Skip to main content

ORIGINAL RESEARCH article

Front. Physiol.
Sec. Computational Physiology and Medicine
Volume 15 - 2024 | doi: 10.3389/fphys.2024.1412985

BFNet: A full-encoder skip connect way for medical image segmentation

Provisionally accepted
Siyu Zhan Siyu Zhan 1,2*Quan Yuan Quan Yuan 3XIN LEI XIN LEI 4Rui Huang Rui Huang 5*Lu Guo Lu Guo 6*Ke Liu Ke Liu 7*Rong Chen Rong Chen 8*
  • 1 Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, Sichuan Province, China
  • 2 Trusted Cloud Computing and Big Data Key Laboratory, School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan Province, China
  • 3 School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan Province, China
  • 4 School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan Province, China
  • 5 Hepatobility & Pancreatic Cen, Sichuan Provincial People’s Hospital,University of Electronic Science and Technology of China, Chengdu, China
  • 6 Department of Pulmonary and Critical Care Medicine, Sichuan Provincial People’s Hospital,University of Electronic Science and Technology of China, Chengdu, China
  • 7 Department of Cardiac Surgery, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, China
  • 8 Department of Delivery room, Chengdu Women and Children's Central Hospital, University of Electronic Science and Technology of China, Chengdu, China

The final, formatted version of the article will be published soon.

    In recent years, semantic segmentation in deep learning has been widely applied in medical image segmentation, leading to the development of numerous models. Convolutional Neural Networks (CNNs) have achieved milestone achievements in medical image analysis. Particularly, deep neural networks based on U-shaped architectures and skip connections have been extensively employed in various medical image tasks. U-Net is characterized by its encoder-decoder architecture and pioneering skip connections, along with multi-scale features, has served as a fundamental network architecture for many modifications.But U-Net cannot fully utilize all the information from the encoder layer in the decoder layer. U-Net++ connects mid parameters of different dimensions through nested and dense skip connections. However, it can only alleviate the disadvantage of not being able to fully utilize the encoder information and will greatly increase the model parameters. In this paper, a novel BFNet is proposed to utilize all feature maps from the encoder at every layer of the decoder and reconnects with the current layer of the encoder. This allows the decoder to better learn the positional information of segmentation targets and improves learning of boundary information and abstract semantics in the current layer of the encoder. Besides enhancing accuracy, our proposed BFNet also reduces network parameters. All the advantages we proposed are demonstrated on our dataset.

    Keywords: deep learning, U-net, Medical image segmentation, Pulmonarty embolism, CNN -convolutional neural network

    Received: 13 May 2024; Accepted: 16 Jul 2024.

    Copyright: © 2024 Zhan, Yuan, LEI, Huang, Guo, Liu and Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Siyu Zhan, Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan Province, China
    Rui Huang, Hepatobility & Pancreatic Cen, Sichuan Provincial People’s Hospital,University of Electronic Science and Technology of China, Chengdu, China
    Lu Guo, Department of Pulmonary and Critical Care Medicine, Sichuan Provincial People’s Hospital,University of Electronic Science and Technology of China, Chengdu, China
    Ke Liu, Department of Cardiac Surgery, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, China
    Rong Chen, Department of Delivery room, Chengdu Women and Children's Central Hospital, University of Electronic Science and Technology of China, Chengdu, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.