Sequential Attention-based Sampling for Histopathological Analysis

TL;DR

SASHA is a deep reinforcement learning method that efficiently analyzes gigapixel histopathological images by selectively sampling high-resolution patches, achieving accurate diagnoses with reduced computational costs.

Contribution

Introduces SASHA, a novel attention-based reinforcement learning approach for selective sampling in histopathology, reducing computational load while maintaining high diagnostic accuracy.

Findings

SASHA matches state-of-the-art full-resolution analysis performance.

SASHA significantly outperforms other sparse sampling methods.

Reduces computational and memory costs by analyzing only 10-20% of patches.

Abstract

Deep neural networks are increasingly applied in automated histopathology. Yet, whole-slide images (WSIs) are often acquired at gigapixel sizes, rendering them computationally infeasible to analyze entirely at high resolution. Diagnostic labels are largely available only at the slide-level, because expert annotation of images at a finer (patch) level is both laborious and expensive. Moreover, regions with diagnostic information typically occupy only a small fraction of the WSI, making it inefficient to examine the entire slide at full resolution. Here, we propose SASHA -- Sequential Attention-based Sampling for Histopathological Analysis -- a deep reinforcement learning approach for efficient analysis of histopathological images. First, SASHA learns informative features with a lightweight hierarchical, attention-based multiple instance learning (MIL) model. Second, SASHA samples intelligently and zooms selectively into a small fraction (10-20\%) of high-resolution patches to achieve reliable diagnoses. We show that SASHA matches state-of-the-art methods that analyze the WSI fully at high resolution, albeit at a fraction of their computational and memory costs. In addition, it significantly outperforms competing, sparse sampling methods. We propose SASHA as an intelligent sampling model for medical imaging challenges that involve automated diagnosis with exceptionally large images containing sparsely informative features. Model implementation is available at: https://github.com/coglabiisc/SASHA.