Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention

TL;DR

This paper introduces MADGNet, a novel medical image segmentation model that enhances domain generalization by incorporating multi-frequency multi-scale attention and an ensemble sub-decoding module, improving performance across diverse modalities.

Contribution

The paper proposes MADGNet with innovative MFMSA and E-SDM components to address frequency variance and information loss, advancing modality-agnostic and domain-generalizable segmentation.

Findings

Outperforms state-of-the-art models across six modalities.

Achieves superior segmentation accuracy on fifteen datasets.

Demonstrates robustness in diverse imaging scenarios.

Abstract

Generalizability in deep neural networks plays a pivotal role in medical image segmentation. However, deep learning-based medical image analyses tend to overlook the importance of frequency variance, which is critical element for achieving a model that is both modality-agnostic and domain-generalizable. Additionally, various models fail to account for the potential information loss that can arise from multi-task learning under deep supervision, a factor that can impair the model representation ability. To address these challenges, we propose a Modality-agnostic Domain Generalizable Network (MADGNet) for medical image segmentation, which comprises two key components: a Multi-Frequency in Multi-Scale Attention (MFMSA) block and Ensemble Sub-Decoding Module (E-SDM). The MFMSA block refines the process of spatial feature extraction, particularly in capturing boundary features, by incorporating multi-frequency and multi-scale features, thereby offering informative cues for tissue outline and anatomical structures. Moreover, we propose E-SDM to mitigate information loss in multi-task learning with deep supervision, especially during substantial upsampling from low resolution. We evaluate the segmentation performance of MADGNet across six modalities and fifteen datasets. Through extensive experiments, we demonstrate that MADGNet consistently outperforms state-of-the-art models across various modalities, showcasing superior segmentation performance. This affirms MADGNet as a robust solution for medical image segmentation that excels in diverse imaging scenarios. Our MADGNet code is available in GitHub Link.