BEDS: Bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation

TL;DR

This paper introduces BEDS, a novel ensemble deep learning method that combines bagging, self-ensemble learning, and testing stage stain augmentation to improve nucleus segmentation in pathological images.

Contribution

It proposes a self-ensemble framework for nucleus segmentation, integrating testing stage stain augmentation, and demonstrates their complementary benefits.

Findings

Enhanced segmentation accuracy with ensemble methods

Testing stage stain augmentation improves robustness

Self-ensemble learning reduces outcome variance

Abstract

Reducing outcome variance is an essential task in deep learning based medical image analysis. Bootstrap aggregating, also known as bagging, is a canonical ensemble algorithm for aggregating weak learners to become a strong learner. Random forest is one of the most powerful machine learning algorithms before deep learning era, whose superior performance is driven by fitting bagged decision trees (weak learners). Inspired by the random forest technique, we propose a simple bagging ensemble deep segmentation (BEDs) method to train multiple U-Nets with partial training data to segment dense nuclei on pathological images. The contributions of this study are three-fold: (1) developing a self-ensemble learning framework for nucleus segmentation; (2) aggregating testing stage augmentation with self-ensemble learning; and (3) elucidating the idea that self-ensemble and testing stage stain augmentation are complementary strategies for a superior segmentation performance. Implementation Detail: https://github.com/xingli1102/BEDs.