Implementation of a deep learning–based computer-aided detection system in clinical practice improved the diagnostic performance for detecting pneumothorax on follow-up chest radiographs after perc... Background Accurate detection of pneumothorax on chest radiographs, the most common complication of percutaneous transthoracic needle biopsies (PTNBs), is not always easy in practice. A computer-ai...

Hong W, et al. Korean J Radiol. 2021 Apr;22:e48. https://doi.org/10.3348/kjr.2020.1229

This study aimed to assess the technical performance of ElastQ Imaging compared with ElastPQ and to investigate the correlation between liver stiffness (LS) values obtained using these two techniques. This retrospective study included 249 patients who underwent LS measurements using both ElastPQ and ElastQ Imaging equipped on the same machine. The applicability, repeatability (coefficient of variation [CV]), acquisition time, and LS values were compared using the chi-square or Wilcoxon signed-rank tests. In the development group, the correlation between the LS values obtained by the two techniques was assessed with Spearman correlation coefficients and linear regression analysis. In the validation group, the agreement between the estimated and real LS values was evaluated using a Bland-Altman plot. ElastQ Imaging had higher applicability (94.0% vs. 78.3%, P<0.001) and higher repeatability, with a lower median CV (0.127 vs. 0.164, P<0.001) than did ElastPQ. The median acquisition time of ElastQ Imaging was significantly shorter than that of ElastPQ (45.5 seconds vs. 96.5 seconds, P<0.001). The median LS value obtained using ElastQ Imaging was significantly higher than that obtained using ElastPQ (5.60 kPa vs. 5.23 kPa, P<0.001). The LS values between the two techniques exhibited a strong positive correlation (r=0.851, P<0.001) in the development group. The mean difference and 95% limits of agreement were 0.0 kPa (-3.9 to 3.9 kPa) in the validation group. ElastQ Imaging may be more reliable and faster than ElastPQ, with strongly correlated LS measurements.

Hong W, et al. Korean J Radiol. 2019 Apr;20(4):599-608. https://doi.org/10.3348/kjr.2018.0557

Jeong WG, et al. Korean J Radiol. 2025 Sep;26:e75. https://doi.org/10.3348/kjr.2025.0457

Objective: Prior studies on models based on deep learning (DL) and measuring the cardiothoracic ratio (CTR) on chest radiographs have lacked rigorous agreement analyses with radiologists or reader tests. We validated the performance of a commercially available DL-based CTR measurement model with various thoracic pathologies, and performed agreement analyses with thoracic radiologists and reader tests using a probabilistic-based reference. Materials and Methods: This study included 160 posteroanterior view chest radiographs (no lung or pleural abnormalities, pneumothorax, pleural effusion, consolidation, and n = 40 in each category) to externally test a DL-based CTR measurement model. To assess the agreement between the model and experts, intraclass or interclass correlation coefficients (ICCs) were compared between the model and two thoracic radiologists. In the reader tests with a probabilistic-based reference standard (Dawid–Skene consensus), we compared diagnostic measures—including sensitivity and negative predictive value (NPV)—for cardiomegaly between the model and five other radiologists using the non-inferiority test. Results: For the 160 chest radiographs, the model measured a median CTR of 0.521 (interquartile range, 0.446–0.59) and a mean CTR of 0.522 ± 0.095. The ICC between the two thoracic radiologists and between the model and two thoracic radiologists was not significantly different (0.972 versus 0.959, p = 0.192), even across various pathologies (all p-values > 0.05). The model showed non-inferior diagnostic performance, including sensitivity (96.3% versus 97.8%) and NPV (95.6% versus 97.4%) (p < 0.001 in both), compared with the radiologists for all 160 chest radiographs. However, it showed inferior sensitivity in chest radiographs with consolidation (95.5% versus 99.9%; p = 0.082) and NPV in chest radiographs with pleural effusion (92.9% versus 94.6%; p = 0.079) and consolidation (94.1% versus 98.7%; p = 0.173). Conclusion: While the sensitivity and NPV of this model for diagnosing cardiomegaly in chest radiographs with consolidation or pleural effusion were not as high as those of the radiologists, it demonstrated good agreement with the thoracic radiologists in measuring the CTR across various pathologies.