Automated Scoring of Nuclear Pleomorphism Spectrum with Pathologist-level Performance in Breast Cancer

TL;DR

This study develops a deep learning model that accurately scores nuclear pleomorphism in breast cancer, achieving performance comparable to expert pathologists without relying on traditional categorical grading.

Contribution

The paper introduces a neural network trained on diverse tumor regions that captures the continuous spectrum of nuclear abnormalities, surpassing traditional classification methods.

Findings

Achieved pathologist-level accuracy in scoring nuclear pleomorphism.

Performed well on both selected regions and entire slide images.

Utilized normal epithelium as a baseline for improved assessment.

Abstract

Nuclear pleomorphism, defined herein as the extent of abnormalities in the overall appearance of tumor nuclei, is one of the components of the three-tiered breast cancer grading. Given that nuclear pleomorphism reflects a continuous spectrum of variation, we trained a deep neural network on a large variety of tumor regions from the collective knowledge of several pathologists, without constraining the network to the traditional three-category classification. We also motivate an additional approach in which we discuss the additional benefit of normal epithelium as baseline, following the routine clinical practice where pathologists are trained to score nuclear pleomorphism in tumor, having the normal breast epithelium for comparison. In multiple experiments, our fully-automated approach could achieve top pathologist-level performance in select regions of interest as well as at whole slide images, compared to ten and four pathologists, respectively.