Benchmarking CNN-based Models against Transformer-based Models for Abdominal Multi-Organ Segmentation on the RATIC Dataset
This work addresses the problem of selecting effective models for medical image segmentation on heterogeneous datasets, providing insights for researchers and practitioners, but it is incremental as it compares existing methods without introducing new ones.
The study benchmarked CNN-based SegResNet against three hybrid transformer-based models for abdominal multi-organ segmentation on the RATIC dataset, finding that SegResNet outperformed all transformer models across all organs, with UNETR++ being the most competitive transformer and UNETR showing faster convergence.
Accurate multi-organ segmentation in abdominal CT scans is essential for computer-aided diagnosis and treatment. While convolutional neural networks (CNNs) have long been the standard approach in medical image segmentation, transformer-based architectures have recently gained attention due to their ability to model long-range dependencies. In this study, we systematically benchmark the three hybrid transformer-based models UNETR, SwinUNETR, and UNETR++ against a strong CNN baseline, SegResNet, for volumetric multi-organ segmentation on the heterogeneous RATIC dataset. The dataset comprises 206 annotated CT scans from 23 institutions worldwide, covering five abdominal organs. All models were trained and evaluated under identical preprocessing and training conditions using the Dice Similarity Coefficient (DSC) as the primary metric. The results show that the CNN-based SegResNet achieves the highest overall performance, outperforming all hybrid transformer-based models across all organs. Among the transformer-based approaches, UNETR++ delivers the most competitive results, while UNETR demonstrates notably faster convergence with fewer training iterations. These findings suggest that, for small- to medium-sized heterogeneous datasets, well-optimized CNN architectures remain highly competitive and may outperform hybrid transformer-based designs.