No abstract

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.

No abstract

No abstract

No abstract

Artefaktlar görüntü kalitesini düşürürler. Literatürde titanyum (Ti) ve zirkonyum (Zr) implant artefaktları ile ilgili çalışma sayısı kısıtlıdır. Bu çalışmanın amacı, farklı çekim parametreleri ile ProMax Artefakt Azaltma Algoritması'nın (AAA) konik ışınlı bilgisayarlı tomografi (KIBT) görüntülerinde Ti ve Zr implantların oluşturduğu artefaktlar üzerine olan etkisinin değerlendirilmesi ve karşılaştırılmasıdır. Materyal ve Metod: Bir Zr ve bir Ti implant sığır kaburgasına yerleştirildi. Bu kemik ProMax 3D Mid KIBT cihazı ile tarandı. Görüntüler 70, 76, 80, 86 ve 90 kVp'de, 2 farklı voksel boyutunda (0.2 ve 0.4 mm) elde edildi. AAA kullanılarak ve kullanılmadan 20 çekim yapıldı. Elde edilen görüntüler ImageJ programına aktarıldı. Ortalama gri değeri (GV) ve standart sapma (SD) ile kontrast-gürültü oranı (CNR) hesaplandı. İstatistiksel analizlerde Pearson's korelasyon katsayısı, Student's t-test, ANOVA and multipl regresyon analizi testleri kullanıldı. Bulgular: AAA her iki implant grubunda da SD'yi anlamlı derecede azalttı (p<0.001) ve bu azalma Zr implant için daha yüksekti. Algoritmanın aktivasyonu ile kVp ve Zr implanttaki SD arasında önemli bir negatif korelasyon gözlendi (p<0.05). Her iki implant grubunda da GV ve CNR değerleri anlamlı olarak yükseldi ve bu artış Zr grubunda daha yüksekti (p<0.001). Sonuç: Zr, KIBT görüntülerini Ti'den daha fazla bozmaktadır. Promax cihazının AAA her iki implant grubunda da görüntü kalitesini iyileştirmektedir ve Zr implantlar üzerine etkisi daha yüksektir. Anahtar kelimeler: Konik ışınlı bilgisayarlı tomografi, artefakt, gürültü, zirkonyum, dental implant. SUMMARY Aim: Artefacts reduce image quality. There are a limited number of studies regarding the artefacts of titanium (Ti) and zirconium (Zr) implants. The aim of this study was to evaluate and compare the effects of different acquisition parameters and ProMax artefact reduction algorithm (ARA) on the artefacts caused by Ti and Zr implants in cone beam CT (CBCT) images. Materials and Methods: One Zr and one Ti implant were inserted in a bovine rib. The bone was scanned with Pro-Max 3D Mid CBCT unit. Images were acquired using 70, 76, 80, 86 and 90 kVps at two different voxel sizes (0.2 and 0.4 mm). Twenty scans were obtained with and without using ARA. Acquired images were transferred to Im-ageJ program. Mean gray values (GV) and standard deviations (SD) were recorded and the contrast-noise ratio (CNR) was calculated. Statistical analysis was carried out with Pearson's correlation coefficient, Student's t-test, ANOVA and multiple regression analysis tests. Results: ARA reduced the SDs in both implant groups significantly (p<0.001) and this reduction was higher

No abstract

The absence of maxillary central incisor is a rare condition. One central incisor with a symmetrical crown can be seen in both deciduous and permanent dentition at the midline and it is clinically the common sign of solitary median maxillary central incisor (SMMCI). SMMCI can be seen as a isolated dental anomaly as it can be seen with other midline defects.The prevalence of SMMCI is 1:50.000 and the etiology is unknown. In the study SMMCI as a rare dental condition is taken into consideration for its systemic approach and treatment.