Development and Practical Implementation of a Deep Learning-Based Pipeline for Automated Pre- and Postoperative Glioma Segmentation.

Journal: AJNR. American journal of neuroradiology
PMID: 34857514

Abstract

BACKGROUND AND PURPOSE: Quantitative volumetric segmentation of gliomas has important implications for diagnosis, treatment, and prognosis. We present a deep-learning model that accommodates automated preoperative and postoperative glioma segmentation with a pipeline for clinical implementation. Developed and engineered in concert, the work seeks to accelerate clinical realization of such tools.

Authors

  • E Lotan
    Department of RadiologyNYU Grossman School of MedicineNew York, New York.
  • B Zhang
    Training Department, Third Military Medical University of Chinese PLA, Shapingba, Chongqing, China.
  • S Dogra
    From the Department of Radiology (E.L., B.Z., S.D., D.C., G.F., E.K.O., Y.W.L.).
  • W D Wang
    Population Health (W.D.W.).
  • D Carbone
    From the Department of Radiology (E.L., B.Z., S.D., D.C., G.F., E.K.O., Y.W.L.).
  • G Fatterpekar
    From the Department of Radiology (E.L., B.Z., S.D., D.C., G.F., E.K.O., Y.W.L.).
  • E K Oermann
    From the Department of Radiology (E.L., B.Z., S.D., D.C., G.F., E.K.O., Y.W.L.).
  • Y W Lui
    From the Department of Radiology (Y.W.L.), New York University Langone Medical Center, New York, New York.

Keywords

External Resources

Popular Topics
Recent Journals