Benchmarking CNN-based Models against Transformer-based Models for Abdominal Multi-Organ Segmentation on the RATIC Dataset

• URL: http://arxiv.org/abs/2603.18616v1
• Date: Thu, 19 Mar 2026 08:35:11 GMT
• Title: Benchmarking CNN-based Models against Transformer-based Models for Abdominal Multi-Organ Segmentation on the RATIC Dataset
• Abstract summary: Multi-organ segmentation in abdominal CT scans is essential for computer-aided diagnosis and treatment.<n> transformer-based architectures have recently gained attention due to their ability to model long-range dependencies.<n>In this study, we benchmark the three hybrid transformer-based models UNETR, SwinUNETR, and UNETR++ against a strong CNN baseline, SegResNet, for volumetric multi-organ segmentation.
• Score: 3.428885759047836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• MSA-DCNN: A Data-Efficient Multi-Scale Deformable CNN for Medical Image Classification [1.6566053195631467]
  Existing deep learning methods struggle with multi-scale morphology and limited annotations due to fixed sampling and data-hungry training.<n>We propose MSA-DCNN, a scale-consistent deformable attention learning framework that introduces adaptive multi-scale sampling, within-scale saliency refinement, learned cross-scale fusion, and auxiliary self-distillation within a unified optimisation scheme.
  arXiv  Detail & Related papers  (2026-07-07T09:52:46Z)
• Performance and Interpretability of Convolutional, Transformer, and Hybrid Deep Learning Models in Colorectal Histology Classification [0.0]
  This study evaluated twelve ImageNet-pretrained CNN, transformer, and hybrid architectures using the Kather colorectal histopathology dataset.<n> EVA-02 achieved the highest overall performance (97.1% accuracy, 97.0% F1-score), closely followed by ViT-B/16.
  arXiv  Detail & Related papers  (2026-06-21T18:56:42Z)
• When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation [9.108764893521526]
  We present the first comprehensive benchmarking of convolutional neural networks, vision transformers and state-space mamba architectures for automated dental caries segmentation on panoramic radiographs through a DC1000 dataset.<n>Results reveal that, contrary to the growing trend toward complex attention based architectures, the CNN-based DoubleU-Net achieved the highest dice coefficient of 0.7345, mIoU of 0.5978, and precision of 0.8145, outperforming all transformer and Mamba variants.
  arXiv  Detail & Related papers  (2025-11-18T19:16:21Z)
• When Swin Transformer Meets KANs: An Improved Transformer Architecture for Medical Image Segmentation [10.656996937993199]
  We introduce UKAST, a U-Net like architecture that integrates rational-function based Kolmogorov-Arnold Networks (KANs) into Swin Transformer encoders.<n>UKAST achieves state-of-the-art performance on four diverse 2D and 3D medical image segmentation benchmarks.
  arXiv  Detail & Related papers  (2025-11-06T05:44:57Z)
• CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation [60.08541107831459]
  This paper proposes a CNN-Transformer rectified collaborative learning framework to learn stronger CNN-based and Transformer-based models for medical image segmentation. Specifically, we propose a rectified logit-wise collaborative learning (RLCL) strategy which introduces the ground truth to adaptively select and rectify the wrong regions in student soft labels. We also propose a class-aware feature-wise collaborative learning (CFCL) strategy to achieve effective knowledge transfer between CNN-based and Transformer-based models in the feature space.
  arXiv  Detail & Related papers  (2024-08-25T01:27:35Z)
• Deep models for stroke segmentation: do complex architectures always perform better? [1.4651272514940197]
  Stroke segmentation plays a crucial role in the diagnosis and treatment of stroke patients. Deep models have been introduced for general medical image segmentation. In this study, we selected four types of deep models that were recently proposed and evaluated their performance for stroke segmentation.
  arXiv  Detail & Related papers  (2024-03-25T20:44:01Z)
• SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging [59.78761085714715]
  This study proposes a novel Siamese Dual-Resolution Transformer (SDR-Former) framework for liver lesion classification. The proposed framework has been validated through comprehensive experiments on two clinical datasets. To support the scientific community, we are releasing our extensive multi-phase MR dataset for liver lesion analysis to the public.
  arXiv  Detail & Related papers  (2024-02-27T06:32:56Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network [63.845552349914186]
  Capturing global contextual information plays a critical role in breast ultrasound (BUS) image classification. Vision Transformers have an improved capability of capturing global contextual information but may distort the local image patterns due to the tokenization operations. In this study, we proposed a hybrid multitask deep neural network called Hybrid-MT-ESTAN, designed to perform BUS tumor classification and segmentation.
  arXiv  Detail & Related papers  (2023-08-04T01:19:32Z)
• Learning from partially labeled data for multi-organ and tumor segmentation [102.55303521877933]
  We propose a Transformer based dynamic on-demand network (TransDoDNet) that learns to segment organs and tumors on multiple datasets. A dynamic head enables the network to accomplish multiple segmentation tasks flexibly. We create a large-scale partially labeled Multi-Organ and Tumor benchmark, termed MOTS, and demonstrate the superior performance of our TransDoDNet over other competitors.
  arXiv  Detail & Related papers  (2022-11-13T13:03:09Z)
• nnFormer: Interleaved Transformer for Volumetric Segmentation [50.10441845967601]
  We introduce nnFormer, a powerful segmentation model with an interleaved architecture based on empirical combination of self-attention and convolution. nnFormer achieves tremendous improvements over previous transformer-based methods on two commonly used datasets Synapse and ACDC.
  arXiv  Detail & Related papers  (2021-09-07T17:08:24Z)
• Spherical coordinates transformation pre-processing in Deep Convolution Neural Networks for brain tumor segmentation in MRI [0.0]
  Deep Convolutional Neural Networks (DCNN) have recently shown very promising results. DCNN models need large annotated datasets to achieve good performance. In this work, a 3D Spherical coordinates transform has been hypothesized to improve DCNN models' accuracy.
  arXiv  Detail & Related papers  (2020-08-17T05:11:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.