Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation

by   Zixian Su, et al.

Single-source domain generalization (SDG) in medical image segmentation is a challenging yet essential task as domain shifts are quite common among clinical image datasets. Previous attempts most conduct global-only/random augmentation. Their augmented samples are usually insufficient in diversity and informativeness, thus failing to cover the possible target domain distribution. In this paper, we rethink the data augmentation strategy for SDG in medical image segmentation. Motivated by the class-level representation invariance and style mutability of medical images, we hypothesize that unseen target data can be sampled from a linear combination of C (the class number) random variables, where each variable follows a location-scale distribution at the class level. Accordingly, data augmented can be readily made by sampling the random variables through a general form. On the empirical front, we implement such strategy with constrained Bézier transformation on both global and local (i.e. class-level) regions, which can largely increase the augmentation diversity. A Saliency-balancing Fusion mechanism is further proposed to enrich the informativeness by engaging the gradient information, guiding augmentation with proper orientation and magnitude. As an important contribution, we prove theoretically that our proposed augmentation can lead to an upper bound of the generalization risk on the unseen target domain, thus confirming our hypothesis. Combining the two strategies, our Saliency-balancing Location-scale Augmentation (SLAug) exceeds the state-of-the-art works by a large margin in two challenging SDG tasks. Code is available at .


page 1

page 3

page 4

page 6

page 7

page 11


Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation

Deep learning-based medical image segmentation models suffer from perfor...

Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation

Although recent years have witnessed the great success of convolutional ...

AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation

Convolutional neural networks have been widely applied to medical image ...

MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization

Accurate segmentation of clustered microcalcifications in mammography is...

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

For medical image segmentation, imagine if a model was only trained usin...

Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation

The domain gap caused mainly by variable medical image quality renders a...

TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation

Deep learning models are notoriously data-hungry. Thus, there is an urgi...

Please sign up or login with your details

Forgot password? Click here to reset