Scientific Reports (Oct 2020)

Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images

  • Eric W. Prince,
  • Ros Whelan,
  • David M. Mirsky,
  • Nicholas Stence,
  • Susan Staulcup,
  • Paul Klimo,
  • Richard C. E. Anderson,
  • Toba N. Niazi,
  • Gerald Grant,
  • Mark Souweidane,
  • James M. Johnston,
  • Eric M. Jackson,
  • David D. Limbrick,
  • Amy Smith,
  • Annie Drapeau,
  • Joshua J. Chern,
  • Lindsay Kilburn,
  • Kevin Ginn,
  • Robert Naftel,
  • Roy Dudley,
  • Elizabeth Tyler-Kabara,
  • George Jallo,
  • Michael H. Handler,
  • Kenneth Jones,
  • Andrew M. Donson,
  • Nicholas K. Foreman,
  • Todd C. Hankinson

DOI
https://doi.org/10.1038/s41598-020-73278-8
Journal volume & issue
Vol. 10, no. 1
pp. 1 – 13

Abstract

Read online

Abstract Deep learning (DL) is a widely applied mathematical modeling technique. Classically, DL models utilize large volumes of training data, which are not available in many healthcare contexts. For patients with brain tumors, non-invasive diagnosis would represent a substantial clinical advance, potentially sparing patients from the risks associated with surgical intervention on the brain. Such an approach will depend upon highly accurate models built using the limited datasets that are available. Herein, we present a novel genetic algorithm (GA) that identifies optimal architecture parameters using feature embeddings from state-of-the-art image classification networks to identify the pediatric brain tumor, adamantinomatous craniopharyngioma (ACP). We optimized classification models for preoperative Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and combined CT and MRI datasets with demonstrated test accuracies of 85.3%, 83.3%, and 87.8%, respectively. Notably, our GA improved baseline model performance by up to 38%. This work advances DL and its applications within healthcare by identifying optimized networks in small-scale data contexts. The proposed system is easily implementable and scalable for non-invasive computer-aided diagnosis, even for uncommon diseases.