loading page

MCRformer: Morphological Constraint Reticular Transformer for 3D Medical Image Segmentation
  • +7
  • Jun Li ,
  • Nan Chen ,
  • Han Zhou ,
  • Riqing Chen ,
  • Chunhui Feng ,
  • Heng Dong ,
  • Taotao Lai ,
  • Changcai Yang ,
  • Lifang Wei ,
  • Fanggang Cai
Jun Li
Fujian Agriculture and Forestry University, Fujian Agriculture and Forestry University, Fujian Agriculture and Forestry University, Fujian Agriculture and Forestry University, Fujian Agriculture and Forestry University

Corresponding Author:[email protected]

Author Profile
Riqing Chen
Author Profile
Chunhui Feng
Author Profile
Heng Dong
Author Profile
Taotao Lai
Author Profile
Changcai Yang
Author Profile
Lifang Wei
Author Profile
Fanggang Cai
Author Profile

Abstract

Medical image segmentation is essential in medical image analysis since it can provide reliable assistance in computer-aided clinical diagnosis, treatment plan-ning, and intervention. Although deep learning algorithms based on CNNs and Transformers have made notable progress in conventional image segmentation, medical image segmentation is still challenging owing to limited ability to learn the prior information about the target shapes, especially for large target areas, which have the problems of rough boundaries in the segmentation results, such as over-segmentation, under-segmentation and internal holes. To alleviate these issues, we propose a novel 3D medical image segmentation network based on Transformer Blocks and the CNN model by fusing morphological information, and design a Reticular Transformer (RT) by the reticular mechanism. Specifically, firstly, the morphological constraint stream is designed to learn the prior shape structure information based on the CNN model. Secondly, the Reticular Transformer is utilized to obtain multi-scale information based on the Transformer, which can further utilize the local texture information and underlying semantic information to obtain sufficient details and receptive field. The experiments on the datasets demonstrate that our proposed method outperforms many existing segmentation models in terms of the performance in metrics DSC and HD (80.46\% in DSC on the Synapse dataset and 90.83\% in DSC on the ACDC dataset). The code will be released at https://github.com/rocklijun/MCRformer.
Dec 2023Published in Expert Systems with Applications volume 232 on pages 120877. 10.1016/j.eswa.2023.120877