Deep Learning model-based approach for preoperative prediction of Ki67 labeling index status in a noninvasive way using magnetic resonance images: A single-center study.

Journal: Clinical neurology and neurosurgery
Published Date:

Abstract

OBJECTIVES: Ki67 is an important biomarker of pituitary adenoma (PA) aggressiveness. In this study, PA invasion of surrounding structures is investigated and deep learning (DL) models are established for preoperative prediction of Ki67 labeling index (Ki67LI) status using conventional magnetic resonance (MR) images.

Authors

  • Xu-Jun Shu
    Medical school of Chinese PLA, Beijing 100853, China; Department of Neurosurgery, The First Medical Centre of Chinese PLA General Hospital, Beijing 100853, China.
  • Hui Chang
    Department of Thoracic Surgery, No. 153 Hospital of Liberation Army, Zhengzhou, China.
  • Qun Wang
    Department of Thoracic Surgery, Zhongshan Hospital, Fudan University, Shanghai 200032, China.
  • Wu-Gang Chen
    School of Computer and Information Engineering, Henan University, Henan Province 475004, China.
  • Kai Zhao
    Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Bo-Yuan Li
    School of Computer and Information Engineering, Henan University, Henan Province 475004, China.
  • Guo-Chen Sun
    Department of Neurosurgery, The First Medical Centre of Chinese PLA General Hospital, Beijing 100853, China.
  • Sheng-Bo Chen
    School of Computer and Information Engineering, Henan University, Henan Province 475004, China. Electronic address: 10120125@vip.henu.edu.cn.
  • Bai-Nan Xu
    Department of Neurosurgery, The First Medical Centre of Chinese PLA General Hospital, Beijing 100853, China. Electronic address: xubain301@126.com.