Inconsistent Performance of Deep Learning Models on Mammogram Classification.

Journal: Journal of the American College of Radiology : JACR
Published Date:

Abstract

OBJECTIVES: Performance of recently developed deep learning models for image classification surpasses that of radiologists. However, there are questions about model performance consistency and generalization in unseen external data. The purpose of this study is to determine whether the high performance of deep learning on mammograms can be transferred to external data with a different data distribution.

Authors

  • Xiaoqin Wang
  • Gongbo Liang
    Department of Computer Science, University of Kentucky, Lexington, Kentucky.
  • Yu Zhang
    College of Marine Electrical Engineering, Dalian Maritime University, Dalian, China.
  • Hunter Blanton
    Department of Computer Science, University of Kentucky, Lexington, Kentucky.
  • Zachary Bessinger
    Department of Computer Science, University of Kentucky, Lexington, Kentucky.
  • Nathan Jacobs