Nuclei Grading of Clear Cell Renal Cell Carcinoma in Histopathological Image by Composite High-Resolution Network

TL;DR

This paper introduces a novel composite high-resolution network for automatic nuclei grading in clear cell renal cell carcinoma, improving segmentation and classification accuracy in histopathological images.

Contribution

The paper proposes a new network architecture combining segmentation and classification with shared features, specifically designed for ccRCC nuclei grading, and introduces a new annotated dataset.

Findings

Achieved state-of-the-art performance on ccRCC nuclei grading dataset.

Effectively separates clustered nuclei for accurate grading.

Demonstrates the benefit of shared features in segmentation and classification tasks.

Abstract

The grade of clear cell renal cell carcinoma (ccRCC) is a critical prognostic factor, making ccRCC nuclei grading a crucial task in RCC pathology analysis. Computer-aided nuclei grading aims to improve pathologists' work efficiency while reducing their misdiagnosis rate by automatically identifying the grades of tumor nuclei within histopathological images. Such a task requires precisely segment and accurately classify the nuclei. However, most of the existing nuclei segmentation and classification methods can not handle the inter-class similarity property of nuclei grading, thus can not be directly applied to the ccRCC grading task. In this paper, we propose a Composite High-Resolution Network for ccRCC nuclei grading. Specifically, we propose a segmentation network called W-Net that can separate the clustered nuclei. Then, we recast the fine-grained classification of nuclei to two cross-category classification tasks, based on two high-resolution feature extractors (HRFEs) which are proposed for learning these two tasks. The two HRFEs share the same backbone encoder with W-Net by a composite connection so that meaningful features for the segmentation task can be inherited for the classification task. Last, a head-fusion block is applied to generate the predicted label of each nucleus. Furthermore, we introduce a dataset for ccRCC nuclei grading, containing 1000 image patches with 70945 annotated nuclei. We demonstrate that our proposed method achieves state-of-the-art performance compared to existing methods on this large ccRCC grading dataset.