图书馆 | 所内网 | 所长信箱 | English | 中国科学院
站内搜索  
 
首 页 新闻 机构概况 机构设置 科研成果 研究队伍 研究生教育 国际交流 院地合作 学术期刊 创新文化 党群园地 科学传播
 
科研成果
概况介绍
论文
专著
专利
成果转化
研究所图库
园区一角南区办公楼实验楼(R楼)园区一角科研楼(A楼)自动化所鸟瞰自动化所正门
相关链接
ARP Email 所报
 您现在的位置:首页 > 科研成果 >论文
论文题目: Multi-class Latent Concept Pooling for computer-aided endoscopy diagnosis
第一作者: Wang S(王帅);Cong Y(丛杨);Fan HJ(范慧杰);Fan BJ(范保杰);Liu LQ(刘连庆);Yang YS(杨云生);Tang YD(唐延东);Zhao HC(赵怀慈);Yu HB(于海斌)
参与作者:
联系作者:
发表刊物: ACM Transactions on Multimedia Computing, Communications and Applications
发表年度: 2017
卷,期,页: 13,2,1-18
论文出处:
第一作者所在部门:
论文编号:
论文摘要: Successful computer-aided diagnosis systems typically rely on training datasets containing sufficient and richly annotated images. However, detailed image annotation is often time consuming and subjective, especially for medical images, which becomes the bottleneck for the collection of large datasets and then building computer-aided diagnosis systems. In this article, we design a novel computer-aided endoscopy diagnosis system to deal with the multi-classification problem of electronic endoscopy medical records (EEMRs) containing sets of frames, while labels of EEMRs can be mined from the corresponding text records using an automatic text-matching strategy without human special labeling. With unambiguous EEMR labels and ambiguous frame labels, we propose a simple but effective pooling scheme called Multi-class Latent Concept Pooling, which learns a codebook from EEMRs with different classes step by step and encodes EEMRs based on a soft weighting strategy. In our method, a computer-aided diagnosis system can be extended to new unseen classes with ease and applied to the standard single-instance classification problem even though detailed annotated images are unavailable. In order to validate our system, we collect 1,889 EEMRs with more than 59K frames and successfully mine labels for 348 of them. The experimental results show that our proposed system significantly outperforms the state-of-the-art methods. Moreover, we apply the learned latent concept codebook to detect the abnormalities in endoscopy images and compare it with a supervised learning classifier, and the evaluation shows that our codebook learning method can effectively extract the true prototypes related to different classes from the ambiguous data.
论文全文:
其他备注:
附件下载:
 
中国科学院沈阳自动化研究所 版权所有 1996-2009 辽ICP备05000867 联系我们
地址:中国辽宁省沈阳市东陵区南塔街114号 邮编:110016 留言反馈 网站地图