MC-DC: An MLP-CNN Based Dual-path Complementary Network for Medical Image Segmentation

Image credit: Elsevier

Abstract

Fusing the CNN and Transformer in the encoder has recently achieved outstanding performance in medical image segmentation. However, two obvious limitations require addressing: (1) The utilization of Transformer leads to heavy parameters, and its intricate structure demands ample data and resources for training, and (2) most previous research had predominantly focused on enhancing the performance of the feature encoder, with little emphasis placed on the design of the feature decoder. To this end, we propose a novel MLP-CNN based dual-path complementary (MC-DC) network for medical image segmentation, which replaces the complex Transformer with a cost-effective Multi-Layer Perceptron (MLP). Specifically, a dual-path complementary (DPC) module is designed to effectively fuse multi-level features from MLP and CNN. To respectively reconstruct global and local information, the dual-path decoder is proposed which is mainly composed of cross-scale global feature fusion (CS-GF) module and cross-scale local feature fusion (CS-LF) module. Moreover, we leverage a simple and efficient segmentation mask feature fusion (SMFF) module to merge the segmentation outcomes generated by the dual-path decoder. Comprehensive experiments were performed on three typical medical image segmentation tasks. For skin lesions segmentation, our MC-DC network achieved 91.69% Dice and 9.52mm ASSD on the ISIC2018 dataset. In addition, the 91.6% Dice and 94.4% Dice were respectively obtained on the Kvasir-SEG dataset and CVC-ClinicDB dataset for polyp segmentation. Moreover, we also conducted experiments on the private COVID-DS36 dataset for lung lesion segmentation. Our MC-DC has achieved 87.6% [87.1%, 88.1%], and 92.3% [91.8%, 92.7%] on ground-glass opacity, interstitial infiltration, and lung consolidation, respectively. The experimental results indicate that the proposed MC-DC network exhibits exceptional generalization capability and surpasses other state-of-the-art methods in higher results and lower computational complexity.

Publication
Computer Methods and Programs in Biomedicine
Xiaoben Jiang 蒋晓奔
Xiaoben Jiang 蒋晓奔
PhD. One apple a day keep the doctor away.

A doctor student of this laboratory, research interests include Medical image processing, AIGC, and Image denoising.

Yu Zhu 朱煜
Yu Zhu 朱煜
Professor. Experts in artificial intelligence and computer vision. Lab leader.

Leader of this laboratory, research interests include Artificial Intelligence, Computer Vision, Industrial controls, Digital Image and Video Processing, Machine learning, Deep Learning and Applications.

Yatong Liu 刘雅童
Yatong Liu 刘雅童
PhD.

A doctoral student of this laboratory, research interests include Medical Image Processing, Deep Learning Algorithm and Multi-source Medical Image Intelligent Analysis.