Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization

TL;DR

This paper introduces a dual-normalization approach with style augmentation to improve the generalization of medical image segmentation models across different imaging modalities, such as MRI and CT.

Contribution

It proposes a novel dual-normalization model with style-based selection for cross-modality segmentation, enhancing generalization without target domain training.

Findings

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

Effective in simulating appearance changes in unseen target domains

Utilizes style augmentation and dual-normalization for robust segmentation

Abstract

For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain? This setting, namely generalizable cross-modality segmentation, owning its clinical potential, is much more challenging than other related settings, e.g., domain adaptation. To achieve this goal, we in this paper propose a novel dual-normalization model by leveraging the augmented source-similar and source-dissimilar images during our generalizable segmentation. To be specific, given a single source domain, aiming to simulate the possible appearance change in unseen target domains, we first utilize a nonlinear transformation to augment source-similar and source-dissimilar images. Then, to sufficiently exploit these two types of augmentations, our proposed dual-normalization based model employs a shared backbone yet independent batch normalization layer for separate normalization. Afterward, we put forward a style-based selection scheme to automatically choose the appropriate path in the test stage. Extensive experiments on three publicly available datasets, i.e., BraTS, Cross-Modality Cardiac, and Abdominal Multi-Organ datasets, have demonstrated that our method outperforms other state-of-the-art domain generalization methods. Code is available at https://github.com/zzzqzhou/Dual-Normalization.