BELDE ARSAN ÖZCAN

BELDE ARSAN ÖZCAN

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2017 in Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
Verified
Journal Article
Closed access
BÖBELDE ARSAN ÖZCAN
BELDE ARSAN ÖZCAN
TKTaha Emre Köse
Taha Emre Köse
ECErhan Cene
Erhan Cene
IOIlknur Ozcan
Ilknur Ozcan

20 August 2022 in Diagnostics
Verified
Journal Article
Open access
PDF file
CBCansu Buyuk
Cansu Buyuk
NANurullah Akkaya
Nurullah Akkaya
BÖBELDE ARSAN ÖZCAN
BELDE ARSAN ÖZCAN
Gürkan ÜnsalGürkan Ünsal
Gürkan Ünsal
SASecil Aksoy
Secil Aksoy
KOKaan Orhan
Kaan Orhan
The study aimed to generate a fused deep learning algorithm that detects and classifies the relationship between the mandibular third molar and mandibular canal on orthopantomographs. Radiographs (n = 1880) were randomly selected from the hospital archive. Two dentomaxillofacial radiologists annotated the data via MATLAB and classified them into four groups according to the overlap of the root of the mandibular third molar and mandibular canal. Each radiograph was segmented using a U-Net-like architecture. The segmented images were classified by AlexNet. Accuracy, the weighted intersection over union score, the dice coefficient, specificity, sensitivity, and area under curve metrics were used to quantify the performance of the models. Also, three dental practitioners were asked to classify the same test data, their success rate was assessed using the Intraclass Correlation Coefficient. The segmentation network achieved a global accuracy of 0.99 and a weighted intersection over union score of 0.98, average dice score overall images was 0.91. The classification network achieved an accuracy of 0.80, per class sensitivity of 0.74, 0.83, 0.86, 0.67, per class specificity of 0.92, 0.95, 0.88, 0.96 and AUC score of 0.85. The most successful dental practitioner achieved a success rate of 0.79. The fused segmentation and classification networks produced encouraging results. The final model achieved almost the same classification performance as dental practitioners. Better diagnostic accuracy of the combined artificial intelligence tools may help to improve the prediction of the risk factors, especially for recognizing such anatomical variations.

23 September 2021 in Oral Radiology
Verified
Journal Article
Closed access
PDF file
DGDilara nil Günaçar
Dilara nil Günaçar
TKTaha Emre Köse
Taha Emre Köse
BÖBELDE ARSAN ÖZCAN
BELDE ARSAN ÖZCAN
EAEmine Zehra Aydın
Emine Zehra Aydın

30 April 2023 in European Annals of Dental Sciences
Verified
Journal Article
Closed access
CBCansu Buyuk
Cansu Buyuk
BÖBELDE ARSAN ÖZCAN
BELDE ARSAN ÖZCAN
Purpose: The aim of the study is to analyze the changes detected in panoramic radiographs due to bruxism with qualitative and quantitative scales. Materials & Methods: 173 panoramic radiographs of 93 healthy and 80 bruxist individuals were included. Maxillary and mandibular teeth were classified as anterior and posterior on radiographs; loss of the lamina dura (LD), widening of the periodontal ligament (PDL) space, attrition, presence of pulp stones, and pulpal sclerosis were scored. Fractal dimension (FD) analyses were calculated in 10 regions of interest (ROI) including bilateral condylar region, gonial region, ramus, apical areas between the 1st molar -2nd premolar, and the 1st premolar and the canine. Data were analyzed with descriptive statistics, Kolmogorov–Smirnov, independent sample t-test, Kruskal–Wallis, and Spearman correlation tests. Results: 98 women and 75 men were included. There was no statistically significant difference between the genders (p>0.05). The incidence of LD loss, widening of the PDL space, attrition, and pulpal sclerosis was significantly higher in bruxist patients than in the control group (p<0.001). The incidence of widening of the PDL space (p=0.004), pulpal sclerosis (p<0.001), and the presence of pulp stones (p<0.001) were significantly higher in the posterior regions. The mean FD of the condyle was 1.18 ±0.16 in the healthy group and 1.20 ±0.11 in the bruxist group. Conclusion: The incidence of LD loss, widening of the PDL space, attrition, and pulpal sclerosis is higher in bruxists. FD didn’t demonstrate significant differences in the mandibular trabecular structures of bruxist and healthy individuals.

27 February 2022 in Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
Verified
Journal Article
Closed access
BÖBELDE ARSAN ÖZCAN
BELDE ARSAN ÖZCAN

1 March 2021 in Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
Verified
Journal Article
Closed access
BÖBELDE ARSAN ÖZCAN
BELDE ARSAN ÖZCAN
GYGül Merve Yalcin-Ülker
Gül Merve Yalcin-Ülker
DMDeniz Gökce Meral
Deniz Gökce Meral
TETamer Lütfi Erdem
Tamer Lütfi Erdem