Abdominal multi-organ segmentation in CT using Swinunter
This work addresses a critical problem in medical imaging for clinical applications such as disease detection and treatment planning, but it is incremental as it adapts an existing transformer-based approach to a specific dataset.
The paper tackles abdominal multi-organ segmentation in CT scans by applying a transformer-based model (Swinunter) to overcome challenges like vague organ boundaries and varying organ sizes, achieving acceptable results and inference time on a public validation set.
Abdominal multi-organ segmentation in computed tomography (CT) is crucial for many clinical applications including disease detection and treatment planning. Deep learning methods have shown unprecedented performance in this perspective. However, it is still quite challenging to accurately segment different organs utilizing a single network due to the vague boundaries of organs, the complex background, and the substantially different organ size scales. In this work we used make transformer-based model for training. It was found through previous years' competitions that basically all of the top 5 methods used CNN-based methods, which is likely due to the lack of data volume that prevents transformer-based methods from taking full advantage. The thousands of samples in this competition may enable the transformer-based model to have more excellent results. The results on the public validation set also show that the transformer-based model can achieve an acceptable result and inference time.