Robust Divergence Learning for Missing-Modality Segmentation

TL;DR

This paper introduces a robust segmentation method for brain MRI that effectively handles missing modalities by using a novel parallel processing network with divergence and mutual information-based loss functions.

Contribution

It proposes a single-modality parallel processing framework with dynamic sharing and specialized loss functions to improve missing-modality segmentation in brain MRI.

Findings

Outperforms existing methods on BraTS datasets.

Effectively handles missing modalities.

Validates each component's contribution.

Abstract

Multimodal Magnetic Resonance Imaging (MRI) provides essential complementary information for analyzing brain tumor subregions. While methods using four common MRI modalities for automatic segmentation have shown success, they often face challenges with missing modalities due to image quality issues, inconsistent protocols, allergic reactions, or cost factors. Thus, developing a segmentation paradigm that handles missing modalities is clinically valuable. A novel single-modality parallel processing network framework based on H\"older divergence and mutual information is introduced. Each modality is independently input into a shared network backbone for parallel processing, preserving unique information. Additionally, a dynamic sharing framework is introduced that adjusts network parameters based on modality availability. A H\"older divergence and mutual information-based loss functions are used for evaluating discrepancies between predictions and labels. Extensive testing on the BraTS 2018 and BraTS 2020 datasets demonstrates that our method outperforms existing techniques in handling missing modalities and validates each component's effectiveness.