第3期 付常洋，等：基于深度学习与结构磁共振成像的抑郁症辅助诊断 ·551· ageNet classification with deep convolutional neural net- ternational Conference on Artificial Intelligence and Stat- works[C]//Proceedings of the 25th International Confer- istics.Fort Lauderdale.USA.2011:315-323. ence on Neural Information Processing Systems.Lake [25]TAJBAKHSH N.SHIN J Y.GURUDU S R.et al.Con- Tahoe,USA,2012:1097-1105. volutional neural networks for medical image analysis: [12]DONAHUE J.HENDRICKS L A.ROHRBACH M,et al. full training or fine tuning[J].IEEE transactions on med- Long-term recurrent convolutional networks for visual re- ical imaging,.2016,35(5):1299-1312. cognition and description[J].IEEE transactions on pat- [26]HON M,KHAN N M.Towards Alzheimer's disease clas- tern analysis and machine intelligence,2017,39(4): sification through transfer learning[C]//IEEE Internation- 677-691. al Conference on Bioinformatics and Biomedicine.Kan- [13]KERMANY D S,GOLDBAUM M,CAI Wenjia,et al. sas City,USA,2017:1166-1169. Identifying medical diagnoses and treatable diseases by [27]LIU Renhao,HALL L O,GOLDGOF D B,et al.Explor- image-based deep learning[J].Cell,2018,172(5): ing deep features from brain tumor magnetic resonance 1122-1131,e1-e2. images via transfer learning[C]//International Joint Con- [14]吕鸿蒙，赵地，迟学斌.基于增强AlexNet的深度学习的 ference on Neural Networks.Vancouver,Canada,2016: 阿尔茨海默病的早期诊断[J1.计算机科学，2017， 235-242. 44(S1:50-60. [28]DA NOBREGA R V M,PEIXOTO S A.DA SILVA S P LV Hongmeng,ZHAO Di,CHI Xuebin.Deep learning P,et al.Lung nodule classification via deep transfer learn- for early diagnosis of Alzheimer's disease based on in- ing in CT lung images[C]//IEEE 31st International Sym- tensive AlexNet[J].Computer science,2017,44(S1): posium on Computer-Based Medical Systems.Karlstad, 50-60. Sweden,2018:244-249. [15]LITJENS G,KOOI T,BEJNORDI B E,et al.A survey on [29]CHEN S.MA K.AND ZHENG Y.Med3D:transfer deep learning in medical image analysis[J].Medical im- learning for 3D medical image analysis[EB/OL]. age analysis,2017,42:60-88. (2019-04-09)[2019-09-025]https:://arxiv..org/abs/1904.0 [16]SZEGEDY C,LIU Wei,JIA Yangqing,et al.Going deep- 0625. er with convolutions[C]//IEEE Conference on Computer [30]DIEDERIK P K,JIMMY B.Adam:a method for Vision and Pattern Recognition.Boston,USA,2015:1-9. stochastic optimization[J/OL].(2017-1-30)[2019-9- [17]SIMONYAN K,ZISSERMAN A.Very deep convolu- 29]https://arxiv.org/abs/1412.6980v5. tional networks for large-scale image recognition[J]. Computer science,2014,18(3):178-182. 作者简介： [18]SZEGEDY C.VANHOUCKE V.IOFFE S.et al.Re- 付常洋，硕士研究生，主要研究方 thinking the inception architecture for computer 向为图像处理与机器学习。 vision[C]//IEEE Conference on Computer Vision and Pat- tern Recognition.Las Vegas,USA,2016:2818-2826. [19]HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA,2016:770-778. [20]HUANG Gao,LIU Zhuang,VAN DER MAATEN L,et 王瑜，副教授，博士，中国自动化 al.Densely connected convolutional networks[Cl//IEEE 学会、中国电子学会和中国人工智能 Conference on Computer Vision and Pattern Recognition. 学会高级会员，生物信息学与人工生 命专委会委员，EEE和计算机学会会 Honolulu,USA,2017:2261-2269. 员，CCF YOCSEF委员，主要研究方 [21]ASHBURNER J,BARNES G,CHEN Chunchuan,et al. 向为图像处理与模式识别。主持国家 SPM12 manual[EB/OL].(2019-01-13)[2020-08-29] 自然科学基金面上项目2项、北京市 https://www.fil.ion.ucl.ac.uk/spm/software/spm12. 自然科学基金面上项目1项。出版学术专著2部，发表学术 [22]ARNONE D,MCKIE S,ELLIOTT R,et al.State-de- 论文30余篇。 pendent changes in hippocampal grey matter in depres sion[J].Molecular psychiatry,2013,18(12):1265-1272. 肖洪兵，副教授，博士，主要研究 [23]IOFFE S,SZEGEDY C.Batch normalization:accelerat- 方向为传感器与高动态测试技术、嵌 ing deep network training by reducing internal covariate 入式系统应用。在研以及完成的科研 shift[Cl//Proceedings of the 32nd International Confer- 项目10余项，其中省级以上项目 ence on International Conference on Machine Learning. 3项。获得北京市科技进步三等奖 Lille,France,2015:448-456. 1项。取得软件著作权3项，实用新 [24]GLOROT X,BORDES A,BENGIO Y.Deep sparse recti- 型专利3项。