Automatic Identification of Adenoid Hypertrophy via Ensemble Deep Learning Models Employing X-ray Adenoid Images

dc.contributor.authorOrenc, Sedat
dc.contributor.authorAcar, Emrullah
dc.contributor.authorOzerdem, Mehmet Sirac
dc.contributor.authorSahin, Sefer
dc.contributor.authorKaya, Abdullah
dc.date.accessioned2025-02-22T14:09:07Z
dc.date.available2025-02-22T14:09:07Z
dc.date.issued2025
dc.departmentDicle Üniversitesien_US
dc.description.abstractAdenoid hypertrophy, characterized by the abnormal enlargement of adenoid tissue, is a condition that can cause significant breathing and sleep disturbances, particularly in children. Accurate diagnosis of adenoid hypertrophy is critical, yet traditional methods, such as imaging and manual interpretation, are prone to errors. This study uses an ensemble deep learning-based approach for adenoid classification. It utilizes a unique dataset sourced from Batman Training and Research Hospital. The dataset is composed of masked and non-masked X-ray images. It is used to train and compare the performance of multiple convolutional neural network (CNN) models. By comparing classification accuracy between masked and non-masked datasets, the study reveals the importance of image preprocessing. Six deep learning models-EfficientNet, MobileNet, ResNet50, ResNet152, VGG16, and Xception-are tested, with ResNet50 achieving the highest accuracy (100% on masked images), while Xception performs the worst (65% F1-score). The results indicate that masking significantly enhances the accuracy and reliability of adenoid classification. ResNet50 and EfficientNet show strong generalization capabilities. Conversely, the lower performance of models like Xception highlights the variability in model suitability for this task. This research provides valuable insights into optimizing deep learning models for medical image classification and it advances the field of AI-based adenoid detection.en_US
dc.description.sponsorshipBatman Training and Research Hospital [680423]; Dicle University's Engineering; Natural Sciences Ethics Committee [680423]en_US
dc.description.sponsorshipThis work was supported by the Batman Training and Research Hospital, and we would like to express our deepest gratitude to Dicle University's Engineering and Natural Sciences Ethics Committee for their approval and support of our research (Project Number 680423). Special thanks are due to Prof. Dr. Mehmet Sirac Ozerdem for his guidance throughout the research and to the university's faculty for providing invaluable resources and facilities for this project. We also extend our sincere appreciation to the medical staff and technical experts who contributed to the data collection and analysis.en_US
dc.identifier.doi10.1007/s10278-025-01423-8
dc.identifier.issn2948-2925
dc.identifier.issn2948-2933
dc.identifier.pmid39885079en_US
dc.identifier.urihttps://doi.org/10.1007/s10278-025-01423-8
dc.identifier.urihttps://hdl.handle.net/11468/29798
dc.identifier.wosWOS:001409441900001en_US
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakPubMed
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofJournal of Imaging Informatics in Medicineen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmzKA_WOS_20250222
dc.subjectImage processingen_US
dc.subjectAdenoid classificationen_US
dc.subjectEnsemble deep learning modelen_US
dc.titleAutomatic Identification of Adenoid Hypertrophy via Ensemble Deep Learning Models Employing X-ray Adenoid Imagesen_US
dc.typeArticleen_US

Dosyalar