Hierarchical Classification for Improved Histopathology Image Analysis

2026-02-28

AI Summary

This work addresses the limitation of existing whole-slide image analysis methods in digital pathology, which typically adopt flat classification schemes and overlook the inherent hierarchical structure among diagnostic categories, thereby hindering the joint optimization of coarse- and fine-grained tasks. To this end, the authors propose HiClass, a novel framework based on multiple instance learning that incorporates a bidirectional feature fusion mechanism to facilitate interaction between coarse- and fine-grained features. Furthermore, HiClass explicitly models hierarchical semantic relationships through a multi-level loss function comprising hierarchical consistency loss, intra- and inter-class distance losses, and grouped cross-entropy loss. Evaluated on a gastric biopsy dataset encompassing four coarse-grained and fourteen fine-grained classes, HiClass significantly outperforms current approaches on both classification tasks, demonstrating its effectiveness and superiority in hierarchical pathological image classification.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Segmentation
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

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.

Problem

• hierarchical classification
• histopathology image analysis
• whole-slide image
• flat classification
• class label hierarchy

Innovation

• hierarchical classification
• bidirectional feature integration
• multiple instance learning
• hierarchical loss functions
• whole-slide image analysis