Deep Learning for Digital Pathology in Limited Data Scenarios.

• Superior document: Linköping Studies in Science and Technology. Licentiate Thesis Series ; v.2253
• Author: Stacke, Karin.
• Place / Publishing House: Linköping : : Linkopings Universitet,, 2022.; {copy}2022.
• Year of Publication: 2022
• Edition: 1st ed.
• Language: English
• Series: Linköping Studies in Science and Technology. Licentiate Thesis Series
• Physical Description: 1 online resource (85 pages)

Table of Contents

Intro -- Abstract -- Populärvetenskaplig sammanfattning -- Acknowledgments -- List of Publications -- Contributions -- Contents -- I Comprehensive Summary -- 1 Introduction -- 1.1 Digital pathology -- 1.2 Deep learning -- 1.3 Objectives and contributions -- 1.4 Thesis outline -- 2 Background -- 2.1 Medical images -- 2.2 Deep learning -- 2.3 Application on medical image data -- 3 Building robust models -- 3.1 Domain shift -- 3.2 Training strategies -- 3.3 Workflow strategies -- 3.4 Discussion -- 4 Handling limited data access -- 4.1 Utilizing labeled data -- 4.2 Utilizing unlabeled data -- 4.3 Discussion -- 5 Multi-modal training -- 5.1 Correlated feature learning -- 5.2 Discussion -- 6 Summary and discussion -- 6.1 Summary of contributions -- 6.2 Clinical impact -- 6.3 Ethical considerations -- 6.4 Future outlook -- 6.5 Concluding remarks -- Bibliography -- II Appended papers.