Geometric Loss for Deep Multiple Sclerosis lesion Segmentation

TL;DR

This paper introduces a novel geometric loss function for deep learning-based MS lesion segmentation, effectively addressing data imbalance and leveraging lesion geometry to improve segmentation accuracy across diverse datasets.

Contribution

The authors propose a new geometric loss formula that incorporates first- and second-order lesion geometry, enhancing deep segmentation models for MS lesions.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively handles data imbalance and lesion heterogeneity

Improves segmentation accuracy using geometric regularization

Abstract

Multiple sclerosis (MS) lesions occupy a small fraction of the brain volume, and are heterogeneous with regards to shape, size and locations, which poses a great challenge for training deep learning based segmentation models. We proposed a new geometric loss formula to address the data imbalance and exploit the geometric property of MS lesions. We showed that traditional region-based and boundary-aware loss functions can be associated with the formula. We further develop and instantiate two loss functions containing first- and second-order geometric information of lesion regions to enforce regularization on optimizing deep segmentation models. Experimental results on two MS lesion datasets with different scales, acquisition protocols and resolutions demonstrated the superiority of our proposed methods compared to other state-of-the-art methods.