Bridging the Gap in Missing Modalities: Leveraging Knowledge Distillation and Style Matching for Brain Tumor Segmentation

TL;DR

This paper introduces MST-KDNet, a novel model that combines multi-scale transformer knowledge distillation, dual-mode logit distillation, and global style matching to improve brain tumor segmentation accuracy, especially with missing modalities.

Contribution

It proposes a new framework integrating multiple distillation and style matching techniques to enhance segmentation robustness in the absence of certain imaging modalities.

Findings

Outperforms existing methods on BraTS and FeTS 2024 datasets.

Achieves higher Dice and HD95 scores with modality loss.

Demonstrates strong robustness and generalization in clinical scenarios.

Abstract

Accurate and reliable brain tumor segmentation, particularly when dealing with missing modalities, remains a critical challenge in medical image analysis. Previous studies have not fully resolved the challenges of tumor boundary segmentation insensitivity and feature transfer in the absence of key imaging modalities. In this study, we introduce MST-KDNet, aimed at addressing these critical issues. Our model features Multi-Scale Transformer Knowledge Distillation to effectively capture attention weights at various resolutions, Dual-Mode Logit Distillation to improve the transfer of knowledge, and a Global Style Matching Module that integrates feature matching with adversarial learning. Comprehensive experiments conducted on the BraTS and FeTS 2024 datasets demonstrate that MST-KDNet surpasses current leading methods in both Dice and HD95 scores, particularly in conditions with substantial modality loss. Our approach shows exceptional robustness and generalization potential, making it a promising candidate for real-world clinical applications. Our source code is available at https://github.com/Quanato607/MST-KDNet.