中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Deep Collocative Learning for Immunofixation Electrophoresis Image Analysis

文献类型：期刊论文

作者Wei, Xiao-Yong9,10; Yang, Zhen-Qun8; Zhang, Xu-Lu9,10; Liao, Ga7; Sheng, Ai-Lin9,10; Zhou, S. Kevin4,5,6; Wu, Yongkang3; Du, Liang1,2
刊名IEEE TRANSACTIONS ON MEDICAL IMAGING
出版日期2021-07-01
卷号40期号:7页码:1898-1910
关键词Tensors Visualization Computational modeling Proteins Analytical models Logic gates Backtracking Immunofixation Electrophoresis deep collocative learning coached attention gates
ISSN号0278-0062
DOI10.1109/TMI.2021.3068404
英文摘要Immunofixation Electrophoresis (IFE) analysis is of great importance to the diagnosis of Multiple Myeloma, which is among the top-9 cancer killers in the United States, but has rarely been studied in the context of deep learning. Two possible reasons are: 1) the recognition of IFE patterns is dependent on the co-location of bands that forms a binary relation, different from the unary relation (visual features to label) that deep learning is good at modeling; 2) deep classification models may perform with high accuracy for IFE recognition but is not able to provide firm evidence (where the co-location patterns are) for its predictions, rendering difficulty for technicians to validate the results. We propose to address these issues with collocative learning, in which a collocative tensor has been constructed to transform the binary relations into unary relations that are compatible with conventional deep networks, and a location-label-free method that utilizes the Grad-CAM saliency map for evidence backtracking has been proposed for accurate localization. In addition, we have proposed Coached Attention Gates that can regulate the inference of the learning to be more consistent with human logic and thus support the evidence backtracking. The experimental results show that the proposed method has obtained a performance gain over its base model ResNet18 by 741.30% in IoU and also outperformed popular deep networks of DenseNet, CBAM, and Inception-v3.
资助项目National Natural Science Foundation of China[61872256] ; National Natural Science Foundation of China[81772275] ; Science and Technology Department of Sichuan Province[2020YFS0125]
WOS研究方向Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
语种英语
WOS记录号WOS:000668842500014
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/17510]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wu, Yongkang; Du, Liang
作者单位1.Sichuan Univ, West China Hosp, Chinese Evidence Based Med Ctr, Chengdu 610041, Peoples R China
2.Sichuan Univ, West China Hosp, Med Device Regulatory Res & Evaluat Ctr, Chengdu 610041, Peoples R China
3.Sichuan Univ, West China Hosp, Dept Lab Med & Outpatient, Chengdu 610041, Peoples R China
4.Chinese Acad Sci, CAS, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
5.Univ Sci & Technol China, Suzhou Inst Adv Res, Suzhou 215123, Peoples R China
6.Univ Sci & Technol China, Sch Biomed Engn, Med Imaging Robot & Analyt Comp Lab & Engn MIRACL, Suzhou 215123, Peoples R China
7.Sichuan Univ, West China Hosp Stomatol, Natl Clin Res Ctr Oral Dis, State Key Lab Oral Dis, Chengdu 610041, Peoples R China
8.Chinese Univ Hong Kong, Dept Biomed Engn, Hong Kong, Peoples R China
9.Peng Cheng Lab, Ctr Artificial Intelligence, Shenzhen 518055, Peoples R China
10.Sichuan Univ, Coll Comp Sci, Chengdu 610065, Peoples R China
推荐引用方式
GB/T 7714		 Wei, Xiao-Yong,Yang, Zhen-Qun,Zhang, Xu-Lu,et al. Deep Collocative Learning for Immunofixation Electrophoresis Image Analysis[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2021,40(7):1898-1910.
APA Wei, Xiao-Yong.,Yang, Zhen-Qun.,Zhang, Xu-Lu.,Liao, Ga.,Sheng, Ai-Lin.,...&Du, Liang.(2021).Deep Collocative Learning for Immunofixation Electrophoresis Image Analysis.IEEE TRANSACTIONS ON MEDICAL IMAGING,40(7),1898-1910.
MLA Wei, Xiao-Yong,et al."Deep Collocative Learning for Immunofixation Electrophoresis Image Analysis".IEEE TRANSACTIONS ON MEDICAL IMAGING 40.7(2021):1898-1910.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。