Your browser doesn't support javascript.
loading
Medical image segmentation network based on multi-scale frequency domain filter.
Chen, Yufeng; Zhang, Xiaoqian; Peng, Lifan; He, Youdong; Sun, Feng; Sun, Huaijiang.
Afiliação
  • Chen Y; School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, PR China. Electronic address: c_y_f_1@163.com.
  • Zhang X; School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, PR China. Electronic address: zhangxiaoqian@swust.edu.cn.
  • Peng L; School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, PR China. Electronic address: penglifan1226@163.com.
  • He Y; School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, PR China. Electronic address: jiazhuangdiandian@163.com.
  • Sun F; Mianyang Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Mianyang 621010, China; NHC Key Laboratory of Nuclear Technology Medical Transformation, Mianyang Central Hospital, Mianyang 621010, PR China. Electronic address: sf266@qq.com.
  • Sun H; School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, PR China. Electronic address: sunhuaijiang@njust.edu.cn.
Neural Netw ; 175: 106280, 2024 Jul.
Article em En | MEDLINE | ID: mdl-38579574
ABSTRACT
With the development of deep learning, medical image segmentation in computer-aided diagnosis has become a research hotspot. Recently, UNet and its variants have become the most powerful medical image segmentation methods. However, these methods suffer from (1) insufficient sensing field and insufficient depth; (2) computational nonlinearity and redundancy of channel features; and (3) ignoring the interrelationships among feature channels. These problems lead to poor network segmentation performance and weak generalization ability. Therefore, first of all, we propose an effective replacement scheme of UNet base block, Double residual depthwise atrous convolution (DRDAC) block, to effectively improve the deficiency of receptive field and depth. Secondly, a new linear module, the Multi-scale frequency domain filter (MFDF), is designed to capture global information from the frequency domain. The high order multi-scale relationship is extracted by combining the depthwise atrous separable convolution with the frequency domain filter. Finally, a channel attention called Axial selection channel attention (ASCA) is redesigned to enhance the network's ability to model feature channel interrelationships. Further, we design a novel frequency domain medical image segmentation baseline method FDFUNet based on the above modules. We conduct extensive experiments on five publicly available medical image datasets and demonstrate that the present method has stronger segmentation performance as well as generalization ability compared to other state-of-the-art baseline methods.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação / Aprendizado Profundo Limite: Humans Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação / Aprendizado Profundo Limite: Humans Idioma: En Ano de publicação: 2024 Tipo de documento: Article