Deep learning predicts gene expression as an intermediate data modality to identify susceptibility patterns in Mycobacterium tuberculosis infected Diversity Outbred mice.

Journal: EBioMedicine
Published Date: May 14, 2021

Abstract

BACKGROUND: Machine learning sustains successful application to many diagnostic and prognostic problems in computational histopathology. Yet, few efforts have been made to model gene expression from histopathology. This study proposes a methodology which predicts selected gene expression values (microarray) from haematoxylin and eosin whole-slide images as an intermediate data modality to identify fulminant-like pulmonary tuberculosis ('supersusceptible') in an experimentally infected cohort of Diversity Outbred mice (n=77).

Authors

  • Thomas E Tavolara
    Center for Biomedical Informatics, Wake Forest School of Medicine, Winston-Salem, USA.
  • M K K Niazi
    Center for Biomedical Informatics, Wake Forest School of Medicine, 486 Patterson Avenue, Winston-Salem, NC 27101, United States. Electronic address: mniazi@wakehealth.edu.
  • Adam C Gower
    Department of Medicine, Boston University School of Medicine, 72 E. Concord St Evans Building, Boston, MA 02118, United States.
  • Melanie Ginese
    Department of Infectious Disease and Global Health, Tufts University Cummings School of Veterinary Medicine, 200 Westboro Rd., North Grafton, MA 01536, United States.
  • Gillian Beamer
    Department of Infectious Disease and Global Health, Tufts University Cummings School of Veterinary Medicine, 200 Westboro Rd., North Grafton, MA 01536, United States.
  • Metin N Gurcan
    Department of Biomedical Informatics, The Ohio State University, Columbus, OH 43210, USA. Electronic address: metin.gurcan@osumc.edu.

Keywords

External Resources

Popular Topics
Recent Journals