Detection and Classification of Breast Cancer Metastates Based on U-Net

TL;DR

This paper introduces a U-Net based method for detecting and classifying breast cancer metastases in lymph nodes, achieving high accuracy and enabling patient-level diagnosis through a multi-step pipeline.

Contribution

The study develops a comprehensive pipeline integrating preprocessing, segmentation, and classification with enhancements like batch normalization and dropout for improved performance.

Findings

Kappa score of 0.902 on training data

Effective metastases detection and classification

Pipeline enables patient-level diagnosis

Abstract

This paper presents U-net based breast cancer metastases detection and classification in lymph nodes, as well as patient-level classification based on metastases detection. The whole pipeline can be divided into five steps: preprocessing and data argumentation, patch-based segmentation, post processing, slide-level classification, and patient-level classification. In order to reduce overfitting and speedup convergence, we applied batch normalization and dropout into U-Net. The final Kappa score reaches 0.902 on training data.