Mining Gaze for Contrastive Learning toward Computer-Assisted Diagnosis
2024
会议录名称THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 7
ISSN2159-5399
页码7543-7551
摘要Obtaining large-scale radiology reports can be difficult for medical images due to various reasons, limiting the effectiveness of contrastive pre-training in the medical image domain and underscoring the need for alternative methods. In this paper, we propose eye-tracking as an alternative to text reports, as it allows for the passive collection of gaze signals without disturbing radiologist's routine diagnosis process. By tracking the gaze of radiologists as they read and diagnose medical images, we can understand their visual attention and clinical reasoning. When a radiologist has similar gazes for two medical images, it may indicate semantic similarity for diagnosis, and these images should be treated as positive pairs when pre-training a computer-assisted diagnosis (CAD) network through contrastive learning. Accordingly, we introduce the Medical contrastive Gaze Image Pre-training (McGIP) as a plug-and-play module for contrastive learning frameworks. McGIP uses radiologist's gaze to guide contrastive pre-training. We evaluate our method using two representative types of medical images and two common types of gaze data. The experimental results demonstrate the practicality of McGIP, indicating its high potential for various clinical scenarios and applications.
会议名称38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence
出版地2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA
会议地点null,Vancouver,CANADA
会议日期FEB 20-27, 2024
URL查看原文
收录类别CPCI-S
语种英语
资助项目Key R&D Program of Guangdong Province, China[2021B0101420006]
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号WOS:001239937300116
出版者ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE
EISSN2374-3468
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/381322
专题生物医学工程学院
信息科学与技术学院_本科生
生物医学工程学院_PI研究组_沈定刚组
生物医学工程学院_PI研究组_王乾组
通讯作者Shen, Dinggang
作者单位
1.ShanghaiTech Univ, Sch Biomed Engn, Shanghai, Peoples R China
2.ShanghaiTech Univ, State Key Lab Adv Med Mat & Devices, Shanghai, Peoples R China
3.Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai, Peoples R China
4.Shanghai United Imaging Intelligence Co Ltd, Shanghai, Peoples R China
5.Shanghai Clin Res & Trial Ctr, Shanghai, Peoples R China
第一作者单位生物医学工程学院;  上海科技大学
通讯作者单位生物医学工程学院;  上海科技大学
第一作者的第一单位生物医学工程学院
推荐引用方式
GB/T 7714
Zhao, Zihao,Wang, Sheng,Wang, Qian,et al. Mining Gaze for Contrastive Learning toward Computer-Assisted Diagnosis[C]. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE,2024:7543-7551.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Zhao, Zihao]的文章
[Wang, Sheng]的文章
[Wang, Qian]的文章
百度学术
百度学术中相似的文章
[Zhao, Zihao]的文章
[Wang, Sheng]的文章
[Wang, Qian]的文章
必应学术
必应学术中相似的文章
[Zhao, Zihao]的文章
[Wang, Sheng]的文章
[Wang, Qian]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。