A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma

TL;DR

This paper introduces HiTrans, a hierarchical Transformer encoder that enhances entire neoplasm segmentation on large Whole Slide Images of Hepatocellular Carcinoma by capturing global dependencies, outperforming traditional CNN-based methods.

Contribution

The paper presents a novel hierarchical Transformer architecture, HiTrans, specifically designed for large-scale histopathological image segmentation, improving dependency learning over existing CNN approaches.

Findings

HiTrans achieves superior segmentation accuracy on HCC WSIs.

Global dependency modeling improves segmentation performance.

Hierarchical Transformer effectively handles large image patches.

Abstract

In digital histopathology, entire neoplasm segmentation on Whole Slide Image (WSI) of Hepatocellular Carcinoma (HCC) plays an important role, especially as a preprocessing filter to automatically exclude healthy tissue, in histological molecular correlations mining and other downstream histopathological tasks. The segmentation task remains challenging due to HCC's inherent high-heterogeneity and the lack of dependency learning in large field of view. In this article, we propose a novel deep learning architecture with a hierarchical Transformer encoder, HiTrans, to learn the global dependencies within expanded 4096$\times$4096 WSI patches. HiTrans is designed to encode and decode the patches with larger reception fields and the learned global dependencies, compared to the state-of-the-art Fully Convolutional Neural networks (FCNN). Empirical evaluations verified that HiTrans leads to better segmentation performance by taking into account regional and global dependency information.