A novel recursive transformer-based U-Net architecture for enhanced multi-scale medical image segmentation

Shanshan Li ¹, Xuefeng Liu ¹, Min Fu ²

⁰College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, 266061, China.

Computers in Biology and Medicine +

|

July 6, 2025

View abstract on PubMed

Summary

A new recursive transformer-based U-Net (ReT-UNet) improves medical image segmentation by capturing long-range dependencies and enhancing feature representation. This advanced deep learning model offers superior accuracy and stability for tasks like cardiac, nodule, and polyp segmentation.

Area Of Science

Artificial Intelligence
Medical Imaging Analysis
Deep Learning Architectures

Background

Automatic medical image segmentation is crucial for diagnosis and treatment planning.
U-Net is widely used but struggles with long-range dependencies in complex medical images.
Anatomical structures can be difficult to distinguish from backgrounds in textured images.

Purpose Of The Study

To introduce a novel network, the recursive transformer-based U-Net (ReT-UNet), to overcome U-Net's limitations.
To enhance the capture of long-range dependencies and improve feature abstraction in medical images.
To improve the accuracy and stability of medical image segmentation.

Main Methods

Developed ReT-UNet integrating recursive feature learning and transformer technology.
Introduced a multi-scale global feature fusion (Multi-GF) module for enhanced contextual understanding.
Incorporated a recursive feature accumulation block and a lightweight atrous spatial pyramid pooling (ASPP) module.

Main Results

Ablation experiments demonstrated consistent performance across multiple trials.
The method showed reduced mis-segmented regions in cardiac, pulmonary nodule, and polyp segmentation.
Improved segmentation accuracy and stability compared to existing state-of-the-art methods.

Conclusions

ReT-UNet demonstrates superior performance over related methods in medical image segmentation.
The proposed architecture holds significant potential for various medical image analysis applications.

Keywords:

Deep learning Medical image processing Multi-scale feature fusion Recursive feature learning Transformer technology