An interpretable machine learning model for predicting bone marrow invasion in patients with lymphoma via F-FDG PET/CT: a multicenter study.

Journal: BMC medical informatics and decision making
Published Date: Jul 15, 2025

Abstract

PURPOSE: Accurate identification of bone marrow invasion (BMI) is critical for determining the prognosis of and treatment strategies for lymphoma. Although bone marrow biopsy (BMB) is the current gold standard, its invasive nature and sampling errors highlight the necessity for noninvasive alternatives. We aimed to develop and validate an interpretable machine learning model that integrates clinical data, F-fluorodeoxyglucose positron emission tomography/computed tomography (F-FDG PET/CT) parameters, radiomic features, and deep learning features to predict BMI in lymphoma patients.

Authors

  • Xinyu Zhu
  • Denglu Lu
    Department of Nuclear Medicine, Liuzhou Workers' Hospital, Liuzhou, 545000, Guangxi Zhuang Autonomous Region, People's Republic of China.
  • Yang Wu
  • Yanqi Lu
    Department of Nuclear Medicine, The First Affiliated Hospital of Guilin Medical University, Guilin, Guangxi Zhuang Autonomous Region, 541001, China.
  • Liang He
    Cancer Biology Research Center (Key Laboratory of the Ministry of Education), Tongji Medical College, Tongji Hospital, Huazhong University of Science and Technology, Wuhan, China.
  • Yanyun Deng
    Department of Nuclear Medicine, Liuzhou Workers' Hospital, Liuzhou, 545000, Guangxi Zhuang Autonomous Region, People's Republic of China.
  • Xingyu Mu
    Department of Radiology, Guangxi Medical University Cancer Hospital, Guangxi Clinical Research Center for Imaging Medicine, Guangxi Clinical Key Specialty (Medical Imaging), Key Discipline Development Program (Medical Imaging), Affiliated Cancer Hospital of Guangxi Medical University, Nanning, China.
  • Wei Fu
    Department of Information Security, Naval University of Engineering, Wuhan, China.

Keywords

External Resources

Popular Topics
Recent Journals