AnatoMix: Anatomy-aware Data Augmentation for Multi-organ Segmentation

TL;DR

AnatoMix is a novel anatomy-aware data augmentation technique that enhances multi-organ segmentation accuracy in medical images by generating anatomically correct augmented data, thereby improving model generalizability.

Contribution

The paper introduces AnatoMix, a new object-level matching and manipulation augmentation method that increases dataset diversity with anatomically accurate images for multi-organ segmentation.

Findings

Improved mean Dice score from 74.8 to 76.1 with AnatoMix.

Demonstrated effectiveness on a public CT dataset.

Enhanced dataset diversity improves segmentation performance.

Abstract

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.