Weakly supervised learning and interpretability for endometrial whole slide image diagnosis
| Autor: | Mahnaz Mohammadi, Jessica Cooper, Ognjen Arandelović, Christina Fell, David Morrison, Sheeba Syed, Prakash Konanahalli, Sarah Bell, Gareth Bryson, David J Harrison, David Harris-Birtill |
|---|---|
| Přispěvatelé: | Innovate UK, University of St Andrews. School of Computer Science, University of St Andrews. Sir James Mackenzie Institute for Early Diagnosis, University of St Andrews. Cellular Medicine Division, University of St Andrews. School of Medicine |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
MCC
QA75 Hyperplasia RC0254 Neoplasms. Tumors. Oncology (including Cancer) QA75 Electronic computers. Computer science 3rd-DAS Weak supervision Adenocarcinoma Cancer detection General Biochemistry Genetics and Molecular Biology iCAIRD RC0254 Endometrial cancer XAI SDG 3 - Good Health and Well-being RB Pathology Digital pathology Interpretability RB |
| Popis: | Funding: This work is supported by the Industrial Centre for AI Research in digital Diagnostics (iCAIRD) which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) [project number: 104690], and in part by Chief Scientist Office, Scotland. Fully supervised learning for whole slide image based diagnostic tasks in histopathology is problematic due to the requirement for costly and time-consuming manual annotation by experts. Weakly supervised learning which utilises only slide-level labels during training is becoming more widespread as it relieves this burden, but has not yet been applied to endometrial whole slide images, in iSyntax format. In this work we apply a weakly supervised learning algorithm to a real-world dataset of this type for the first time, with over 85% validation accuracy and over 87% test accuracy. We then employ interpretability methods including attention heatmapping, feature visualisation, and a novel end-to-end saliency-mapping approach to identify distinct morphologies learned by the model and build an understanding of its behaviour. These interpretability methods, alongside consultation with expert pathologists, allow us to make comparisons between machine-learned knowledge and consensus in the field. This work contributes to the state of the art by demonstrating a robust practical application of weakly supervised learning on a real-world digital pathology dataset and shows the importance of fine-grained interpretability to support understanding and evaluation of model performance in this high-stakes use case. Publisher PDF |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|