期刊
MODERN PATHOLOGY
卷 34, 期 12, 页码 2098-2108出版社
ELSEVIER SCIENCE INC
DOI: 10.1038/s41379-021-00859-x
关键词
-
类别
资金
- DFG [INST 216/512/1FUGG]
- National Cancer Institute [1U24CA199374-01, R01CA249992-01A1, R01CA202752-01A1, R01CA208236-01A1, R01CA216579-01A1, R01CA220581-01A1, 1U01CA239055-01, 1U01CA248226-01, 1U54CA254566-01]
- National Heart, Lung and Blood Institute [1R01HL15127701A1]
- National Institute for Biomedical Imaging and Bioengineering [1R43EB028736-01]
- National Center for Research Resources [1 C06 RR12463-01]
- VA Merit Review Award from the United States Department of Veterans Affairs Biomedical Laboratory Research and Development Service [IBX004121A]
- Office of the Assistant Secretary of Defense for Health Affairs, through the Breast Cancer Research Program [W81XWH-19-1-0668]
- Prostate Cancer Research Program [W81XWH-15-1-0558, W81XWH-20-1-0851]
- Lung Cancer Research Program [W81XWH-18-1-0440, W81XWH-20-1-0595]
- Peer Reviewed Cancer Research Program [W81XWH-18-1-0404]
- Kidney Precision Medicine Project (KPMP) Glue Grant
- Ohio Third Frontier Technology Validation Fund
- Clinical and Translational Science Collaborative of Cleveland from the National Center for Advancing Translational Sciences (NCATS) component of the National Institutes of Health [UL1TR0002548]
- NIH roadmap for Medical Research
- Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering at Case Western Reserve University
Digital pathology offers potential for computational analysis and automation of routine pathological tasks, but artifacts in histological slides can significantly impact the accuracy of deep learning-based models for cancer detection. Strategies to prevent accuracy losses in diagnostic models due to artifacts are necessary.
Digital pathology provides a possibility for computational analysis of histological slides and automatization of routine pathological tasks. Histological slides are very heterogeneous concerning staining, sections' thickness, and artifacts arising during tissue processing, cutting, staining, and digitization. In this study, we digitally reproduce major types of artifacts. Using six datasets from four different institutions digitized by different scanner systems, we systematically explore artifacts' influence on the accuracy of the pre-trained, validated, deep learning-based model for prostate cancer detection in histological slides. We provide evidence that any histological artifact dependent on severity can lead to a substantial loss in model performance. Strategies for the prevention of diagnostic model accuracy losses in the context of artifacts are warranted. Stress-testing of diagnostic models using synthetically generated artifacts might be an essential step during clinical validation of deep learning-based algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据