Diverse data augmentation for learning image segmentation with cross-modality annotations

The dearth of annotated data is a major hurdle in building reliable image segmentation models. Man-ual annotation of medical images is tedious, time-consuming, and significantly variable across imaging modalities. The need for annotation can be ameliorated by leveraging an annotation-rich source modality in learning a segmentation model for an annotation-poor target modality. In this paper, we introduce a diverse data augmentation generative adversarial network (DDA-GAN) to train a segmentation model for an unannotated target image domain by borrowing information from an annotated source image domain. This is achieved by generating diverse augmented data for the target domain by one-to-many source-to-target translation. The DDA-GAN uses unpaired images from the source and target domains and is an end-to-end convolutional neural network that (i) explicitly disentangles domain-invariant structural fea-tures related to segmentation from domain-specific appearance features, (ii) combines structural features from the source domain with appearance features randomly sampled from the target domain for data augmentation, and (iii) train the segmentation model with the augmented data in the target domain and the annotations from the source domain. The effectiveness of our method is demonstrated both qualita-tively and quantitatively in comparison with the state of the art for segmentation of craniomaxillofacial bony structures via MRI and cardiac substructures via CT.(c) 2021 Elsevier B.V. All rights reserved.

Automated summary

The lack of annotated data is a major challenge in building reliable image segmentation models. In this paper, a diverse data augmentation generative adversarial network (DDA-GAN) is introduced to train a segmentation model for an unannotated target image domain by borrowing information from an annotated source image domain. The method effectively combines features from different domains to improve segmentation quality through data augmentation and model training.