u7684\u80cc\u5916\u4fa7\u524d\u989d\u53f6\u76ae\u8d28\u5185\u90e8\u7684\u5174\u594b\u6027\u548c\u6291\u5236\u6027\u8fde\u63a5\u5f3a\u5ea6\u6bd4\u6b63\u5e38\u7ec4\u964d\u4f4e\uff0c\u540c\u65f6\u4e18\u8111\u5185\u90e8\u7684\u5174\u594b\u6027\u8fde\u63a5\u5f3a\u5ea6\u6bd4\u6b63\u5e38\u7ec4\u5f02\u5e38\u589e\u9ad8\u3002\u8fd9\u4e9b\u53d1\u73b0\u4e0e\u5df2\u77e5\u7684\u8fd9\u4e24\u4e2a\u8111\u533a\u5728\u6291\u90c1\u75c7\u4e2d\u7684\u529f\u80fd\u5f02\u5e38\u76f8\u4e00\u81f4\u3002\u8fd9\u4e00\u65b0\u65b9\u6cd5\u4e3a\u7cbe\u795e\u75be\u75c5\u7684\u795e\u7ecf\u75c5\u7406\u673a\u5236\u7814\u7a76\u63d0\u4f9b\u4e86\u4e00\u79cd\u65b0\u7684\u9014\u5f84\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-7-10-1-1.png\")
<\/figure>\n<\/div>\n\n\n
<\/p>\n\n\n\n
\n\n\n\n
22.\u00a0\u00a0 \u00a0Lian et al.,\u201cMeshSNet: Deep Multi-Scale Mesh Feature Learning for End-to-End Tooth Labeling on 3D Dental Surfaces\u201d.<\/strong>
\u4f5c\u4e3a\u77eb\u6b63\u6cbb\u7597\u8ba1\u5212\uff08Orthodontic Treatment Planning\uff09\u7684\u5173\u952e\u73af\u8282\uff0c\u4ece\u4e09\u7ef4\u7259\u79d1\u8868\u9762\u6a21\u578b\uff08Dental Surface Model\uff09\u4e0a\u7cbe\u786e\u6807\u6ce8\u7259\u9f7f\u662f\u5206\u6790\u548c\u91cd\u6392\u7259\u9f7f\u4f4d\u7f6e\u7684\u524d\u63d0\u3002\u5148\u8fdb\u7684\u53e3\u8154\u5185\u626b\u63cf\u4eea\uff08IntraOral Scanner\uff0cIOS\uff09\u867d\u7136\u5b9e\u73b0\u4e86\u9ad8\u6548\u7684\u4e09\u7ef4\u8868\u9762\u6a21\u578b\u91cd\u6784\uff0c\u4f46\u7531\u4e8eIOS\u91c7\u96c6\u6570\u636e\u7684\u4e0d\u89c4\u5219\u6027\uff0c\u7259\u9f7f\u6807\u6ce8\u4ecd\u5177\u6709\u6311\u6218\u6027\u3002Lian\u7b49\u4eba[22]\u63d0\u51fa\u4e00\u79cd\u7aef\u5230\u7aef\u7684\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\uff08\u5373MeshSNet\uff09\u4ece\u539f\u59cb\u76843D\u7f51\u683c\u8868\u9762\uff08Surface Mesh\uff09\u4e0a\u81ea\u52a8\u5b66\u4e60\u9ad8\u9636\u8868\u9762\u7279\u5f81\uff0c\u4ece\u800c\u5b9e\u73b0\u4e86\u9ad8\u6548\u4e14\u7cbe\u786e\u5730\u81ea\u52a8\u6807\u6ce8\u7259\u9f7f\u3002\u533a\u522b\u4e8e\u4f20\u7edf\u7684CNN\u6a21\u578b\uff0c\u8be5\u6587\u63d0\u51fa\u7684MeshSNet\u6a21\u578b\u76f4\u63a5\u4ee5\u7f51\u683c\u8868\u9762\u5143\u7d20\uff08Mesh Triangle\uff09\u7684\u57fa\u672c\u7279\u5f81\u4e3a\uff08\u5373Triangle\u9876\u70b9\u5750\u6807\u548c\u6cd5\u5411\u91cf\uff09\u8f93\u5165\uff0c\u5e76\u6a21\u62dfCNN\u7684\u673a\u5236\u4ee5\u5206\u5c42\u5730\u5b66\u4e60\u548c\u878d\u5408\u591a\u5c3a\u5ea6\u9ad8\u9636\u7279\u5f81\u4ee5\u63d0\u9ad8\u6807\u6ce8\u7684\u51c6\u786e\u6027\uff08\u56fe27\uff09\u3002\u8be5\u6587\u91c7\u75283-fold\u4ea4\u53c9\u9a8c\u8bc1\u5728\u771f\u5b9e\u7684IOS\u7259\u79d1\u8868\u9762\u6570\u636e\u4e0a\u8fdb\u884c\u6d4b\u8bd5\uff0c\u7ed3\u679c\u8868\u660eMeshSNet\u6027\u80fd\u4f18\u5f02\uff08\u5e73\u5747Dice>0.93\uff09\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-7-11-1-1.png\")
