AnatoMix: Anatomy-aware Data Augmentation for Multi-organ Segmentation
This work addresses the need for improved generalizability in multi-organ segmentation for clinicians, though it appears incremental as it builds on existing data augmentation methods.
The paper tackles the problem of multi-organ segmentation in medical images by proposing AnatoMix, a novel data augmentation strategy that generates new images with correct anatomy to increase dataset size, resulting in a mean dice score of 76.1 compared to 74.8 for the baseline.
Multi-organ segmentation in medical images is a widely researched task and can save much manual efforts of clinicians in daily routines. Automating the organ segmentation process using deep learning (DL) is a promising solution and state-of-the-art segmentation models are achieving promising accuracy. In this work, We proposed a novel data augmentation strategy for increasing the generalizibility of multi-organ segmentation datasets, namely AnatoMix. By object-level matching and manipulation, our method is able to generate new images with correct anatomy, i.e. organ segmentation mask, exponentially increasing the size of the segmentation dataset. Initial experiments have been done to investigate the segmentation performance influenced by our method on a public CT dataset. Our augmentation method can lead to mean dice of 76.1, compared with 74.8 of the baseline method.