Hierarchical Classification for Improved Histopathology Image Analysis

TL;DR

This paper introduces HiClass, a hierarchical classification framework for histopathology images that leverages bidirectional feature integration and specialized loss functions to improve both coarse- and fine-grained whole-slide image classification.

Contribution

It presents a novel hierarchical classification method that enhances deep learning for histopathology by integrating features bidirectionally and optimizing with tailored loss functions.

Findings

Achieved superior classification accuracy on gastric biopsy dataset.

Effectively captures hierarchical features for better WSI analysis.

Improves both coarse- and fine-grained classification performance.

Abstract

Whole-slide image analysis is essential for diagnostic tasks in pathology, yet existing deep learning methods primarily rely on flat classification, ignoring hierarchical relationships among class labels. In this study, we propose HiClass, a hierarchical classification framework for improved histopathology image analysis, that enhances both coarse-grained and fine-grained WSI classification. Built based upon a multiple instance learning approach, HiClass extends it by introducing bidirectional feature integration that facilitates information exchange between coarse-grained and fine-grained feature representations, effectively learning hierarchical features. Moreover, we introduce tailored loss functions, including hierarchical consistency loss, intra- and inter-class distance loss, and group-wise cross-entropy loss, to further optimize hierarchical learning. We assess the performance of HiClass on a gastric biopsy dataset with 4 coarse-grained and 14 fine-grained classes, achieving superior classification performance for both coarse-grained classification and fine-grained classification. These results demonstrate the effectiveness of HiClass in improving WSI classification by capturing coarse-grained and fine-grained histopathological characteristics.