3D Transformer Models for Volumetric Medical Image Segmentation

View at publisher Summarise with VIRAT
Authors: D. Shunmuga Kumari, M. Sakthivanitha, J Chitra, M. Mohamed Sirajudeen, S. Nithya Priya, P.N. Shiammala
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Segmentation of volumetric medical images is important for computer-aided diagnosis, treatment planning, and monitoring for disease progression. However, current approaches using CNNs may struggle to capture long-range dependencies across three-dimensional position space, and they may lack fine anatomical detail due to down-sampling techniques. A TransVol-Net, a 3D transformer-based segmentation framework has been introduced with the following components: 3D patch embedding, a hybrid convolution - transformer encoder-decoder backbone, and a multi-scale fusion refinement head. The model architecture uses window-based multi-head self-attention for fast global context modeling while leveraging convolution layers to maintain local texture information. TransVol-Net is evaluated on the BraTS dataset, where it achieves mean Dice scores of$\geq 91.0 {\%}$(WT),$\geq 88.0 {\%}$(TC), and$\geq 85.0 {\%}$(ET) across all the tumors, and exceeds other, state-of-the-art methods for 3D U-Net, TransBTS, or Swin UNTR. The results further evidence increased sensitivity for small lesions and more fluid boundary delineation for tumor voxels compared with other state-of-the-art segmentation models. In conclusion, our findings for TransVol-Net demonstrate a reformulated model that provides a more scalable and clinically acceptable avenue for volumetric segmentation that has applicability to CT, MRI, and PET-CT imaging workflows.

Fields of Study & Subjects

Medical Image Segmentation Techniques Brain Tumor Detection and Classification Advanced Neural Network Applications

Publication details

Journal / source
International Conference on Intelligent Sustainable Systems (ICISS)
Pages
1660–1665
Publication date
4 March 2026
Language
EN