Opinions Vary? Diagnosis First!

被引:2
|
作者
Wu, Junde [1 ]
Fang, Huihui [1 ]
Yang, Dalu [1 ]
Wang, Zhaowei [1 ]
Zhou, Wenshuo [1 ]
Shang, Fangxin [1 ]
Yang, Yehui [1 ]
Xu, Yanwu [1 ]
机构
[1] Intelligent Healthcare Unit, Beijing, Peoples R China
关键词
Multi-rater learning; Optic disc/cup segmentation; Glaucoma diagnosis;
D O I
10.1007/978-3-031-16434-7_58
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the advancement of deep learning techniques, an increasing number of methods have been proposed for optic disc and cup (OD/OC) segmentation from the fundus images. Clinically, OD/OC segmentation is often annotated by multiple clinical experts to mitigate the personal bias. However, it is hard to train the automated deep learning models on multiple labels. A common practice to tackle the issue is majority vote, e.g., taking the average of multiple labels. However such a strategy ignores the different expertness of medical experts. Motivated by the observation that OD/OC segmentation is often used for the glaucoma diagnosis clinically, in this paper, we propose a novel strategy to fuse the multi-rater OD/OC segmentation labels via the glaucoma diagnosis performance. Specifically, we assess the expertness of each rater through an attentive glaucoma diagnosis network. For each rater, its contribution for the diagnosis will be reflected as an expertness map. To ensure the expertness maps are general for different glaucoma diagnosis models, we further propose an Expertness Generator (ExpG) to eliminate the high-frequency components in the optimization process. Based on the obtained expertness maps, the multi-rater labels can be fused as a single ground-truth which we dubbed as Diagnosis First Ground-truth (DiagFirstGT). Experimental results show that by using DiagFirstGT as ground-truth, OD/OC segmentation networks will predict the masks with superior glaucoma diagnosis performance.
引用
收藏
页码:604 / 613
页数:10
相关论文
共 50 条
  • [1] OPINIONS VARY ON CERTIFICATION
    HELLIER, CJ
    [J]. MATERIALS EVALUATION, 1994, 52 (11) : 1232 - 1232
  • [2] Opinions vary on whether we know It all
    Zetie, Carl
    [J]. NEW SCIENTIST, 2018, 239 (3197) : 54 - 54
  • [3] LASER ANGIOPLASTY - PROGRESSING, BUT OPINIONS, FORECASTS VARY
    GOLDSMITH, MF
    [J]. JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 1985, 253 (11): : 1525 - 1527
  • [4] OPINIONS VARY ON HOSPITAL ANTITRUST INVOLVEMENT IN 86
    BURDA, D
    [J]. HOSPITALS, 1986, 60 (02): : 40 - 40
  • [5] Opinions Vary on Pharmaco-genetic Exceptionalism
    不详
    [J]. CLINICAL PHARMACOLOGY & THERAPEUTICS, 2022, 112 (04) : 744 - 744
  • [6] Opinions vary on India's new biodiversity act
    Sharma, DC
    [J]. FRONTIERS IN ECOLOGY AND THE ENVIRONMENT, 2003, 1 (01) : 8 - 8
  • [7] Do First Opinions Affect Second Opinions?
    Geva Vashitz
    Joseph S. Pliskin
    Yisrael Parmet
    Yona Kosashvili
    Gal Ifergane
    Shlomo Wientroub
    Nadav Davidovitch
    [J]. Journal of General Internal Medicine, 2012, 27 : 1265 - 1271
  • [8] Do First Opinions Affect Second Opinions?
    Vashitz, Geva
    Pliskin, Joseph S.
    Parmet, Yisrael
    Kosashvili, Yona
    Ifergane, Gal
    Wientroub, Shlomo
    Davidovitch, Nadav
    [J]. JOURNAL OF GENERAL INTERNAL MEDICINE, 2012, 27 (10) : 1265 - 1271
  • [9] First the report, then the opinions on it
    Sullivan, P
    [J]. CANADIAN MEDICAL ASSOCIATION JOURNAL, 2003, 168 (01) : 79 - 79
  • [10] Opinions vary on whether unabomb suspect will damage science's image
    Durso, TW
    [J]. SCIENTIST, 1996, 10 (12): : 3 - &