Artificial Intelligence-Assisted Lung Ultrasound for Pneumothorax: Diagnostic Accuracy Compared with CT in Emergency and Critical Care
Tomography · 30.10.2025 · 11 (11) · 121
DOI: 10.3390/tomography11110121 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Tomography, online erschienen am 30.10.2025. Verfasst von İsmail Dal und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thoracic Surgery, Faculty of Medicine, Kastamonu University, Kastamonu 37150, Turkey. Hauptthemen laut MEDLINE: Pneumothorax, Artificial Intelligence, Tomography, X-Ray Computed. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Pneumothorax (PTX) requires rapid recognition in emergency and critical care. Lung ultrasound (LUS) offers a fast, radiation-free alternative to computed tomography (CT), but its accuracy is limited by operator dependence. Artificial intelligence (AI) may standardize interpretation and improve performance.
Methods
This retrospective single-center study included 46 patients (23 with CT-confirmed PTX and 23 controls). Sixty B-mode and M-mode frames per patient were extracted using a Clarius C3 HD3 wireless device, yielding 2760 images. CT served as the diagnostic reference. Experimental studies were conducted within the framework of three scenarios. Transformer-based models, Vision Transformer (ViT) and DINOv2, were trained and tested under two scenarios: random frame split and patient-level split. Also, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) classifiers were trained on the feature maps extracted by using Video Vision Transformer (ViViT) for ultrasound video sequences in Scenario 3. Model performance was evaluated using accuracy, sensitivity, specificity, F1-score, and area under the ROC curve (AUC).
Results
Both transformers achieved high diagnostic accuracy, with B-mode images outperforming M-mode inputs in the first two scenarios. In Scenario 1, ViT reached 99.1% accuracy, while DINOv2 achieved 97.3%. In Scenario 2, which avoided data leakage, DINOv2 performed best in the B-mode region (90% accuracy, 80% sensitivity, 100% specificity, F1-score 88.9%). ROC analysis confirmed strong discriminative ability, with AUC values of 0.973 for DINOv2 and 0.964 for ViT on B-mode images. Also, both RF and XGBoost classifiers trained on the ViViT feature maps reached 90% accuracy on the video sequences.
Conclusions
AI-assisted LUS substantially improves PTX detection, with transformers—particularly DINOv2—achieving near-expert accuracy. Larger multicenter datasets are required for validation and clinical integration.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Thoracic Surgery, Faculty of Medicine, Kastamonu University, Kastamonu 37150, Turkey.
- Department of Computer Engineering, Faculty of Engineering and Architecture, Kastamonu University, Kastamonu 37150, Turkey.
ORCID-Profile: İsmail Dal, Kemal Akyol
Zitieren
APA
Dal, İ., & Akyol, K. (2025). Artificial Intelligence-Assisted Lung Ultrasound for Pneumothorax: Diagnostic Accuracy Compared with CT in Emergency and Critical Care. Tomography, 11(11), 121. https://doi.org/10.3390/tomography11110121
Vancouver
Dal İ, Akyol K. Artificial Intelligence-Assisted Lung Ultrasound for Pneumothorax: Diagnostic Accuracy Compared with CT in Emergency and Critical Care. Tomography. 2025;11(11):121. doi:10.3390/tomography11110121
BibTeX
@article{Dal2025,
author = {Dal, İsmail and Akyol, Kemal},
title = {Artificial Intelligence-Assisted Lung Ultrasound for Pneumothorax: Diagnostic Accuracy Compared with CT in Emergency and Critical Care},
journal = {Tomography},
year = {2025},
volume = {11},
number = {11},
pages = {121},
doi = {10.3390/tomography11110121}
}
EUVIMED