Immune subtyping of melanoma whole slide images using multiple instance learning

Godson, L., Alemi, N., Nsengimana, J., Cook, G. P., Clarke, E. L., Treanor, D., Bishop, D. T., Newton-Bishop, J., Gooya, A. and Magee, D. (2024) Immune subtyping of melanoma whole slide images using multiple instance learning. Medical Image Analysis, 93, 103097. (doi: 10.1016/j.media.2024.103097) (PMID:38325154)

Abstract

Determining early-stage prognostic markers and stratifying patients for effective treatment are two key challenges for improving outcomes for melanoma patients. Previous studies have used tumour transcriptome data to stratify patients into immune subgroups, which were associated with differential melanoma specific survival and potential predictive biomarkers. However, acquiring transcriptome data is a time-consuming and costly process. Moreover, it is not routinely used in the current clinical workflow. Here, we attempt to overcome this by developing deep learning models to classify gigapixel haematoxylin and eosin (H and E) stained pathology slides, which are well established in clinical workflows, into these immune subgroups. We systematically assess six different multiple instance learning (MIL) frameworks, using five different image resolutions and three different feature extraction methods. We show that pathology-specific self-supervised models using 10x resolution patches generate superior representations for the classification of immune subtypes. In addition, in a primary melanoma dataset, we achieve a mean area under the receiver operating characteristic curve (AUC) of 0.80 for classifying histopathology images into ‘high’ or ‘low immune’ subgroups and a mean AUC of 0.82 in an independent TCGA melanoma dataset. Furthermore, we show that these models are able to stratify patients into ‘high’ and ‘low immune’ subgroups with significantly different melanoma specific survival outcomes (log rank test, P<0.005). We anticipate that MIL methods will allow us to find new biomarkers of high importance, act as a tool for clinicians to infer the immune landscape of tumours and stratify patients, without needing to carry out additional expensive genetic tests.

• Item Type: Articles
• Additional Information: This work was supported by the Engineering and Physical Sciences Research Council (EPSRC), United Kingdom [EP/S024336/1]; Cancer Research UK [C588/A19167, C8216/A6129, and C588/A10721 and NIH CA83115]; and the Medical Research Council, United Kingdom [MR/S001530/1].
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Gooya, Dr Ali

Creator Roles

Gooya, A.: Conceptualization, Supervision

• Authors: Godson, L., Alemi, N., Nsengimana, J., Cook, G. P., Clarke, E. L., Treanor, D., Bishop, D. T., Newton-Bishop, J., Gooya, A., and Magee, D.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: Medical Image Analysis
• Publisher: Elsevier
• ISSN: 1361-8415
• Published Online: 01 February 2024
• Copyright Holders: Copyright © 2024 The Authors
• First Published: First published in Medical Image Analysis 93:103097
• Publisher Policy: Reproduced under a Creative Commons licence