Classification of Atelectasis from Chest X-Ray Images Using Deep Learning Approaches
Muş Alparslan Üniversitesi Fen Bilimleri Dergisi · 27.06.2026 · 14 (1) · 84-94
DOI: 10.18586/msufbd.1877734 ↗Kurz gefasst
Fachartikel in der Zeitschrift Muş Alparslan Üniversitesi Fen Bilimleri Dergisi, online erschienen am 27.06.2026. Verfasst von Ömer Faruk Gök und 2 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Gefördert von: the Scientific and Technical Research Council of Turkey.
Abstract (Originalsprache)
Atelectasis, the partial or complete collapse of the lung, requires early diagnosis for effective treatment. This study investigates the effects of Region of Interest (ROI) cropping and transfer learning on the automatic classification of atelectasis from chest X-ray images. Four SqueezeNet-based models were developed using two image types (raw and cropped lung regions) and two training strategies (from-scratch and transfer learning). Models I and II were trained from scratch on raw and cropped images, respectively, while Models III and IV employed transfer learning on the same image sets. Performance was evaluated using standard classification metrics. Model IV, combining transfer learning and ROI-cropped images, achieved the best performance, with 98.43% accuracy, 0.984 F1-score, and 0.999 AUC. It also reached 0.9861 precision, 0.9828 sensitivity, and 0.9859 specificity. ROI-based cropping consistently improved classification performance. Combining transfer learning with ROI-focused preprocessing significantly enhances atelectasis detection and shows promise as a reliable clinical decision-support approach.
Förderung
- the Scientific and Technical Research Council of Turkey
Zitieren
APA
Gök, Ö. F., Doganay, F., & Abut, S. (2026). Classification of Atelectasis from Chest X-Ray Images Using Deep Learning Approaches. Muş Alparslan Üniversitesi Fen Bilimleri Dergisi, 14(1), 84-94. https://doi.org/10.18586/msufbd.1877734
Vancouver
Gök ÖF, Doganay F, Abut S. Classification of Atelectasis from Chest X-Ray Images Using Deep Learning Approaches. Muş Alparslan Üniversitesi Fen Bilimleri Dergisi. 2026;14(1):84-94. doi:10.18586/msufbd.1877734
BibTeX
@article{Gk2026,
author = {Gök, Ömer Faruk and Doganay, Fatih and Abut, Serdar},
title = {Classification of Atelectasis from Chest X-Ray Images Using Deep Learning Approaches},
journal = {Muş Alparslan Üniversitesi Fen Bilimleri Dergisi},
year = {2026},
volume = {14},
number = {1},
pages = {84--94},
doi = {10.18586/msufbd.1877734}
}
EUVIMED