Deep Transfer Learning and Radiomics Feature Prediction of Survival of Patients with High-Grade Gliomas.

Journal: AJNR. American journal of neuroradiology
Published Date:

Abstract

BACKGROUND AND PURPOSE: Patient survival in high-grade glioma remains poor, despite the recent developments in cancer treatment. As new chemo-, targeted molecular, and immune therapies emerge and show promising results in clinical trials, image-based methods for early prediction of treatment response are needed. Deep learning models that incorporate radiomics features promise to extract information from brain MR imaging that correlates with response and prognosis. We report initial production of a combined deep learning and radiomics model to predict overall survival in a clinically heterogeneous cohort of patients with high-grade gliomas.

Authors

  • W Han
    Department of Orthopaedics and Traumatology, Beijing Jishuitan Hospital, Beijing 100035, China.
  • L Qin
    Department of Imaging (L.Q., G.Y.), Dana-Farber Cancer Institute, Boston, Massachusetts.
  • C Bay
    From the Department of Radiology (W.H., C.B., X.C., N.M., A.L., X.X., G.Y.), Brigham and Women's Hospital, Boston, Massachusetts.
  • X Chen
    Division of Infectious Diseases,The People's Hospital of Meizhou,Meizhou,China.
  • K-H Yu
    Harvard Medical School (W.H., L.Q., C.B., K.-H.Y., N.M., X.X., G.Y.), Boston, Massachusetts.
  • N Miskin
    From the Department of Radiology (W.H., C.B., X.C., N.M., A.L., X.X., G.Y.), Brigham and Women's Hospital, Boston, Massachusetts.
  • A Li
    From the Department of Radiology (W.H., C.B., X.C., N.M., A.L., X.X., G.Y.), Brigham and Women's Hospital, Boston, Massachusetts.
  • X Xu
    From the Department of Radiology (W.H., C.B., X.C., N.M., A.L., X.X., G.Y.), Brigham and Women's Hospital, Boston, Massachusetts.
  • G Young
    From the Department of Radiology (W.H., C.B., X.C., N.M., A.L., X.X., G.Y.), Brigham and Women's Hospital, Boston, Massachusetts gsyoung@bwh.harvard.edu.