Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation
This work addresses data scarcity in medical image segmentation, offering a transferable augmentation method that is incremental over prior object-centric approaches.
The paper tackles the challenge of limited labeled data in medical image segmentation by proposing an object-centric data augmentation model that learns shape variations of objects of interest, demonstrating effectiveness in improving kidney tumour segmentation with gains from both same-dataset and transferred external data.
Obtaining labelled data in medical image segmentation is challenging due to the need for pixel-level annotations by experts. Recent works have shown that augmenting the object of interest with deformable transformations can help mitigate this challenge. However, these transformations have been learned globally for the image, limiting their transferability across datasets or applicability in problems where image alignment is difficult. While object-centric augmentations provide a great opportunity to overcome these issues, existing works are only focused on position and random transformations without considering shape variations of the objects. To this end, we propose a novel object-centric data augmentation model that is able to learn the shape variations for the objects of interest and augment the object in place without modifying the rest of the image. We demonstrated its effectiveness in improving kidney tumour segmentation when leveraging shape variations learned both from within the same dataset and transferred from external datasets.