Automatic B-lines quantification with lung ultrasound in mechanically ventilated patients
7 affiliations
- 1Department of Anesthesia and Intensive Care, ASST Santi Paolo e Carlo, San Paolo University Hospital Milan, Italy
- 2Division of Respiratory Diseases, ASST Fatebenefratelli-Sacco, L. Sacco University Hospital Milan, Italy
- 3Department of Biomedical and Clinical Sciences, Università degli Studi di Milano, Milano, Italy
- 4Department of Radiology, Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico University Hospital Milan, Italy
- 5Department of Health Sciences, University of Milan, Italy
- 6Operative Unit of Radiology Department, Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico University Hospital Milan, Italy
- 7Coordinated Research Center on Respiratory Failure, University of Milan, Italy
Abstract
Background: If ultrasound dedicated software for the identification and quantification of interstitial syndrome is equal or superior to experts observation is still being explored. The primary objective of this study was to compare the performance of an automatic method based on a dedicated software algorithm with that of expert clinicians in terms of B-lines quantification.
Methods: Adult patients with acute respiratory failure who were deeply sedated, paralysed and mechanically ventilated were prospectively enrolled within 48 hours from ICU admission and underwent lung ultrasound by a trained physician. For each patient, 12 clips were stored, one for each thoracic region. The clips were then analyzed automatically using a built-in automatic recognition system and visually by two experts. A score of 0 was assigned if fewer than two B-lines were detected, a score of 1 if three or more B-lines were detected and a score of 2 if coalescent B-lines were detected.
Results: A total of 40 patients were included in the study. Out of the 480 clips analysed, 54.2% had a lung score of 0, 6.8% had a lung score of 1, 8.8% had a lung score of 2 and 20.2% had a lung score of 3. The agreement between the experts in detecting the scores 0, 1, 2 was excellent (ICC = 0.82) in 383 (79.8%) clips. The agreement between the automatic system and the experts was poor (ICC = 0.33), with a significant difference (p < 0.001).
Conclusions: In mechanically ventilated patients with acute respiratory failure, an automatic B-lines quantification system did not present an acceptable accuracy compared to expert consensus for B-lines counting, probably due to the coexistence of consolidation and pleural effusion.
Related
- Diaphragmatic Rapid Shallow Breathing Index Versus Diaphragmatic Thickness Fraction for Predicting Weaning Success in Mechanically Ventilated Patients
- Postextubation Stridor: An Analysis of Incidence, Risk Factors, and Clinical Outcomes in Mechanically Ventilated Patients
- Assessing the Influence of Propofol Sedation Versus Propofol-Free Sedation on Recovery From Sepsis and Septic Shock in Mechanically Ventilated ICU Patients: A Retrospective, Propensity-Score Matched, Cohort Study
- Modified Allen's Test versus Barbeau Test for Estimating Hands' Collateral Circulation before Radial Artery Puncture for Mechanically Ventilated Patients
- Effect of Endotracheal Tube Care Strategies on Accidental Extubation among Mechanically Ventilated Patients
BibTeX
@article{ciabattoni2026automatic,
title = {{Automatic B-lines quantification with lung ultrasound in mechanically ventilated patients}},
author = {Arianna Ciabattoni and Dejan Radovanovic and Tommaso Pozzi and Martina Gurgitano and Gianpaolo Carrafiello and Alessandro Monte and Silvia Coppola and Davide Chiumello},
journal = {Multidisciplinary Respiratory Medicine},
year = {2026},
month = sep,
doi = {10.5826/mrm.2026.1069},
url = {https://doi.org/10.5826/mrm.2026.1069},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - Automatic B-lines quantification with lung ultrasound in mechanically ventilated patients
AU - Arianna Ciabattoni
AU - Dejan Radovanovic
AU - Tommaso Pozzi
AU - Martina Gurgitano
AU - Gianpaolo Carrafiello
AU - Alessandro Monte
AU - Silvia Coppola
AU - Davide Chiumello
PY - 2026
DA - 2026/09/01
JO - Multidisciplinary Respiratory Medicine
DO - 10.5826/mrm.2026.1069
UR - https://doi.org/10.5826/mrm.2026.1069
AB - Background: If ultrasound dedicated software for the identification and quantification of interstitial syndrome is equal or superior to experts observation is still being explored. The primary objective of this study was to compare the performance of an automatic method based on a dedicated software algorithm with that of expert clinicians in terms of B-lines quantification. Methods: Adult patients with acute respiratory failure who were deeply sedated, paralysed and mechanically ventilated were prospectively enrolled within 48 hours from ICU admission and underwent lung ultrasound by a trained physician. For each patient, 12 clips were stored, one for each thoracic region. The clips were then analyzed automatically using a built-in automatic recognition system and visually by two experts. A score of 0 was assigned if fewer than two B-lines were detected, a score of 1 if three or more B-lines were detected and a score of 2 if coalescent B-lines were detected. Results: A total of 40 patients were included in the study. Out of the 480 clips analysed, 54.2% had a lung score of 0, 6.8% had a lung score of 1, 8.8% had a lung score of 2 and 20.2% had a lung score of 3. The agreement between the experts in detecting the scores 0, 1, 2 was excellent (ICC = 0.82) in 383 (79.8%) clips. The agreement between the automatic system and the experts was poor (ICC = 0.33), with a significant difference (p < 0.001). Conclusions: In mechanically ventilated patients with acute respiratory failure, an automatic B-lines quantification system did not present an acceptable accuracy compared to expert consensus for B-lines counting, probably due to the coexistence of consolidation and pleural effusion.
SN - 1828-695X
SN - 2049-6958
ER -