Deep learning network enhances imaging quality of low-b-value diffusion-weighted imaging and improves lesion detection in prostate cancer.

Journal: BMC cancer
Published Date: May 27, 2025

Abstract

BACKGROUND: Diffusion-weighted imaging with higher b-value improves detection rate for prostate cancer lesions. However, obtaining high b-value DWI requires more advanced hardware and software configuration. Here we use a novel deep learning network, NAFNet, to generate a deep learning reconstructed (DLR) images from 800 b-value to mimic 1500 b-value images, and to evaluate its performance and lesion detection improvements based on whole-slide images (WSI).

Authors

  • Zheng Liu
    ICSC World Laboratory, Geneva, Switzerland.
  • Wei-Jie Gu
    Department of Urology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China.
  • Fang-Ning Wan
    Department of Urology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China.
  • Zhang-Zhe Chen
    Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China.
  • Yun-Yi Kong
    Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China.
  • Xiao-Hang Liu
    Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China. 09111230002@fudan.edu.cn.
  • Ding-Wei Ye
    Department of Urology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China. dwyeli@163.com.
  • Bo Dai
    School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China.

Keywords

External Resources

Popular Topics
Recent Journals