Scalable deep learning algorithm to compute percent pulmonary contusion among patients with rib fractures.

Journal: The journal of trauma and acute care surgery
PMID: 35319542

Abstract

BACKGROUND: Pulmonary contusion exists along a spectrum of severity, yet is commonly binarily classified as present or absent. We aimed to develop a deep learning algorithm to automate percent pulmonary contusion computation and exemplify how transfer learning could facilitate large-scale validation. We hypothesized that our deep learning algorithm could automate percent pulmonary contusion computation and that greater percent contusion would be associated with higher odds of adverse inpatient outcomes among patients with rib fractures.

Authors

  • Jeff Choi
    From the Division of General Surgery (J.C., K.M., D.I.H., J.D.F.), Department of Surgery, Department of Biomedical Data Science (J.C.), Stanford University; Program in Epithelial Biology (N.Y.L.), Stanford University School of Medicine; and Department of Computer Science (A.P., K.C.), Stanford University, Stanford, California.
  • Katherine Mavrommati
  • Nancy Yanzhe Li
  • Advait Patil
    2Department of Neurosurgery, Harvard Medical School, Cambridge, Massachusetts.
  • Karen Chen
  • David I Hindin
  • Joseph D Forrester

Keywords

External Resources

Popular Topics
Recent Journals