Deep learning in rare disease. Detection of tubers in tuberous sclerosis complex.

Journal: PloS one
Published Date:

Abstract

OBJECTIVE: To develop and test a deep learning algorithm to automatically detect cortical tubers in magnetic resonance imaging (MRI), to explore the utility of deep learning in rare disorders with limited data, and to generate an open-access deep learning standalone application.

Authors

  • Iván Sánchez Fernández
    1 Division of Epilepsy and Clinical Neurophysiology, Department of Neurology, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA.
  • Edward Yang
    Boston Children's Hospital, Harvard Medical School, Boston, MA, United States of America.
  • Paola Calvachi
    Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States of America.
  • Marta Amengual-Gual
    Boston Children's Hospital, Harvard Medical School, Boston, MA, United States of America.
  • Joyce Y Wu
    Mattel Children's Hospital, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, United States of America.
  • Darcy Krueger
    Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States of America.
  • Hope Northrup
    Division of Medical Genetics, Department of Pediatrics, McGovern Medical School at the University of Texas Health Science Center at Houston (UTHealth) and Children's Memorial Hermann Hospital, Houston, TX, USA.
  • Martina E Bebin
    University of Alabama at Birmingham, Birmingham, Alabama, United States of America.
  • Mustafa Sahin
    Rosamund Stone Zander Translational Neuroscience Center, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States.
  • Kun-Hsing Yu
    Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
  • Jurriaan M Peters
    Boston Children's Hospital and Harvard Medical School, Boston, Massachusetts 02115, USA.