<\/figure>\n<\/div>\n\n\n
23.\u00a0\u00a0 \u00a0Xiao et al.,\u201cEstimating Reference Bony Shape Model for Personalized Surgical Reconstruction of Posttraumatic Facial Defects\u201d.<\/strong>
\u989d\u9762\u77eb\u6b63\u624b\u672f\u4e2d\uff0c\u9700\u672f\u524d\u4f30\u8ba1\u75c5\u4eba\u6b63\u5e38\u7684\u9762\u90e8\u9aa8\u9abc\u5f62\u72b6\u7528\u4e8e\u672f\u524d\u89c4\u5212\u3002Xiao\u7b49\u4eba[23]\u9488\u5bf9\u56e0\u4e8b\u6545\uff08\u5982\u8f66\u7978\uff0c\u6218\u4e89\u7b49\uff09\u9020\u6210\u7684\u9762\u90e8\u7f3a\u635f\uff0c\u63d0\u51fa\u4e86\u4e00\u79cd\u81ea\u52a8\u5316\u75c5\u4eba\u6b63\u5e38\u9762\u90e8\u9aa8\u9abc\u5f62\u72b6\u9884\u6d4b\u65b9\u6cd5\u3002\u8be5\u65b9\u6cd5\u5229\u7528\u75c5\u4eba\u4e8b\u6545\u524d\u62cd\u6444\u7684\u4eba\u8138\u7167\u7247\u53ca\u5f53\u524d\u75c5\u4eba\u5934\u90e8CT\u5f71\u50cf\uff0c\u5e76\u7ed3\u5408\u4e09\u7ef4\u4eba\u8138\u91cd\u5efa\u3001\u7a00\u758f\u8868\u793a\u3001\u7edf\u8ba1\u5f62\u72b6\u6a21\u578b\u53ca\u5f62\u53d8\u5efa\u6a21\u7b49\u6280\u672f\uff0c\u7cbe\u786e\u4e14\u5feb\u901f\u5730\u6062\u590d\u75c5\u4eba\u6b63\u5e38\u9762\u90e8\u9aa8\u9abc\u5f62\u72b6\uff08\u56fe28\uff09\u3002\u76f8\u5bf9\u4e8e\u4f20\u7edf\u4f9d\u9760\u533b\u751f\u7ecf\u9a8c\u624b\u5de5\u6784\u5efa\u6b63\u5e38\u9aa8\u9abc\u7684\u65b9\u6cd5\uff0c\u8be5\u65b9\u6cd5\u4e0d\u4f46\u63d0\u9ad8\u4e86\u9884\u6d4b\u7684\u7cbe\u5ea6\u53ca\u6548\u7387\uff0c\u540c\u65f6\u4e5f\u4f18\u5316\u4e86\u6b64\u7c7b\u989d\u9762\u77eb\u6b63\u624b\u672f\u7684\u672f\u524d\u89c4\u5212\u5b9e\u65bd\u6d41\u7a0b\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-7-12-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\n\n\n\n
24.\u00a0\u00a0 \u00a0Tang et al.,\u201cPre-operative Overall Survival Time Prediction for Glioblastoma Patients Using Deep Learning on Both Imaging Phenotype and Genotype\u201d.<\/strong>
\u7814\u7a76\u8bc1\u660e\u80f6\u8d28\u6bcd\u7ec6\u80de\u7624\uff08GBM\uff09\u60a3\u8005\u9884\u540e\u4e0e\u80bf\u7624\u7684\u5206\u5b50\u75c5\u7406\u6307\u6807\u6709\u7740\u5341\u5206\u7d27\u5bc6\u7684\u8054\u7cfb\u3002\u76ee\u524dGBM\u9884\u540e\u7814\u7a76\u4e3b\u8981\u57fa\u4e8e\u672f\u524d\u9884\u6d4b\uff0c\u800c\u672f\u524d\u65e0\u6cd5\u5f97\u77e5\u80bf\u7624\u5206\u5b50\u75c5\u7406\u4fe1\u606f\uff0c\u56e0\u6b64\u65e0\u6cd5\u5229\u7528\u8be5\u4fe1\u606f\u63d0\u9ad8\u9884\u540e\u7cbe\u5ea6\u3002Tang\u7b49\u4eba[24]\u63d0\u51fa\u4e86\u4e00\u79cd\u591a\u4efb\u52a1\u7684\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\uff0c\u4ece\u672f\u524d\u591a\u6a21\u6001\u8111\u5f71\u50cf\u6570\u636e\u4e2d\u63d0\u53d6\u4e0e\u80bf\u7624\u5206\u5b50\u75c5\u7406\u76f8\u5173\u7684\u7279\u5f81\uff0c\u5e76\u5c06\u5176\u7528\u4e8e\u5206\u5b50\u75c5\u7406\u5206\u578b\u9884\u6d4b\u548c\u5168\u56e0\u751f\u5b58\u671f\uff08Overall