Test-retest reproducibility of a deep learning–based automatic detection algorithm for the chest radiograph

The authors of this retrospective study performed test-retest reproducibility analyses for a deep learning-based automatic detection algorithm (DLAD) using two stationary chest radiographs with short-term intervals, in order to analyze influential factors on test-retest variations. The test, which included patients with pulmonary nodules resected in 2017, showed that DLAD was robust to the test-retest variation.

Key points

• The deep learning–based automatic detection algorithm was robust to the test-retest variation of the chest radiographs in general.
• The test-retest variation was negatively associated with solid portion size and good nodule conspicuity.
• High-specificity cutoff (46%) resulted in discordant classifications of 8.9% (15/169; p = 0.04) between the test-retest radiographs.

Article: Test-retest reproducibility of a deep learning–based automatic detection algorithm for the chest radiograph

Authors: Hyungjin Kim, Chang Min Park & Jin Mo Goo