Back to all publications
  • AI/ML

CANDI: An R Package and Shiny App for Annotating Radiographs and Evaluating Computer-Aided Diagnosis

Marcus A. Badgeley, Manway Liu, Benjamin S. Glicksberg, Mark Shervey, John R. Zech, Khader Shameer, Joseph Lehar, Eric K. Oermann, Michael V. McConnell, Thomas M. Snyder, Joel T. Dudley

Abstract/Background

Radiologists have used algorithms for Computer-Aided Diagnosis (CAD) for decades. These algorithms use machine learning with engineered features, and there have been mixed findings on whether they improve radiologists’ interpretations. Deep learning offers superior performance but requires more training data and has not been evaluated in joint algorithm-radiologist decision systems.

Next Publication
Deep Learning Predicts Hip Fracture Using Confounding Patient and Healthcare Variables