Survival\uff09\u9884\u6d4b\u4e2d\uff0c\u901a\u8fc7\u540c\u65f6\u63d0\u53d6\u5206\u5b50\u75c5\u7406\u76f8\u5173\u7684\u7279\u5f81\u6765\u63d0\u9ad8\u9884\u540e\u7684\u9884\u6d4b\u7cbe\u5ea6\u3002\u8be5\u6587\u4f7f\u7528\u5408\u4f5c\u533b\u9662\u4e34\u5e8a\u91c7\u96c6\u7684120\u540dGBM\u60a3\u8005\u7684\u591a\u6a21\u6001\u8111\u5f71\u50cf\uff08T1\u589e\u5f3a\u548c\u5f25\u6563\u52a0\u6743\u6210\u50cfDWI\uff09\uff0c\u91c7\u7528\u5341\u6298\u4ea4\u53c9\u9a8c\u8bc1\uff0c\u4e0e\u73b0\u6709\u9884\u540e\u9884\u6d4b\u65b9\u6cd5\u76f8\u6bd4\uff0c\u8be5\u65b9\u6cd5\u5728\u5168\u56e0\u751f\u5b58\u671f\u9884\u6d4b\u4efb\u52a1\u4e2d\u8fbe\u5230\u4e86\u6bd4\u4f20\u7edf\u65b9\u6cd5\u66f4\u9ad8\u7684\u7cbe\u5ea6\uff08\u56fe29\uff09\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-7-13-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\u00a0\u00a0 \u00a0
25.\u00a0\u00a0 \u00a0Zhu et al.,\u201cRobust and Discriminative Brain Genome Association Analysis\u201d.<\/strong>
\u4e3a\u4e86\u89e3\u51b3\u73b0\u6709Brain Genome Association (BGA) \u7814\u7a76\u672a\u8003\u8651\u7c7b\u6807\u7b7e\u800c\u5bfc\u81f4BGA\u7814\u7a76\u4e0d\u5177\u6709\u5224\u522b\u80fd\u529b\u7684\u7f3a\u9677\uff0cZhu\u7b49\u4eba[25]\u63d0\u51fa BGA\u5206\u6790\u6a21\u578b\u3002\u8be5\u6a21\u578b\u5229\u7528\u7c7b\u6807\u7b7e\uff0c\u540c\u65f6\u8fd8\u8003\u8651\u4e86\u6570\u636e\u6e90\u95f4\u7684\u5f02\u8d28\u6027\u548c\u6570\u636e\u6837\u672c\u7684\u566a\u97f3\u7b49\u95ee\u9898\u8fdb\u884cBGA\u5206\u6790\u3002\u91c7\u7528\u5341\u6298\u4ea4\u53c9\u4ea4\u53c9\u9a8c\u8bc1\uff0c\u8be5\u6587\u6240\u8ff0\u65b9\u6cd5\u7684\u5206\u7c7b\u7cbe\u5ea6\u8d85\u8fc7\u6700\u597d\u5bf9\u6bd4\u7b97\u6cd53.6%\uff0c\u5e76\u8fdc\u4f18\u4e8ebaseline\u65b9\u6cd5\uff08\u56fe30\uff09\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-7-14-1-1.png\")
<\/figure>\n<\/div>\n\n\n
\n\n\n\n
\u4eba\u8111\u5fae\u7ed3\u6784<\/strong><\/p>\n\n\n\n
26.\u00a0\u00a0 \u00a0Huynh et al.,\u201cProbing Brain Micro-Architecture by Orientation Distribution Invariant Identification of Diffusion Compartments\u201d.<\/strong>
\u5f25\u6563\u78c1\u5171\u632f\u6210\u50cf\u80fd\u591f\u7528\u4e8e\u6620\u5c04\u4eba\u8111\u7ec4\u7ec7\u7684\u5fae\u7ed3\u6784\u53d8\u5316\uff0c\u4f46\u4eba\u8111\u5fae\u7ed3\u6784\u7ec4\u7ec7\u4e4b\u95f4\u901a\u5e38\u5177\u6709\u8f83\u5927\u7684\u53d8\u5f02\u6027\u3002Huynh\u7b49\u4eba[26]\u63d0\u51fa\u4e86\u4e00\u79cd\u7403\u9762\u5e73\u5747\u4fe1\u53f7\u8c31\u6210\u50cf\u6280\u672f (Spherical Mean Spectrum