[Skip to Navigation]
Sign In
From the JAMA Network
March 2018

Not Just Digital Pathology, Intelligent Digital Pathology

Author Affiliations
  • 1Department of Pathology, Yale University School of Medicine, New Haven, Connecticut
JAMA Oncol. 2018;4(3):403-404. doi:10.1001/jamaoncol.2017.5449

The promise of digital pathology is not the simple transfer of an image from a glass slide to a monitor, nor even the flexibility of distribution and modification of the image, but rather the potential to augment the pathologist’s eye with information/intelligence that cannot be gleaned by human examination. Although automated analysis of immunohistochemistry (IHC) has exceeded human capability to measure expression, to date, that machine-derived data has not changed patient care. However, the emergence of deep learning algorithms (a machine learning method, eg, convolutional neural networks) may soon change this equation.

Add or change institution