Transformers for Medical Image Segmentation
Authors:
- 29 August 2025
- book chapter
- Published by IGI Global Scientific Publishing
- p. 161-218
Abstract
Recent advances in transformer-based deep learning architectures have significantly enhanced medical image segmentation by enabling precise delineation of anatomical structures across various imaging modalities and clinical contexts. Transformers leverage self-attention mechanisms to model long-range dependencies and global context, overcoming the limitations of convolutional neural networks with localized receptive fields. This chapter reviews the application of transformers in segmentation tasks such as brain tumors, retinal vessels, and skin lesions, highlighting innovations in architecture, performance benchmarks, and evaluation metrics. Comparative analyses reveal trends in accuracy, robustness, and efficiency, while addressing challenges like computational demands, limited annotated data, and clinical interpretability. Future directions include lightweight architectures, multimodal integration, and clinical validation. These developments illustrate the transformative role of transformers in precision medicine and AI-driven healthcare.Keywords
This publication has 155 references indexed in Scilit:
- Transformer Skip‐Fusion Based SwinUNet for Liver Segmentation From CT ImagesInternational Journal of Imaging Systems and Technology, 2024
- TrEnD: A transformer‐based encoder‐decoder model with adaptive patch embedding for mass segmentation in mammogramsMedical Physics, 2023
- NVTrans‐UNet: Neighborhood vision transformer based U‐Net for multi‐modal cardiac MR image segmentationJournal of Applied Clinical Medical Physics, 2023
- RT‐Unet: An advanced network based on residual network and transformer for medical image segmentationInternational Journal of Intelligent Systems, 2022
- Automated Kidney Tumor Segmentation with Convolution and Transformer Network2022
- Multi-compound Transformer for Accurate Biomedical Image Segmentation2021
- CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation2021
- TransBridge: A Lightweight Transformer for Left Ventricle Segmentation in Echocardiography2021
- TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation2021
- Boundary-Aware Transformers for Skin Lesion Segmentation2021