Detection of Cervical Vertebrae Using Object Detection and Semantic Segmentation Methods in Lateral Cephalometric Radiographs

Mazhar Kayaoğlu; Abdülkadir Şengür; Saadet Çınarsoy Ciğerim; Sabahattin Bor

Makale detayları

Detection of Cervical Vertebrae Using Object Detection and Semantic Segmentation Methods in Lateral Cephalometric Radiographs

Yazarlar:

Mazhar Kayaoğlu | Abdülkadir Şengür | Saadet Çınarsoy Ciğerim | Sabahattin Bor

Yayıncı:

Bingol University

Ana Başlıklar:

Karar Desteği ve Grup Destek Sistemleri

Dergi:

Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.26-36

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001352628

pISSN:

2149-6366

Anahtar kelimeler:

Özet:

 This study proposes an artificial intelligence-based method for the detection and semantic segmentation of C2, C3, and C4 cervical vertebrae in lateral cephalometric radiographs. The dataset comprises 2520 radiographs obtained from the Orthodontics Department of Van Yüzüncü Yıl University Faculty of Dentistry. In the initial stage, vertebral regions were identified using YOLOv8 and YOLOv11 object detection models, and these areas were meticulously annotated using QuPath software. The labelled data were then subjected to segmentation using advanced deep learning models such as Attention-UNet, Attention-ResUNet, SEEA-UNet, and ResAt-UNet. The study revealed that the object detection models achieved a high performance with an accuracy of 99.8. Among the segmentation models, Attention-ResUNet demonstrated the best performance with an accuracy of 99.25, while the ResAt-UNet model stood out with its balanced generalization capacity. The generated binary masks provided a reliable dataset for bone age estimation and skeletal maturity analysis. This study aims to reduce radiation exposure and streamline clinical workflows by eliminating the need for additional imaging. The findings indicate that AI-supported methods minimize errors caused by manual assessments and ensure standardization in skeletal analysis. It is anticipated that these methods could be widely utilized in orthodontic and pediatric medical applications in the future.

 This study proposes an artificial intelligence-based method for the detection and semantic segmentation of C2, C3, and C4 cervical vertebrae in lateral cephalometric radiographs. The dataset comprises 2520 radiographs obtained from the Orthodontics Department of Van Yüzüncü Yıl University Faculty of Dentistry. In the initial stage, vertebral regions were identified using YOLOv8 and YOLOv11 object detection models, and these areas were meticulously annotated using QuPath software. The labelled data were then subjected to segmentation using advanced deep learning models such as Attention-UNet, Attention-ResUNet, SEEA-UNet, and ResAt-UNet. The study revealed that the object detection models achieved a high performance with an accuracy of 99.8. Among the segmentation models, Attention-ResUNet demonstrated the best performance with an accuracy of 99.25, while the ResAt-UNet model stood out with its balanced generalization capacity. The generated binary masks provided a reliable dataset for bone age estimation and skeletal maturity analysis. This study aims to reduce radiation exposure and streamline clinical workflows by eliminating the need for additional imaging. The findings indicate that AI-supported methods minimize errors caused by manual assessments and ensure standardization in skeletal analysis. It is anticipated that these methods could be widely utilized in orthodontic and pediatric medical applications in the future.

 This study proposes an artificial intelligence-based method for the detection and semantic segmentation of C2, C3, and C4 cervical vertebrae in lateral cephalometric radiographs. The dataset comprises 2520 radiographs obtained from the Orthodontics Department of Van Yüzüncü Yıl University Faculty of Dentistry. In the initial stage, vertebral regions were identified using YOLOv8 and YOLOv11 object detection models, and these areas were meticulously annotated using QuPath software. The labelled data were then subjected to segmentation using advanced deep learning models such as Attention-UNet, Attention-ResUNet, SEEA-UNet, and ResAt-UNet. The study revealed that the object detection models achieved a high performance with an accuracy of 99.8. Among the segmentation models, Attention-ResUNet demonstrated the best performance with an accuracy of 99.25, while the ResAt-UNet model stood out with its balanced generalization capacity. The generated binary masks provided a reliable dataset for bone age estimation and skeletal maturity analysis. This study aims to reduce radiation exposure and streamline clinical workflows by eliminating the need for additional imaging. The findings indicate that AI-supported methods minimize errors caused by manual assessments and ensure standardization in skeletal analysis. It is anticipated that these methods could be widely utilized in orthodontic and pediatric medical applications in the future.

