Diagnostic Efficiency of Various Systems for Automatic Analysis of Radiographs in the Detection of Lung Nodule

Abstract

The purpose of the study was to compare the effectiveness of various artificial intelligence systems for detecting foci and rounded lesions in the lungs. For testing, we selected four software products based on convolutional neural networks, positioning themselves as a sensitive system for evaluating digital chest radiographs. An analytical validation method was used for clinical evaluation. For diagnostics, 3 data samples were formed with the identification of signs of diseases (sample 1–5150 radiographs, detection of pathological changes 3 %; sample 2–100 radiographs, detection of pathological changes 6 %; sample 3–300 radiographs, detection of the prevalence of pathological changes 50 %). None of the software products passed the AUC threshold of 0.811 on all three samples. In all three samples, all software products have high accuracy and high sensitivity in detecting round formations, which leads to rare cases of overdiagnosis and special cases of underdiagnosis. The use of digital X-ray image analysis systems based on artificial intelligence technologies is a promising direction for high-quality diagnostics, primarily when considering their young radiologists as an additional opinion.