Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG study

IntroductionCardiogenic pulmonary edema (CPE) is a serious complication of heart failure in dogs, commonly characterized by excess fluid within the lung interstitium and alveoli. Point-of-care ultrasound (POCUS) allows for the prompt identification of pulmonary alterations through the presence of B-...

Full description

Saved in:
Bibliographic Details
Main Authors: Aurélie Jourdan, Caroline Dania, Maxime Cambournac
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Veterinary Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fvets.2025.1647547/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850043835248279552
author Aurélie Jourdan
Aurélie Jourdan
Caroline Dania
Caroline Dania
Maxime Cambournac
Maxime Cambournac
author_facet Aurélie Jourdan
Aurélie Jourdan
Caroline Dania
Caroline Dania
Maxime Cambournac
Maxime Cambournac
author_sort Aurélie Jourdan
collection DOAJ
description IntroductionCardiogenic pulmonary edema (CPE) is a serious complication of heart failure in dogs, commonly characterized by excess fluid within the lung interstitium and alveoli. Point-of-care ultrasound (POCUS) allows for the prompt identification of pulmonary alterations through the presence of B-lines. However, interpretation remains subjective and operator dependent. Artificial intelligence (AI) may offer standardized, real-time analysis, but its application in veterinary medicine is largely unexplored.ObjectiveTo assess the performance of an AI-based ultrasound algorithm in detecting B-lines in dogs and to evaluate its agreement with manual quantification by experienced operators.MethodsIn this prospective study conducted at a single center, 40 dogs were enrolled: 20 with suspected CPE and 20 healthy controls. CPE suspicion was based on respiratory distress, a left atrium-to-aorta ratio (La:Ao) ≥1.6, >3 B-lines per field at thoracic POCUS, and clinical improvement following furosemide administration. Lung ultrasound was performed according to the Vet BLUE protocol. Cine loops were analyzed using the Butterfly Auto B-line Counter and reviewed independently by two POCUS-trained clinicians, each blinded to the AI results and to the other's evaluation.ResultsThe AI algorithm failed to provide a B-line count in 14.2% of cineloops overall, with failures occurring in 11.8% of the suspected CPE group and 2.4% of the non-CPE group. Quantification failures were significantly more frequent in the suspected CPE group (OR 4.88; p < 0.0001). Intraclass correlation coefficients showed excellent agreement for B-line counts (ICC = 0.88) and strong concordance for pathological classification (>3 B-lines; ICC = 0.85) between operators and AI. AI accuracy compared to clinicians was 84 and 86%.ConclusionThe AI algorithm demonstrated excellent agreement with experienced operators both for precise B-line counting and for the classification of pathological lung patterns. These findings support the potential of AI as a valuable decision-support tool for detecting clinically relevant cardiogenic pulmonary edema in veterinary critical care.
format Article
id doaj-art-919dd2aaa45344fba6d5919b31bacdfe
institution DOAJ
issn 2297-1769
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Veterinary Science
spelling doaj-art-919dd2aaa45344fba6d5919b31bacdfe2025-08-20T02:55:07ZengFrontiers Media S.A.Frontiers in Veterinary Science2297-17692025-08-011210.3389/fvets.2025.16475471647547Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG studyAurélie Jourdan0Aurélie Jourdan1Caroline Dania2Caroline Dania3Maxime Cambournac4Maxime Cambournac5Centre Hospitalier Vétérinaire Frégis, Paris, FranceIVC Evidensia France, Courbevoie, FranceCentre Hospitalier Vétérinaire Frégis, Paris, FranceIVC Evidensia France, Courbevoie, FranceCentre Hospitalier Vétérinaire Frégis, Paris, FranceIVC Evidensia France, Courbevoie, FranceIntroductionCardiogenic pulmonary edema (CPE) is a serious complication of heart failure in dogs, commonly characterized by excess fluid within the lung interstitium and alveoli. Point-of-care ultrasound (POCUS) allows for the prompt identification of pulmonary alterations through the presence of B-lines. However, interpretation remains subjective and operator dependent. Artificial intelligence (AI) may offer standardized, real-time analysis, but its application in veterinary medicine is largely unexplored.ObjectiveTo assess the performance of an AI-based ultrasound algorithm in detecting B-lines in dogs and to evaluate its agreement with manual quantification by experienced operators.MethodsIn this prospective study conducted at a single center, 40 dogs were enrolled: 20 with suspected CPE and 20 healthy controls. CPE suspicion was based on respiratory distress, a left atrium-to-aorta ratio (La:Ao) ≥1.6, >3 B-lines per field at thoracic POCUS, and clinical improvement following furosemide administration. Lung ultrasound was performed according to the Vet BLUE protocol. Cine loops were analyzed using the Butterfly Auto B-line Counter and reviewed independently by two POCUS-trained clinicians, each blinded to the AI results and to the other's evaluation.ResultsThe AI algorithm failed to provide a B-line count in 14.2% of cineloops overall, with failures occurring in 11.8% of the suspected CPE group and 2.4% of the non-CPE group. Quantification failures were significantly more frequent in the suspected CPE group (OR 4.88; p < 0.0001). Intraclass correlation coefficients showed excellent agreement for B-line counts (ICC = 0.88) and strong concordance for pathological classification (>3 B-lines; ICC = 0.85) between operators and AI. AI accuracy compared to clinicians was 84 and 86%.ConclusionThe AI algorithm demonstrated excellent agreement with experienced operators both for precise B-line counting and for the classification of pathological lung patterns. These findings support the potential of AI as a valuable decision-support tool for detecting clinically relevant cardiogenic pulmonary edema in veterinary critical care.https://www.frontiersin.org/articles/10.3389/fvets.2025.1647547/fullartificial intelligencelung ultrasoundB-lines detectioncanine pulmonary edemapoint of care ultrasound (POCUS)
spellingShingle Aurélie Jourdan
Aurélie Jourdan
Caroline Dania
Caroline Dania
Maxime Cambournac
Maxime Cambournac
Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG study
Frontiers in Veterinary Science
artificial intelligence
lung ultrasound
B-lines detection
canine pulmonary edema
point of care ultrasound (POCUS)
title Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG study
title_full Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG study
title_fullStr Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG study
title_full_unstemmed Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG study
title_short Sonographic machine-assisted recognition and tracking of B-lines in dogs: the SMARTDOG study
title_sort sonographic machine assisted recognition and tracking of b lines in dogs the smartdog study
topic artificial intelligence
lung ultrasound
B-lines detection
canine pulmonary edema
point of care ultrasound (POCUS)
url https://www.frontiersin.org/articles/10.3389/fvets.2025.1647547/full
work_keys_str_mv AT aureliejourdan sonographicmachineassistedrecognitionandtrackingofblinesindogsthesmartdogstudy
AT aureliejourdan sonographicmachineassistedrecognitionandtrackingofblinesindogsthesmartdogstudy
AT carolinedania sonographicmachineassistedrecognitionandtrackingofblinesindogsthesmartdogstudy
AT carolinedania sonographicmachineassistedrecognitionandtrackingofblinesindogsthesmartdogstudy
AT maximecambournac sonographicmachineassistedrecognitionandtrackingofblinesindogsthesmartdogstudy
AT maximecambournac sonographicmachineassistedrecognitionandtrackingofblinesindogsthesmartdogstudy