Classifying Breast Histopathology Images with a Ductal Instance-Oriented Pipeline

TL;DR

This paper introduces DIOP, a pipeline combining ductal and tissue segmentation with multi-level features, achieving high accuracy in classifying breast histopathology images efficiently, comparable to pathologists.

Contribution

The study presents a novel ductal instance-oriented pipeline that integrates segmentation and multi-level features for improved diagnostic classification in breast histopathology images.

Findings

DIOP outperforms previous feature-based and CNN-based methods in all diagnostic tasks.

Achieves four-way classification accuracy comparable to pathologists.

Runs in a few seconds, enabling interactive use.

Abstract

In this study, we propose the Ductal Instance-Oriented Pipeline (DIOP) that contains a duct-level instance segmentation model, a tissue-level semantic segmentation model, and three-levels of features for diagnostic classification. Based on recent advancements in instance segmentation and the Mask R-CNN model, our duct-level segmenter tries to identify each ductal individual inside a microscopic image; then, it extracts tissue-level information from the identified ductal instances. Leveraging three levels of information obtained from these ductal instances and also the histopathology image, the proposed DIOP outperforms previous approaches (both feature-based and CNN-based) in all diagnostic tasks; for the four-way classification task, the DIOP achieves comparable performance to general pathologists in this unique dataset. The proposed DIOP only takes a few seconds to run in the inference time, which could be used interactively on most modern computers. More clinical explorations are needed to study the robustness and generalizability of this system in the future.