Optimizing Operating Points for High Performance Lesion Detection and Segmentation Using Lesion Size Reweighting

TL;DR

This paper introduces a novel lesion size reweighting method that improves detection and segmentation of both small and large lesions in medical images, addressing the limitations of standard loss functions.

Contribution

A new reweighing strategy that enhances small lesion detection without compromising large lesion segmentation accuracy.

Findings

Outperforms existing strategies on a large multi-center dataset

Significantly improves small lesion detection rates

Maintains high segmentation accuracy for large lesions

Abstract

There are many clinical contexts which require accurate detection and segmentation of all focal pathologies (e.g. lesions, tumours) in patient images. In cases where there are a mix of small and large lesions, standard binary cross entropy loss will result in better segmentation of large lesions at the expense of missing small ones. Adjusting the operating point to accurately detect all lesions generally leads to oversegmentation of large lesions. In this work, we propose a novel reweighing strategy to eliminate this performance gap, increasing small pathology detection performance while maintaining segmentation accuracy. We show that our reweighing strategy vastly outperforms competing strategies based on experiments on a large scale, multi-scanner, multi-center dataset of Multiple Sclerosis patient images.