Towards Modality-Agnostic Continual Domain-Incremental Brain Lesion Segmentation

TL;DR

This paper introduces CLMU-Net, a replay-based continual learning framework for brain lesion segmentation that effectively handles arbitrary multi-modal MRI data without prior modality knowledge, significantly improving segmentation accuracy across diverse datasets.

Contribution

The paper presents CLMU-Net, a novel continual learning model that supports flexible modality combinations and reduces forgetting through a unified multi-channel approach and targeted replay strategies.

Findings

Outperforms popular CL baselines on five MRI datasets.

Achieves ≥18% improvement in Dice scores across heterogeneous modalities.

Demonstrates robustness under diverse modality conditions.

Abstract

Brain lesion segmentation from multi-modal MRI often assumes fixed modality sets or predefined pathologies, making existing models difficult to adapt across cohorts and imaging protocols. Continual learning (CL) offers a natural solution but current approaches either impose a maximum modality configuration or suffer from severe forgetting in buffer-free settings. We introduce CLMU-Net, a replay-based CL framework for 3D brain lesion segmentation that supports arbitrary and variable modality combinations without requiring prior knowledge of the maximum set. A conceptually simple yet effective channel-inflation strategy maps any modality subset into a unified multi-channel representation, enabling a single model to operate across diverse datasets. To enrich inherently local 3D patch features, we incorporate lightweight domain-conditioned textual embeddings that provide global modality-disease context for each training case. Forgetting is further reduced through principled replay using a compact buffer composed of both prototypical and challenging samples. Experiments on five heterogeneous MRI brain datasets demonstrate that CLMU-Net consistently outperforms popular CL baselines. Notably, our method yields an average Dice score improvement of $\geq$ 18\% while remaining robust under heterogeneous-modality conditions. These findings underscore the value of flexible modality handling, targeted replay, and global contextual cues for continual medical image segmentation. Our implementation is available at https://github.com/xmindflow/CLMU-Net.