Abdominal multi-organ segmentation in CT using Swinunter

TL;DR

This paper explores the use of a transformer-based model for abdominal multi-organ segmentation in CT scans, demonstrating promising results and inference efficiency, especially with large datasets.

Contribution

It introduces a transformer-based approach for multi-organ segmentation in CT, highlighting its potential advantages over traditional CNN methods with sufficient data.

Findings

Transformer model achieves acceptable segmentation accuracy.

Large datasets enable transformer models to outperform CNNs.

Inference time remains efficient with the transformer approach.

Abstract

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.