Imaging, SMSI)\uff0c\u7528\u4e8e\u5b9a\u91cf\u5fae\u7ed3\u6784\u53d8\u5316\u3002\u8be5\u65b9\u6cd5\u4e0d\u4f9d\u8d56\u4e8e\u56fa\u5b9a\u7684\u7ec4\u7ec7\u6210\u5206\u6570\u91cf\u5047\u8bbe\uff0c\u800c\u662f\u5c06\u6269\u6563\u4fe1\u53f7\u8868\u793a\u4e3a\u4ece\u7c97\u5230\u7ec6\u7684\u591a\u5c3a\u5ea6\u5149\u8c31\u6269\u6563\u8fc7\u7a0b\u3002\u8be5\u65b9\u6cd5\u5141\u8bb8\u5b9a\u91cf\u795e\u7ecf\u8f74\u7a81\u5bc6\u5ea6\uff0c\u5fae\u89c2\u6269\u6563\u5404\u5411\u5f02\u6027\uff0c\u8f74\u7a81\u95f4\u81ea\u7531\u6269\u6563\u7cfb\u6570\u7b49\u591a\u79cd\u7ec4\u7ec7\u53d8\u5316\u3002\u5229\u7528\u5a74\u513f\u8111\u8fde\u63a5\u7ec4\u8ba1\u5212 \uff08Baby Connectome Project\uff09\uff0c\u9a8c\u8bc1\u4e86\u8be5\u65b9\u6cd5\u5373\u5feb\u901f\u53c8\u51c6\u786e\uff0c\u5e76\u4e14\u80fd\u591f\u514b\u670d\u6700\u5148\u8fdb\u7684\u5fae\u7ed3\u6784\u6a21\u578b\u4e2d\u7684\u504f\u5dee; \u540c\u65f6\u63ed\u793a\u4e86\u5a74\u513f\u51fa\u751f\u540e\u4e24\u5e74\u5185\u5927\u8111\u5fae\u89c2\u7ed3\u6784\u7684\u53d8\u5316\uff08\u5982\u56fe31\u6240\u793a\uff09\u3002
\u00a0<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-4-13-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
27. Huynh et al., \u201cCharacterizing Non-Gaussian Diffusion in Heterogeneously Oriented Tissue Microenvironments\u201d.<\/strong>
\u5728\u4eba\u8111\u4e2d\uff0c\u590d\u6742\u7684\u5404\u7c7b\u7ec4\u7ec7\u7ec6\u80de\u53ca\u5176\u7ec6\u80de\u819c\u7b49\u5fae\u7ed3\u6784\u7ec4\u7ec7\u4f7f\u5f97\u6c34\u5206\u5b50\u7684\u6269\u6563\u8fd0\u52a8\u504f\u79bb\u5178\u578b\u7684\u9ad8\u65af\u5206\u5e03\u3002\u5c3d\u7ba1\u6269\u6563\u5cf0\u5ea6\u6210\u50cf (Diffusion Kurtosis Imaging, DKI) \u80fd\u591f\u91cf\u5316\u8fd9\u79cd\u975e\u9ad8\u65af\u5f62\u6001\uff0c\u4f46\u5f80\u5f80\u88ab\u590d\u6742\u7684\u767d\u8d28\u7ea4\u7ef4\u7ed3\u6784\u6240\u6df7\u6dc6\uff0c\u4f8b\u5982\u7ea4\u7ef4\u5206\u53c9\u3001\u5f2f\u66f2\u548c\u5206\u652f\u7b49\u3002Huynh\u7b49\u4eba[27]\u63d0\u51fa\u4e86\u4e00\u79cd\u65b0\u7684\u6269\u6563\u5cf0\u5ea6\u6210\u50cf\u6a21\u578b\uff0c\u5141\u8bb8\u5728\u975e\u5747\u5300\u65b9\u5411\u7684\u5fae\u7ed3\u6784\u73af\u5883\u4e2d\u8868\u5f81\u5fae\u7ed3\u6784\u7684\u975e\u9ad8\u65af\u5f62\u6001\u3002\u8be5\u65b9\u6cd5\u7ed9\u4e88\u4e00\u4e2a\u66f4\u5e7f\u4e49\u7684\u7ed3\u679c\uff0c\u5373\u7403\u9762\u5e73\u5747\u4fe1\u53f7\u4e0d\u4f9d\u8d56\u4e8e\u4f53\u7d20\u5185\u7684\u7ea4\u7ef4\u65b9\u5411\u5206\u5e03\uff0c\u56e0\u6b64\u53ef\u4ee5\u5c06\u6269\u6563\u4fe1\u53f7\u7684\u5e73\u5747\u503c\u62df\u5408\u5230\u5bf9\u79f0\u7684\u5cf0\u5ea6\u6a21\u578b\u4e2d\uff0c\u907f\u514d\u4e86\u590d\u6742\u7684\u767d\u8d28\u7ea4\u7ef4\u7ed3\u6784\u5bf9\u6a21\u578b\u672c\u8eab\u7684\u5f71\u54cd\u3002\u5b9e\u9a8c\u8bc1\u660e\u4e86