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

Liu C, Fan F, Schwarz A, Maier A (2025)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2025

Journal

Informatik aktuell Gesellschaft für Informatik (GI)

Publisher: Springer Vieweg

Series: Informatik aktuell

City/Town: Wiesbaden

Pages Range: 136-141

Conference Proceedings Title: Bildverarbeitung für die Medizin 2025. Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025

Event location: Regensburg DE

ISBN: 9783658474218

DOI: 10.1007/978-3-658-47422-5_29

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, such as nnUNet, are achieving promising accuracy. However, overfitting is still a critical issue for DL-based models due to the limited size of segmentation datasets especially in the medical domain. In this work, a novel data augmentation (DA) strategy is proposed to improve the over-fitting problem of multi-organ segmentation datasets, namely AnatoMix. Different from basic DA strategies based on image transformation on a single image, AnatoMix manipulates multiple images in the segmentation dataset and generates new data by mixing multiple images while maintaining human anatomy as realistic as possible. AnatoMix takes the size and location of each organ into consideration, and the corresponding segmentation ground truth is automatically obtained. The initial experiments have been done to extend the publicly available CT-ORG dataset with AnatoMix generating 1,545 new volumes from the 28 original ones. The extended dataset is then evaluated by training a U-Net on the original and the augmented dataset and tested on the same test data. In our experiments the extended dataset leads to mean dice of 76.1, compared with 74.8 on the original dataset. This shows AnatoMix can effectively improve the generalizability of a limited segmentation dataset.

Authors with CRIS profile

Chang Liu Lehrstuhl für Informatik 5 (Mustererkennung) Annette Schwarz Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Liu, C., Fan, F., Schwarz, A., & Maier, A. (2025). Anatomy-aware Data Augmentation for Multi-organ Segmentation in CT: AnatoMix. In Christoph Palm, Katharina Breininger, Thomas Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Thomas M. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2025. Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025 (pp. 136-141). Regensburg, DE: Wiesbaden: Springer Vieweg.

MLA:

Liu, Chang, et al. "Anatomy-aware Data Augmentation for Multi-organ Segmentation in CT: AnatoMix." Proceedings of the German Conference on Medical Image Computing, 2025, Regensburg Ed. Christoph Palm, Katharina Breininger, Thomas Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Thomas M. Tolxdorff, Wiesbaden: Springer Vieweg, 2025. 136-141.

BibTeX: Download