Machine Learning Algorithm Detection of Confluent B-Lines

• Published in: Ultrasound in medicine & biology Vol. 49; no. 9; pp. 2095 - 2102
• Main Authors: Baloescu, Cristiana, Rucki, Agnieszka A., Chen, Alvin, Zahiri, Mohsen, Ghoshal, Goutam, Wang, Jing, Chew, Rita, Kessler, David, Chan, Daniela K.I., Hicks, Bryson, Schnittke, Nikolai, Shupp, Jeffrey, Gregory, Kenton, Raju, Balasundar, Moore, Christopher
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01.09.2023
• Subjects: Adult; Algorithms; Artificial intelligence; B-line; Humans; Lung - diagnostic imaging; Lung ultrasound; Machine Learning; Point-of-care ultrasound; Prospective Studies; Pulmonary Edema; Radiology; Ultrasonography - methods; Point-of-care ultrasound; B-line; Lung ultrasound; Artificial intelligence; Machine learning
• ISSN: 0301-5629; 1879-291X; 1879-291X
• DOI: 10.1016/j.ultrasmedbio.2023.05.016

B-lines are a ring-down artifact of lung ultrasound that arise with increased alveolar water in conditions such as pulmonary edema and infectious pneumonitis. Confluent B-line presence may signify a different level of pathology compared with single B-lines. Existing algorithms aimed at B-line counting do not distinguish between single and confluent B-lines. The objective of this study was to test a machine learning algorithm for confluent B-line identification. This study used a subset of 416 clips from 157 subjects, previously acquired in a prospective study enrolling adults with shortness of breath at two academic medical centers, using a hand-held tablet and a 14-zone protocol. After exclusions, random sampling generated a total of 416 clips (146 curvilinear, 150 sector and 120 linear) for review. A group of five experts in point-of-care ultrasound blindly evaluated the clips for presence/absence of confluent B-lines. Ground truth was defined as majority agreement among the experts and used for comparison with the algorithm. Confluent B-lines were present in 206 of 416 clips (49.5%). Sensitivity and specificity of confluent B-line detection by algorithm compared with expert determination were 83% (95% confidence interval [CI]: 0.77–0.88) and 92% (95% CI: 0.88–0.96). Sensitivity and specificity did not statistically differ between transducers. Agreement between algorithm and expert for confluent B-lines measured by unweighted κ was 0.75 (95% CI: 0.69–0.81) for the overall set. The confluent B-line detection algorithm had high sensitivity and specificity for detection of confluent B-lines in lung ultrasound point-of-care clips, compared with expert determination.