Efficient subtyping of ovarian cancer histopathology whole slide images using active sampling in multiple instance learning

TL;DR

This paper introduces DRAS-MIL, a novel active sampling method for efficient and accurate classification of ovarian cancer subtypes in histopathology slides, significantly reducing computational resources needed.

Contribution

The paper presents DRAS-MIL, an active sampling approach that focuses on discriminative regions, enabling faster and more memory-efficient slide classification without sacrificing accuracy.

Findings

Achieves similar accuracy to exhaustive analysis with less memory

Reduces GPU evaluation time to 33% and CPU time to 14%

Uses at most 18% of the memory compared to standard methods

Abstract

Weakly-supervised classification of histopathology slides is a computationally intensive task, with a typical whole slide image (WSI) containing billions of pixels to process. We propose Discriminative Region Active Sampling for Multiple Instance Learning (DRAS-MIL), a computationally efficient slide classification method using attention scores to focus sampling on highly discriminative regions. We apply this to the diagnosis of ovarian cancer histological subtypes, which is an essential part of the patient care pathway as different subtypes have different genetic and molecular profiles, treatment options, and patient outcomes. We use a dataset of 714 WSIs acquired from 147 epithelial ovarian cancer patients at Leeds Teaching Hospitals NHS Trust to distinguish the most common subtype, high-grade serous carcinoma, from the other four subtypes (low-grade serous, endometrioid, clear cell, and mucinous carcinomas) combined. We demonstrate that DRAS-MIL can achieve similar classification performance to exhaustive slide analysis, with a 3-fold cross-validated AUC of 0.8679 compared to 0.8781 with standard attention-based MIL classification. Our approach uses at most 18% as much memory as the standard approach, while taking 33% of the time when evaluating on a GPU and only 14% on a CPU alone. Reducing prediction time and memory requirements may benefit clinical deployment and the democratisation of AI, reducing the extent to which computational hardware limits end-user adoption.