Advancing hierarchical neural networks with scale-aware pyramidal feature learning for medical image dense prediction.

Journal: Computer methods and programs in biomedicine
PMID: 40184852

Abstract

BACKGROUND AND OBJECTIVE: Hierarchical neural networks are pivotal in medical imaging for multi-scale representation, aiding in tasks such as object detection and segmentation. However, their effectiveness is often limited by the loss of intra-scale information and misalignment of inter-scale features. Our study introduces the Integrated-Scale Pyramidal Interactive Reconfiguration to Enhance feature learning (INSPIRE).

Authors

  • Xiang Liu
    College of Agricultural Science and Engineering, Hohai University, Nanjing 210098, China; Anhui Provincial Key Laboratory of Environmental Pollution Control and Resource Reuse, Anhui Jianzhu University, Hefei 230009, China.
  • James Liang
    Department of Computer Engineering, Rochester Institute of Technology, USA.
  • Jianwei Zhang
    University of Hamburg, 22527 Hamburg, Germany.
  • Zihan Qian
    Department of Biostatistics, Harvard TH.Chan School of Public Health, USA.
  • Phoebe Xing
    Alvus Health Inc., Harvard Pagliuca Life Lab, USA; United World College of South East Asia, Singapore.
  • Taige Chen
    Department of Physics, University of Illinois Urbana-Champaign, USA.
  • Shanchieh Yang
    Department of Computer Engineering, Rochester Institute of Technology, USA.
  • Chijioke Chukwudi
    Department of Surgery, Massachusetts General Hospital, USA.
  • Liang Qiu
  • Dongfang Liu
    Department of Pathology, Immunology and Laboratory Medicine, Rutgers University- New Jersey Medical School, 185 South Orange Avenue, Newark, NJ, 07103, USA; Center for Immunity and Inflammation, New Jersey Medical School, Rutgers-The State University of New Jersey, Newark, NJ, 07103, USA. Electronic address: dongfang.liu@rutgers.edu.
  • Junhan Zhao
    Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02114, United States.

Keywords

External Resources

Popular Topics
Recent Journals