Convolutional Neural Network Performance for Sella Turcica Segmentation

Abstract

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, Turkiye) 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.

C1 [Duman, Suayip Burak; Ozen, Duygu Celik; Eser, Gozde; Altun, Oguzhan] Inonu Univ, Fac Dent, Dept Oral & Maxillofacial Radiol, TR-44210 Malatya, Turkey.

[Syed, Ali Z.] Case Western Reserve Univ, Sch Dent Med, Dept Oral & Maxillofacial Med & Diagnost Sci, Cleveland, OH 44106 USA.

[Bayrakdar, Ibrahim Sevki] Eskisehir Osmangazi Univ, Fac Dent, Dept Oral & Maxillofacial Radiol, TR-26040 Eskisehir, Turkey.

[Bayrakdar, Ibrahim Sevki; Celik, Ozer] Eskisehir Osmangazi Univ, Dept Ctr Res & Applicat Comp Aided Diag & Treatme, TR-26040 Eskisehir, Turkey.

[Salehi, Hassan S.] Calif State Univ Chico, Dept Elect & Comp Engn, Chico, CA 95929 USA.

[Abdelkarim, Ahmed] Univ Texas Hlth Sci Ctr San Antonio, Dept Oral & Maxillofacial Radiol, San Antonio, TX 79229 USA.

[Celik, Ozer] Eskisehir Osmangazi Univ, Fac Sci, Dept Math Comp, TR-26040 Eskisehir, Turkey.

[Orhan, Kaan] Ankara Univ, Fac Dent, Dept Oral & Maxillofacial Radiol, TR-06100 Ankara, Turkey.

[Orhan, Kaan] Ankara Univ, Med Design Applicat & Res Ctr MEDITAM, TR-06100 Ankara, Turkey.

[Orhan, Kaan] Med Univ Lublin, Dept Dent & Maxillofacial Radiodiagnost, PL-20001 Lublin, Poland.