Convolutional Neural Network Performance for Sella Turcica Segmentation and Classification Using CBCT Images
Şuayip Burak Duman,
Ali Z. Syed,
Duygu Celik Ozen,
İbrahim Şevki Bayrakdar,
Hassan S. Salehi,
Ahmed Abdelkarim,
Özer Celik,
Gözde Eser,
Oğuzhan Altun,
Kaan Orhan
Affiliations
Şuayip Burak Duman
Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Inonu University, 44210 Malatya, Turkey
Ali Z. Syed
Department of Oral and Maxillofacial Medicine and Diagnostic Sciences, School of Dental Medicine, Case Western Reserve University, Cleveland, OH 44106, USA
Duygu Celik Ozen
Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Inonu University, 44210 Malatya, Turkey
İbrahim Şevki Bayrakdar
Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskişehir Osmangazi University, 26040 Eskişehir, Turkey
Hassan S. Salehi
Department of Electrical and Computer Engineering, California State University, Chico, CA 95929, USA
Ahmed Abdelkarim
Department of Oral and Maxillofacial Radiology, University of Texas Health Sciences Center at San Antonio, San Antonio, TX 79229, USA
Özer Celik
Department of Center of Research and Application for Computer Aided Diagnosis and Treatment in Health, Eskişehir Osmangazi University, 26040 Eskişehir, Turkey
Gözde Eser
Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Inonu University, 44210 Malatya, Turkey
Oğuzhan Altun
Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Inonu University, 44210 Malatya, Turkey
Kaan Orhan
Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Ankara University, 06100 Ankara, Turkey
The present study aims to validate the diagnostic performance and evaluate the reliability of an artificial intelligence system based on the convolutional neural network method for the morphological classification of sella turcica in CBCT (cone-beam computed tomography) images. In this retrospective study, sella segmentation and classification models (CranioCatch, Eskisehir, Türkiye) were applied to sagittal slices of CBCT images, using PyTorch supported by U-Net and TensorFlow 1, and we implemented the GoogleNet Inception V3 algorithm. The AI models achieved successful results for sella turcica segmentation of CBCT images based on the deep learning models. The sensitivity, precision, and F-measure values were 1.0, 1.0, and 1.0, respectively, for segmentation of sella turcica in sagittal slices of CBCT images. The sensitivity, precision, accuracy, and F1-score were 1.0, 0.95, 0.98, and 0.84, respectively, for sella-turcica-flattened classification; 0.95, 0.83, 0.92, and 0.88, respectively, for sella-turcica-oval classification; 0.75, 0.94, 0.90, and 0.83, respectively, for sella-turcica-round classification. It is predicted that detecting anatomical landmarks with orthodontic importance, such as the sella point, with artificial intelligence algorithms will save time for orthodontists and facilitate diagnosis.
