TFCNs: A CNN-Transformer Hybrid Network for Medical Image Segmentation

TL;DR

This paper introduces TFCNs, a hybrid CNN-Transformer model that enhances medical image segmentation by effectively capturing semantic features and reducing distortions, achieving state-of-the-art results on CT datasets.

Contribution

The paper presents a novel CNN-Transformer hybrid architecture with RL-Transformer and CLAB modules for improved medical image segmentation.

Findings

Achieved dice score of 83.72% on Synapse dataset.

Demonstrated robustness on COVID-19 lesion datasets.

Outperformed existing segmentation methods.

Abstract

Medical image segmentation is one of the most fundamental tasks concerning medical information analysis. Various solutions have been proposed so far, including many deep learning-based techniques, such as U-Net, FC-DenseNet, etc. However, high-precision medical image segmentation remains a highly challenging task due to the existence of inherent magnification and distortion in medical images as well as the presence of lesions with similar density to normal tissues. In this paper, we propose TFCNs (Transformers for Fully Convolutional denseNets) to tackle the problem by introducing ResLinear-Transformer (RL-Transformer) and Convolutional Linear Attention Block (CLAB) to FC-DenseNet. TFCNs is not only able to utilize more latent information from the CT images for feature extraction, but also can capture and disseminate semantic features and filter non-semantic features more effectively through the CLAB module. Our experimental results show that TFCNs can achieve state-of-the-art performance with dice scores of 83.72\% on the Synapse dataset. In addition, we evaluate the robustness of TFCNs for lesion area effects on the COVID-19 public datasets. The Python code will be made publicly available on https://github.com/HUANGLIZI/TFCNs.