Deep Learning Based Decision Support for Medicine -- A Case Study on Skin Cancer Diagnosis
Preprint
Abstract
Early detection of skin cancers like melanoma is crucial to ensure high chances of survival for patients. Clinical application of Deep Learning (DL)-based Decision Support Systems (DSS) for skin cancer screening has the potential to improve the quality of patient care. The majority of work in the medical AI community focuses on a diagnosis setting that is mainly relevant for autonomous operation. Practical decision support should, however, go beyond plain diagnosis and provide explanations. This paper provides an overview of works towards explainable, DL-based decision support in medical applications with the example of skin cancer diagnosis from clinical, dermoscopic and histopathologic images. Analysis reveals that comparably little attention is payed to the explanation of histopathologic skin images and that current work is dominated by visual relevance maps as well as dermoscopic feature identification. We conclude that future work should focus on meeting the stakeholder's cognitive concepts, providing exhaustive explanations that combine global and local approaches and leverage diverse modalities. Moreover, the possibility to intervene and guide models in case of misbehaviour is identified as a major step towards successful deployment of AI as DL-based DSS and beyond.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Regulatory Frameworks for Development and Evaluation of Artificial Intelligence-Based Diagnostic Imaging Algorithms: Summary and RecommendationsJournal of the American College of Radiology, 2021
- Explainable skin lesion diagnosis using taxonomiesPattern Recognition, 2021
- Explainable classifier for improving the accountability in decision-making for colorectal cancer diagnosis from histopathological imagesJournal of Biomedical Informatics, 2020
- Automated acquisition of explainable knowledge from unannotated histopathology imagesNature Communications, 2019
- Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification taskEuropean Journal of Cancer, 2019
- Unmasking Clever Hans predictors and assessing what machines really learnNature Communications, 2019
- Methods for interpreting and understanding deep neural networksDigital Signal Processing, 2018
- Medical image retrieval using deep convolutional neural networkNeurocomputing, 2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- A Deep Learning Architecture for Image Representation, Visual Interpretability and Automated Basal-Cell Carcinoma Cancer Detection2013