Deep Learning Algorithm Aids in Reticular Opacity Detection in Interstitial Lung Disease Patients
A deep learning algorithm (DLA), when applied to interstitial lung disease (ILD) patients, has been found to outperform readers in detecting reticular opacity, DLA assistance improved reader performance and interobserver agreement, and benefits were maintained in mild disease, through the benefit of DLA was greater in terms of sensitivity than specificity, in a study published in the American Journal of Roentgenology.
“Interobserver agreement was moderate (κ=0.517) for readers alone versus almost perfect (κ=0.870) for readers with DLA. Sensitivity, specificity, and accuracy for reticular opacity for DLA were 98.0%, 99.0%, and 98.5%; for pooled readers alone were 77.3%, 92.3%, and 84.8%; and for readers with DLA were 93.8%, 97.3%, and 95.6%. All metrics were significantly better (all p≤.002) for DLA and for readers with DLA compared with readers alone. Sensitivity for readers without and with DLA were 66.7% and 86.8% in mild disease, 84.2% and 98.8% in moderate disease, and 87.3% and 100.0% in severe disease. DLA exhibited 100.0% accuracy in the cases from the second center,” wrote first author Dr. Wooil Kim, corresponding author Dr. Sang Min Lee, and colleagues from the Asian Medical Center in Seoul, South Korea.
The retrospective study included 197 patients and 197 randomly selected age- and sex-matched controls with “surgically proven ILD between January 2017 and December 2018 who underwent preoperative chest radiograph and chest CT within a 30-day interval,” according to the team.
Wooil, et. al., suggested that “Use of DLA may facilitate detection of reticular opacity on chest radiograph in the early stages of ILD.”
Wooil Kim, Sang Min Lee, Jung Im Kim, Yura Ahn, Sohee Park, Jooae Choe, and Joon Beom Seo. Utility of a Deep Learning Algorithm for Detection of Reticular Opacity on Chest Radiograph in Patients with Interstitial Lung Disease. American Journal of Roentgenology. Available online October 20, 2021, at https://www.ajronline.org/doi/10.2214/AJR.21.26682. Accessed November 8, 2021.