\u5728\u6709\u65b9\u5411\u5f02\u8d28\u6027\u7684\u5927\u8111\u7ec4\u7ec7\u7ed3\u6784\u4e2d\uff0c\u76f8\u6bd4\u4e8e\u76ee\u524d\u7684DKI\u6280\u672f\uff0c\u8be5\u6587\u6240\u63d0\u51fa\u7684\u65b9\u6cd5\u5728\u5b9a\u91cf\u5fae\u7ed3\u6784\u7684\u975e\u9ad8\u65af\u5f62\u6001\u4e2d\u5177\u6709\u66f4\u9ad8\u7684\u4e00\u81f4\u6027\uff08\u56fe32\uff09\u3002<\/p>\n\n\n![\"\"](\"http:\/\/106.52.84.14\/wp-content\/uploads\/2025\/04\/image-85-4-14-1-1.jpg\")
<\/figure>\n<\/div>\n\n\n
\n\n\n\n
[1] \u201cRCA-U-Net: Residual Channel Attention U-Net for Fast Tissue Quantification in Magnetic Resonance Fingerprinting\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Zhenghan Fang, Yong Chen, Dong Nie, Weili Lin, and Dinggang Shen]
[2] \u201cWavelet-Based Semi-Supervised Adversarial Learning for Synthesizing Realistic 7T from 3T MRI\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Liangqiong Qu, Shuai Wang, Pew-Thian Yap*, Dinggang Shen*] * Co-corresponding authors
[3] \u201cReconstructing High-Quality Diffusion MRI Data from Orthogonal Slice-Undersampled Data Using Graph Convolutional Neural Networks\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Yoonmi Hong, Geng Chen, Pew-Thian Yap*, Dinggang Shen*] * Co-corresponding authors
[4] \u201cMulti-Stage Image Quality Assessment of Diffusion MRI via Semi-Supervised Nonlocal Residual Networks\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Siyuan Liu, Kim-Han Thung, Weili Lin, Pew-Thian Yap, Dinggang Shen]
[5] \u201cDisease-Image Specific Generative Adversarial Network for Brain Disease Diagnosis with Incomplete Multi-Modal Neuroimages\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Yongsheng Pan, Mingxia Liu*, Chunfeng Lian, Yongxia*, Dinggang Shen*] * Co-corresponding authors
[6] \u201cCoCa-GAN: Common-feature-learning-based Context-aware Generative Adversarial Network for Glioma Grading\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Pu Huang, Dengwang Li, Zhicheng Jiao, Dongming Wei, Guoshi Li, Han Zhang*, and Dinggang Shen*] * Co-corresponding authors
[7] \u201cSynthesis and Inpainting-based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Dongming Wei, Sahar Ahmad, Jiayu Huo, Yunhao Ge, Wen Peng, Pew-Thian Yap, Zhong Xue, Dinggang Shen*, Qian Wang*] * Co-corresponding authors
[8] \u201cIntrinsic Patch-based Cortical Anatomical Parcellation using Graph Convolutional Neural Network on Surface Manifold\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Zhengwang Wu, Fenqiang Zhao, Jing Xia, Li Wang, Gang Li*, Dinggang Shen*] * Co-corresponding authors
[9] \u201cAutomated Parcellation of the Cortex Using Structural Connectome Harmonics\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [H. Patrick Taylor IV, Zhengwang Wu, Ye Wu, Dinggang Shen, Han Zhang, Pew-Thian Yap]