 Bu çalışmada, lateral sefalometrik radyografilerde C2, C3 ve C4 servikal vertebralarının tespiti ve semantik segmentasyonu için yapay zeka tabanlı bir yöntem önerilmektedir. Veriler, Van Yüzüncü Yıl Üniversitesi Diş Hekimliği Fakültesi Ortodonti Anabilim Dalından temin edilen 2520 radyografiden oluşmaktadır. İlk aşamada YOLOv8 ve YOLOv11 nesne algılama modelleri kullanılarak vertebra bölgeleri tespit edilmiş ve ardından bu alanlar QuPath yazılımı ile detaylı şekilde anotasyonlanmıştır. Etiketlenen veriler, Attention-UNet, Attention-ResUNet, SEEA-UNet ve ResAt-UNet gibi ileri seviye derin öğrenme modelleri kullanılarak segmentasyon işlemlerine tabi tutulmuştur. Çalışma, nesne algılama modellerinin 99,8 doğruluk oranıyla yüksek performans sergilediğini ortaya koymuştur. Segmentasyon modelleri arasında en iyi performansı 99,25 doğruluk oranı ile Attention-ResUNet gösterirken, ResAt-UNet modeli genelleme kapasitesindeki dengesiyle dikkat çekmiştir. Elde edilen ikili maskeler, kemik yaşı tahmini ve iskeletsel olgunluk analizi için güvenilir bir veri seti oluşturmuştur. Bu çalışma, ek görüntüleme ihtiyacını ortadan kaldırarak radyasyon maruziyetini azaltmayı ve klinik süreçleri hızlandırmayı amaçlamaktadır. Sonuçlar, yapay zeka destekli yöntemlerin manuel değerlendirme kaynaklı hataları en aza indirdiğini ve iskeletsel analizde standardizasyon sağladığını göstermektedir. Gelecekte, bu yöntemlerin ortodonti ve pediatrik tıbbi uygulamalarda yaygın olarak kullanılabileceği öngörülmektedir.

Makale detayları

Detection of Cervical Vertebrae Using Object Detection and Semantic Segmentation Methods in Lateral Cephalometric Radiographs

Yazarlar:

Mazhar Kayaoğlu | Abdülkadir Şengür | Saadet Çınarsoy Ciğerim | Sabahattin Bor

Yayıncı:

Bingol University

Ana Başlıklar:

Karar Desteği ve Grup Destek Sistemleri

Dergi:

Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.26-36

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001352628

pISSN:

2149-6366

Object detection

Semantic segmentation

ClassificationNesne Tespiti

Semantik Segmentasyon

Sınıflandırma

Sayı

Makale detayları

Detection of Cervical Vertebrae Using Object Detection and Semantic Segmentation Methods in Lateral Cephalometric Radiographs

Yazarlar: Mazhar Kayaoğlu | Abdülkadir Şengür | Saadet Çınarsoy Ciğerim | Sabahattin Bor

Yayıncı: Bingol University

Ana Başlıklar: Karar Desteği ve Grup Destek Sistemleri

Dergi: Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.26-36

Belge Tipi: Makale

Yayın Tarihi: 6/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001352628

pISSN: 2149-6366

Object detection

Semantic segmentation

ClassificationNesne Tespiti

Semantik Segmentasyon

Sınıflandırma

Sayı

Yazarlar:

Mazhar Kayaoğlu | Abdülkadir Şengür | Saadet Çınarsoy Ciğerim | Sabahattin Bor

Yayıncı:

Bingol University

Ana Başlıklar:

Karar Desteği ve Grup Destek Sistemleri

Dergi:

Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.26-36

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001352628

pISSN:

2149-6366