Automated identification of chest radiographs with referable abnormality with deep learning: need for recalibration.
Journal:
European radiology
Published Date:
Jul 14, 2020
Abstract
OBJECTIVES: To evaluate the calibration of a deep learning (DL) model in a diagnostic cohort and to improve model's calibration through recalibration procedures.
Authors
Keywords
Adult
Aged
Algorithms
Area Under Curve
Bayes Theorem
Calibration
Deep Learning
Diagnosis, Computer-Assisted
Female
Humans
Image Processing, Computer-Assisted
Lung
Male
Middle Aged
Pattern Recognition, Automated
Predictive Value of Tests
Radiography, Thoracic
Reference Standards
Reproducibility of Results
Retrospective Studies
ROC Curve