Denoising Diffusion Probabilistic Model to Simulate Contrast-enhanced spinal MRI of Spinal Tumors: A Multi-Center Study.

Journal: Academic radiology
Published Date:

Abstract

RATIONALE AND OBJECTIVES: To generate virtual T1 contrast-enhanced (T1CE) sequences from plain spinal MRI sequences using the denoising diffusion probabilistic model (DDPM) and to compare its performance against one baseline model pix2pix and three advanced models.

Authors

  • Chenxi Wang
    Laboratory of Cell Engineering, Institute of Biotechnology, Research Unit of Cell Death Mechanism, Chinese Academy of Medical Science, 2021RU008, Beijing 100071, China.
  • Senpeng Zhang
    Department of Biomedical Informatics, State Key Laboratory of Vascular Homeostasis and Remodeling, School of Basic Medical Sciences, Peking University, 38 Xueyuan Road, Beijing 100191, China (S.Z.).
  • Jun Xu
    Department of Nephrology, The Affiliated Baiyun Hospital of Guizhou Medical University, Guizhou, China.
  • Honghao Wang
    Department of Radiology, State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University Third Hospital, 49 North Garden Road, Haidian District, Beijing 100191, PR China (C.W., J.X., H.W., Q.W., Y.Z., X.X., N.L.).
  • Qizheng Wang
    Department of Radiology, Peking University Third Hospital, 49 North Garden Road, Haidian District, Beijing, 100191, People's Republic of China.
  • Yupeng Zhu
  • Xiaoying Xing
    Department of Radiology, Peking University Third Hospital, Haidian District, 49 North Garden Road, Beijing, 100191, People's Republic of China.
  • Dapeng Hao
    Department of Radiology, The Affiliated Hospital of Qingdao University, Shinan Jiangsu 16 Rd, Qingdao, Shandong 266003, China.
  • Ning Lang
    Department of Radiology, Peking University Third Hospital, Beijing 10019, China.