In European journal of radiology ; h5-index 47.0
PURPOSE : We aimed to evaluate the performance of a fully automated quantitative software in detecting interstitial lung abnormalities (ILA) according to the Fleischner Society guidelines on routine chest CT compared with radiologists' visual analysis.
METHOD : This retrospective single-centre study included participants with ILA findings and 1:2 matched controls who underwent routine chest CT using various CT protocols for health screening. Two thoracic radiologists independently reviewed the CT images using the Fleischner Society guidelines. We developed a fully automated quantitative tool for detecting ILA by modifying deep learning-based quantification of interstitial lung disease and evaluated its performance using the radiologists' consensus for ILA as a reference standard.
RESULTS : A total of 336 participants (mean age, 70.5 ± 6.1 years; M:F = 282:54) were included. Inter-reader agreements were substantial for the presence of ILA (weighted κ, 0.74) and fair for its subtypes (weighted κ, 0.38). The quantification system for identifying ILA using a threshold of 5 % in at least one zone showed 67.6 % sensitivity, 93.3 % specificity, and 90.5 % accuracy. Eight of 20 (40 %) false positives identified by the system were underestimated by readers for ILA extent. Contrast-enhancement in a certain vendor and suboptimal inspiration caused a true false-positive on the system (all P < 0.05). The best cut-off value of abnormality extent detecting ILA on the system was 3.6 % (sensitivity, 84.8 %; specificity 92.4 %).
CONCLUSIONS : Inter-reader agreement was substantial for ILA but only fair for its subtypes. Applying an automated quantification system in routine clinical practice may aid the objective identification of ILA.
Kim Min Seon, Choe Jooae, Hwang Hye Jeon, Lee Sang Min, Yun Jihye, Kim Namkug, Ko Myung-Su, Yi Jaeyoun, Yu Donghoon, Seo Joon Beom
2022-Oct-17
Deep learning, Interstitial lung abnormality, Interstitial lung disease, Quantification
