Cross-shaped windows transformer with self-supervised pretraining for clinically significant prostate cancer detection in bi-parametric MRI.

Journal: Medical physics
Published Date: Nov 26, 2024

Abstract

BACKGROUND: Bi-parametric magnetic resonance imaging (bpMRI) has demonstrated promising results in prostate cancer (PCa) detection. Vision transformers have achieved competitive performance compared to convolutional neural network (CNN) in deep learning, but they need abundant annotated data for training. Self-supervised learning can effectively leverage unlabeled data to extract useful semantic representations without annotation and its associated costs.

Authors

  • Yuheng Li
    Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA.
  • Jacob Wynne
    Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA.
  • Jing Wang
    Endoscopy Center, Peking University Cancer Hospital and Institute, Beijing, China.
  • Richard L J Qiu
    Department of Radiation Oncology, Winship Cancer Institute of Emory University, Atlanta, GA, United States of America.
  • Justin Roper
    Radiology Oncology, Emory University, 1365 Clifton Road, Department of Radiation Oncology, Atlanta, Atlanta, Georgia, 30322, UNITED STATES.
  • Shaoyan Pan
    Department of Biomedical Informatics, Emory University, Atlanta, GA 30308, United States of America.
  • Ashesh B Jani
    Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA 30322, USA.
  • Tian Liu
    Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA 30322, USA.
  • Pretesh R Patel
    Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA.
  • Hui Mao
  • Xiaofeng Yang
    Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA 30322, USA.

Keywords

External Resources

Popular Topics
Recent Journals