Artificial Intelligence-Assisted Lung Ultrasound for Pneumothorax: Diagnostic Accuracy Compared with CT in Emergency and Critical Care
Yazarlar (2)
Ismail Dal
Kastamonu Üniversitesi, Türkiye
Kastamonu Üniversitesi, Türkiye
Prof. Dr. Kemal AKYOL Kastamonu Üniversitesi, Türkiye
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Tomography (Q2) | ||
| Dergi ISSN | 2379-1381 Dergi Bilgileri (2025) | ||
| Dergi Tarandığı Indeksler | SCI-Expanded | ||
| Makale Dili | İngilizce | Basım Tarihi | 10-2025 |
| Kabul Tarihi | – | Yayınlanma Tarihi | 30-10-2025 |
| Cilt / Sayı / Sayfa | 11 / 11 / 1–23 | DOI | 10.3390/tomography11110121 |
| Makale Linki | https://www.mdpi.com/2379-139X/11/11/121 | ||
| UAK Araştırma Alanları |
Radyoloji
|
||
| Özet |
| Simple Summary Pneumothorax is a life-threatening condition that requires rapid and accurate diagnosis, especially in emergency and critical care settings. Although lung ultrasound (LUS) offers a fast and radiation-free diagnostic option, its accuracy can vary depending on the operator’s experience. This study evaluated the potential of artificial intelligence (AI) to assist clinicians by automatically detecting pneumothorax on LUS images and videos. Using transformer-based deep learning models, we compared the diagnostic performance of Vision Transformer (ViT), DINOv2, and Video Vision Transformer (ViViT) architectures. When tested on data from different patients, the DINOv2 model achieved 90% accuracy, demonstrating reliable generalization without overfitting. Furthermore, when video sequences were analyzed, both Random Forest and eXtreme Gradient Boosting classifiers trained on ViViT-derived features achieved 90% accuracy, showing that AI can effectively interpret dynamic pleural motion. These results indicate that transformer-based AI can enhance pneumothorax diagnosis by improving consistency and reducing operator dependence, supporting broader use of lung ultrasound in emergency and point-of-care environments. Abstract 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 … |
| Anahtar Kelimeler |
| artificial intelligence | diagnostic imaging | emergency service | pneumothorax | point-of-care systems | ultrasonography |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Google Scholar | 1 |