[10] \u201cSurface-Volume Consistent Construction of Longitudinal Atlases for the Early Developing Brains\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Sahar Ahmad, Zhengwang Wu, Gang Li, Li Wang, Weili Lin, Pew-Thian Yap*, Dinggang Shen*, and the UNC\/UMN Baby Connectome Project Consortium] * Co-corresponding authors
[11] \u201cRevealing Developmental Regionalization of Infant Cerebral Cortex Based on Multiple Cortical Properties\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Fan Wang, Chunfeng Lian, Zhengwang Wu, Li Wang, John Gilmore, Weili Lin, Dinggang Shen, Gang Li]
[12] \u201cHarmonization of Infant Cortical Thickness using Surface-to-Surface Cycle-Consistent Adversarial Networks\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Fenqiang Zhao, Zhengwang Wu, Li Wang, Weili Lin, Shunren Xia, Dinggang Shen, Gang Li]
[13] \u201cEarly Development of Infant Brain Complex Network\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Weixiong Jiang, Han Zhang*, Ye Wu , Liming Hsu, Dan Hu, Dinggang Shen*] * Co-corresponding authors
[14] \u201cMulti-layer temporal network analysis reveals increasing temporal reachability and spreadability in the first two years of life\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Zhen Zhou, Han Zhang*, Li-Ming Hsu, Weili Lin, Gang Pan*, Dinggang Shen*, and the UNC\/UMN Baby Connectome Project Consortium] * Co-corresponding authors
[15] \u201cA Deep Learning Framework for Noise Component Detection from Resting-state Functional MRI\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Tae-Eui Kam, Xuyun Wen, Bing Jin, Zhicheng Jiao, Li-Ming Hsu, Zhen Zhou, Yujie Liu, Koji Yamashita, Sheng-Che Hung, Weili Lin, Han Zhang*, and Dinggang Shen*, and the UNC\/UMN Baby Connectome Project Consortium] * Co-corresponding authors
[16] \u201cDeep Granular Feature-Label Distribution Learning for Neuroimaging-based Infant Age Prediction\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Dan Hu, Han Zhang, Zhengwang Wu, Weili Lin, Gang Li*, Dinggang Shen*, and the UNC\/UMN Baby Connectome Project Consortium] * Co-corresponding authors
[17] \u201cInter-modality Dependence Induced Data Recovery for MCI Conversion Prediction\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Tao Zhou, Kimhan Thung, Yu Zhang, Huazhu Fu, Jianbing Shen, Dinggang Shen, Ling Shao]
[18] \u201cEnd-to-End Dementia Status Prediction from Brain MRI using Multi-Task Weakly-Supervised Attention Network\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Chunfeng Lian, Mingxia Liu*, Li Wang, Dinggang Shen*] * Co-corresponding authors
