External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms.

Journal: JAMA oncology
Published Date:

Abstract

IMPORTANCE: A computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening.

Authors

  • Mattie Salim
    From the Departments of Pathology and Oncology (M.S., F.S.), Physiology and Pharmacology (K.D., P.L.), and Medical Epidemiology and Biostatistics (M.E.), Karolinska Institute, Stockholm, Sweden; Department of Radiology (M.S.) and Breast Radiology (F.S.), Karolinska University Hospital, Dalagatan 90, 113 43 Stockholm, Sweden; and the Department of Radiology, Capio Sankt Görans Hospital, Stockholm, Sweden (K.D.).
  • Erik Wåhlin
    Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Stockholm, Sweden.
  • Karin Dembrower
    Department of Oncology and Pathology, Karolinska Institute, Stockholm, Sweden.
  • Edward Azavedo
    Department of Oncology-Pathology, Karolinska Institute, Stockholm, Sweden.
  • Theodoros Foukakis
    Department of Oncology/Pathology, Karolinska Institutet, Stockholm, Sweden; Theme Cancer, Karolinska University Hospital, Stockholm, Sweden.
  • Yue Liu
    School of Athletic Performance, Shanghai University of Sport, Shanghai, China.
  • Kevin Smith
  • Martin Eklund
    Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden. Electronic address: martin.eklund@ki.se.
  • Fredrik Strand
    Department of Oncology and Pathology, Karolinska Institute, Stockholm, Sweden.