CTI-Unet: Hybrid Local Features and Global Representations Efficiently

Recent advancements in medical image segmentation have demonstrated superior performance by combining Transformer and U-Net due to the Transformer's exceptional ability to capture long-range semantic dependencies. However, existing approaches mostly replace or concatenate the Convolutional Neur...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 735 - 739
Main Authors Hu, Haigen, Jin, Zhichao, Zhou, Qianwei, Guan, Qiu, Chen, Qi
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
CNN
Codes
Convolutional neural networks
Feature extraction
Fuses
Image segmentation
Medical Image Segmentation
Multi-Scale Feature Fusion
Semantics
Transformers
Vision Transformer
Online AccessGet full text

Cover

More Information
Summary:Recent advancements in medical image segmentation have demonstrated superior performance by combining Transformer and U-Net due to the Transformer's exceptional ability to capture long-range semantic dependencies. However, existing approaches mostly replace or concatenate the Convolutional Neural Networks (CNNs) and Transformers in series, which limits the potential of their combination. In this paper, we introduce a dual-branch feature encoder, CTI-UNet, that effectively fuses the global representations and local features of the CNN and Transformer branches at different scales through bidirectional feature interaction. Our proposed method outperforms existing approaches on multiple medical datasets, demonstrating state-of-the-art performance. The code for CTI-UNet is publicly available at https://github.com/huhaigen/CTI-UNet.
DOI:10.1109/ICIP49359.2023.10222235