mlsanityData to 14 Oct 2026

Comparative Study of UNet-based Architectures for Liver Tumor Segmentation in Multi-Phase Contrast-Enhanced Computed Tomography

arXiv 2510.25522 ↗First posted 29 Oct 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Segmentation of liver structures in multi-phase contrast-enhanced computed tomography (CECT) plays a crucial role in computer-aided diagnosis and treatment planning. In this study, we investigate the performance of UNet-based architectures for liver tumor segmentation, evaluating ResNet, Transformer-based, and State-space (Mamba) backbones initialized with pretrained weights. Our comparative analysis reveals that despite the theoretical advantages of modern architectures in modeling long-range dependencies, ResNet-based models demonstrated superior sample efficiency on this dataset. This suggests that the inherent inductive biases of Convolutional Neural Networks (CNNs) remain advantageous for generalizing on limited medical data compared to data-hungry alternatives. To further improve segmentation quality, we introduce attention mechanisms into the backbone, finding that the Convolutional Block Attention Module (CBAM) yields the optimal configuration. The ResNetUNet3+ with CBAM achieved the highest nominal performance with a Dice score of 0.755 and IoU of 0.662, while also delivering the most precise boundary delineation (lowest HD95 of 77.911). Critically, while statistical testing indicated that the improvement in mean Dice score was not significant (p > 0.05) compared to the baseline, the proposed model exhibited greater stability (lower standard deviation) and higher specificity (0.926). These findings demonstrate that classical ResNet architectures, when enhanced with modern attention modules, provide a robust and statistically comparable alternative to emerging methods, offering a stable direction for liver tumor segmentation in clinical practice.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 29 Oct 2025.

Builds on

14 of 35 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  6. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  7. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 419
  8. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
  9. 2024Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentationcited by 133
  10. 2020Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networkscited by 79
  11. 2020Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mappingcited by 49
  12. 2023From CNN to Transformer: A Review of Medical Image Segmentation Modelscited by 22
2 more
  1. 2025Deep Skin Lesion Segmentation with Transformer-CNN Fusion: Toward Intelligent Skin Cancer Analysiscited by 5
  2. 2023Trustworthy Multi-phase Liver Tumor Segmentation via Evidence-based Uncertaintycited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer Segmentation
  2. 2026Parameter-Efficient Fine-Tuning of Foundation Models for Liver Tumor Segmentation in CT
  3. 2025ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation
  4. 2024MLLA-UNet: Mamba-like Linear Attention in an Efficient U-Shape Model for Medical Image Segmentation
  5. 2026MNet++: Extended 2D/3D Networks for Anisotropic Medical Image Segmentation
  6. 2023Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation
  7. 2025UNet with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning for Medical Image Segmentation
  8. 2023Rethinking Intermediate Layers design in Knowledge Distillation for Kidney and Liver Tumor Segmentation