[19] \u201cDynamic Routing Capsule Networks for Mild Cognitive Impairment Diagnosis\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Zhicheng Jiao, Pu Huang, Tae-Eui Kam, Li-Ming Hsu, Ye Wu, Han Zhang*, and Dinggang Shen*] * Co-corresponding authors
[20] \u201cDeep Multi-modal Latent Representation Learning for Automated Dementia Diagnosis\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Tao Zhou, Mingxia Liu, Huazhu Fu, Jun Wang, Jianbing Shen, Ling Shao, Dinggang Shen]
[21] \u201cIdentification of Abnormal Circuit Dynamics in Major Depressive Disorder via Multiscale Neural Modeling of Resting-state fMRI\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Guoshi Li, Yujie Liu, Yanting Zheng, Ye Wu, Pew-Thian Yap, Shijun Qiu, Han Zhang*, and Dinggang Shen*] * Co-corresponding authors
[22] \u201cMeshSNet: Deep Multi-Scale Mesh Feature Learning for End-to-End Tooth Labeling on 3D Dental Surfaces\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Chunfeng Lian, Li Wang*, Tai-Hsien Wu, Mingxia Liu*, Francisca Dur\u00e1n, Ching-Chang Ko, Dinggang Shen*] * Co-corresponding authors
[23] \u201cEstimating Reference Bony Shape Model for Personalized Surgical Reconstruction of Posttraumatic Facial Defects\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Deqiang Xiao, Li Wang, Hannah Deng, Kim-Han Thung, Jihua Zhu, Peng Yuan, Yriu L. Rodrigues, Leonel Perez, Jr., Christopher E. Crecelius, Jaime Gateno, Tiansku Kuang, Steve G.F. Shen, Daeseung Kim, David M. Alfi, Pew-Thian Yap, James J. Xia*, Dinggang Shen*] * Co-corresponding authors
[24] \u201cPre-operative Overall Survival Time Prediction for Glioblastoma Patients Using Deep Learning on Both Imaging Phenotype and Genotype\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Zhenyu Tang, Yuyun Xu, Zhicheng Jiao, Junfeng Lu, Lei Jin, Abudumijiti Aibaidula, Jinsong Wu, Qian Wang, Han Zhang*, and Dinggang Shen*] * Co-corresponding authors
[25] \u201cRobust and Discriminative Brain Genome Association Analysis\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Xiaofeng Zhu, Dinggang Shen]
[26] \u201cProbing Brain Micro-Architecture by Orientation Distribution Invariant Identification of Diffusion Compartments\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Khoi Huynh, Tiantian Xu, Ye Wu, Geng Chen, Kim-Han Thung, Haiyong Wu, Weili Lin, Dinggang Shen, and Pew-Thian Yap, and the UNC\/UMN Baby Connectome Project Consortium]
[27] \u201cCharacterizing Non-Gaussian Diffusion in Heterogeneously Oriented Tissue Microenvironments\u201d, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019. [Khoi Huynh, Tiantian Xu, Ye Wu, Kim-Han Thung, Geng Chen, Weili Lin, Dinggang Shen, and Pew-Thian Yap]
<\/p>\n","protected":false},"excerpt":{"rendered":"