A Multi-resolution Model for Histopathology Image Classification and Localization with Multiple Instance Learning

TL;DR

This paper introduces a multi-resolution multiple instance learning model that accurately classifies and localizes prostate cancer in whole slide histopathology images using only slide-level labels, reducing annotation costs.

Contribution

The novel multi-resolution MIL model leverages saliency maps for fine-grained prediction without requiring detailed annotations, trained on a large-scale prostate biopsy dataset.

Findings

Achieved 92.7% accuracy in grade prediction

Reached 98.2% AUROC for malignancy detection

Obtained 99.4% AUROC for cancer detection on external data

Abstract

Histopathological images provide rich information for disease diagnosis. Large numbers of histopathological images have been digitized into high resolution whole slide images, opening opportunities in developing computational image analysis tools to reduce pathologists' workload and potentially improve inter- and intra- observer agreement. Most previous work on whole slide image analysis has focused on classification or segmentation of small pre-selected regions-of-interest, which requires fine-grained annotation and is non-trivial to extend for large-scale whole slide analysis. In this paper, we proposed a multi-resolution multiple instance learning model that leverages saliency maps to detect suspicious regions for fine-grained grade prediction. Instead of relying on expensive region- or pixel-level annotations, our model can be trained end-to-end with only slide-level labels. The model is developed on a large-scale prostate biopsy dataset containing 20,229 slides from 830 patients. The model achieved 92.7% accuracy, 81.8% Cohen's Kappa for benign, low grade (i.e. Grade group 1) and high grade (i.e. Grade group >= 2) prediction, an area under the receiver operating characteristic curve (AUROC) of 98.2% and an average precision (AP) of 97.4% for differentiating malignant and benign slides. The model obtained an AUROC of 99.4% and an AP of 99.8% for cancer detection on an external dataset.