Feature Re-calibration based Multiple Instance Learning for Whole Slide Image Classification

TL;DR

This paper introduces a novel feature re-calibration method for multiple instance learning in whole slide image classification, leveraging distribution statistics, balanced-batch sampling, and Transformer-based spatial encoding to improve accuracy.

Contribution

It proposes a new MIL framework that re-calibrates instance distributions using max-instance statistics, employs balanced-batch sampling, and integrates a Transformer-based spatial encoding module.

Findings

Outperforms existing MIL methods on benchmark datasets.

Effective in modeling spatial and morphological information.

Improves classification accuracy in whole slide image analysis.

Abstract

Whole slide image (WSI) classification is a fundamental task for the diagnosis and treatment of diseases; but, curation of accurate labels is time-consuming and limits the application of fully-supervised methods. To address this, multiple instance learning (MIL) is a popular method that poses classification as a weakly supervised learning task with slide-level labels only. While current MIL methods apply variants of the attention mechanism to re-weight instance features with stronger models, scant attention is paid to the properties of the data distribution. In this work, we propose to re-calibrate the distribution of a WSI bag (instances) by using the statistics of the max-instance (critical) feature. We assume that in binary MIL, positive bags have larger feature magnitudes than negatives, thus we can enforce the model to maximize the discrepancy between bags with a metric feature loss that models positive bags as out-of-distribution. To achieve this, unlike existing MIL methods that use single-batch training modes, we propose balanced-batch sampling to effectively use the feature loss i.e., (+/-) bags simultaneously. Further, we employ a position encoding module (PEM) to model spatial/morphological information, and perform pooling by multi-head self-attention (PSMA) with a Transformer encoder. Experimental results on existing benchmark datasets show our approach is effective and improves over state-of-the-art MIL methods.