出版专著1部，主编教 fier neural networks[Cl//Proceedings of the Fourteenth In- 材3部，发表学术论文20余篇。ageNet classification with deep convolutional neural net￾works[C]//Proceedings of the 25th International Confer￾ence on Neural Information Processing Systems. Lake Tahoe, USA, 2012: 1097−1105. DONAHUE J, HENDRICKS L A, ROHRBACH M, et al. Long-term recurrent convolutional networks for visual re￾cognition and description[J]. IEEE transactions on pat￾tern analysis and machine intelligence, 2017, 39(4): 677–691. [12] KERMANY D S, GOLDBAUM M, CAI Wenjia, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5): 1122–1131, e1-e2. [13] 吕鸿蒙, 赵地, 迟学斌. 基于增强 AlexNet 的深度学习的 阿尔茨海默病的早期诊断 [J]. 计算机科学, 2017, 44(S1): 50–60. LV Hongmeng, ZHAO Di, CHI Xuebin. Deep learning for early diagnosis of Alzheimer's disease based on in￾tensive AlexNet[J]. Computer science, 2017, 44(S1): 50–60. [14] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Medical im￾age analysis, 2017, 42: 60–88. [15] SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deep￾er with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015: 1−9. [16] SIMONYAN K, ZISSERMAN A. Very deep convolu￾tional networks for large-scale image recognition[J]. Computer science, 2014, 18(3): 178–182. [17] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Re￾thinking the inception architecture for computer vision[C]//IEEE Conference on Computer Vision and Pat￾tern Recognition. Las Vegas, USA, 2016: 2818−2826. [18] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 770−778. [19] HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 2261−2269. [20] ASHBURNER J, BARNES G, CHEN Chunchuan, et al. SPM12 manual[EB/OL]. (2019−01−13)[2020−08−29]. https://www.fil.ion.ucl.ac.uk/spm/software/spm12. [21] ARNONE D, MCKIE S, ELLIOTT R, et al. State-de￾pendent changes in hippocampal grey matter in depres￾sion[J]. Molecular psychiatry, 2013, 18(12): 1265–1272. [22] IOFFE S, SZEGEDY C. Batch normalization: accelerat￾ing deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Confer￾ence on International Conference on Machine Learning. Lille, France, 2015: 448−456. [23] GLOROT X, BORDES A, BENGIO Y. Deep sparse recti￾fier neural networks[C]//Proceedings of the Fourteenth In- [24] ternational Conference on Artificial Intelligence and Stat￾istics. Fort Lauderdale, USA, 2011: 315−323. TAJBAKHSH N, SHIN J Y, GURUDU S R, et al. Con￾volutional neural networks for medical image analysis: full training or fine tuning[J]. IEEE transactions on med￾ical imaging, 2016, 35(5): 1299–1312. [25] HON M, KHAN N M. Towards Alzheimer’s disease clas￾sification through transfer learning[C]//IEEE Internation￾al Conference on Bioinformatics and Biomedicine. Kan￾sas City, USA, 2017: 1166−1169. [26] LIU Renhao, HALL L O, GOLDGOF D B, et al. Explor￾ing deep features from brain tumor magnetic resonance images via transfer learning[C]//International Joint Con￾ference on Neural Networks. Vancouver, Canada, 2016: 235−242. [27] DA NÓBREGA R V M, PEIXOTO S A, DA SILVA S P P, et al. Lung nodule classification via deep transfer learn￾ing in CT lung images[C]//IEEE 31st International Sym￾posium on Computer-Based Medical Systems. Karlstad, Sweden, 2018: 244−249. [28] CHEN S, MA K, AND ZHENG Y. Med3D: transfer learning for 3D medical image analysis[EB/OL]. (2019−04−09)[2019−09−025] https://arxiv.org/abs/1904.0 0625. [29] DIEDERIK P K, JIMMY B. Adam: a method for stochastic optimization[J/OL]. (2017-1-30)[2019-9- 29] https://arxiv.org/abs/1412.6980v5. [30] 作者简介： 付常洋，硕士研究生，主要研究方 向为图像处理与机器学习。 王瑜，副教授，博士，中国自动化 学会、中国电子学会和中国人工智能 学会高级会员，生物信息学与人工生 命专委会委员，IEEE 和计算机学会会 员，CCF YOCSEF 委员，主要研究方 向为图像处理与模式识别。主持国家 自然科学基金面上项目 2 项、北京市 自然科学基金面上项目 1 项。出版学术专著 2 部，发表学术 论文 30 余篇。 肖洪兵，副教授，博士，主要研究 方向为传感器与高动态测试技术、嵌 入式系统应用。在研以及完成的科研 项目 1 0 余项，其中省级以上项目 3 项。获得北京市科技进步三等奖 1 项。取得软件著作权 3 项，实用新 型专利 3 项。出版专著 1 部，主编教 材 3 部，发表学术论文 20 余篇。 第 3 期 付常洋，等：基于深度学习与结构磁共振成像的抑郁症辅助诊断 ·551·