Browsing by Author "Alpay, Burcin Arican"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Article Citation Count: 0Comparison of gray-level detectability on computer monitors among several dental specialties: A web-based study(Wroclaw Medical Univ, 2023) Alpay, Burcin Arican; Buyuk, Cansu; Ates, Ayfer Atav; Ağız,Diş ve Çene Radyolojisi / Oral, Dental and Maxillofacial RadiologyBackground. Diagnosis in dentistry begins with the correct reading and interpreting of the dental radio-graph.Objectives. The aim of the present study was to examine the effects of the imaging technique used, the dentistry specialty and the years of experience on the gray-level perception among dentists.Material and methods. A custom web application was developed. Dentomaxillofacial radiologists (DentRads), endodontists (Ends) and general dental practitioners (GDPs) were invited via e-mail to parti-cipate in the study. A total of 46 participants met the requirements of the test. The test comprised 2 webpages. On the 1st page, the participants were asked for information such as gender, specialty, the years of experience, and the imaging techniques they used. Then, on the 2nd page, they were welcomed with instructions and directions, and asked to rearrange 85 gray color tones represented by square bars of equal dimensions. These mixed gray bars were placed in 4 rows according to the principles of the Farnsworth- Munsell 100-hue test (FM). Each clinician's test results were recorded in a database. The individual's level of recognition of gray tones was evaluated through the total error score (TES), which was calculated using a web-based independent scoring software program. Lower TES values were a desirable result, indicating fewer misplacement, while higher scores indicated more misplacements of gray tones. The testing time (TT) was recorded automatically.Results. The years of the participants' experience as dentists or specialists did not affect TES or TT. The dentists who used the charge-coupled device-complementary metal oxide semiconductor (CCD-CMOS) had lower TES values than those who used analog radiographs (p < 0.05).Conclusions. While the specialty and the years of experience did not affect the clinicians' ability to recognize gray tones, the digital imaging techniques (photostimulable phosphor (PSP) and CCD/CMOS) could improve the clinicians'gray-level perception.Article Citation Count: 3Detection of the separated root canal instrument on panoramic radiograph: a comparison of LSTM and CNN deep learning methods(British inst Radiology, 2023) Buyuk, Cansu; Buyuk, Cansu; Er, Fusun; Ağız,Diş ve Çene Radyolojisi / Oral, Dental and Maxillofacial RadiologyObjectives: A separated endodontic instrument is one of the challenging complications of root canal treatment. The purpose of this study was to compare two deep learning methods that are convolutional neural network (CNN) and long short -term memory (LSTM) to detect the separated endodontic instruments on dental radiographs.Methods: Panoramic radiographs from the hospital archive were retrospectively evaluated by two dentists. A total of 915 teeth, of which 417 are labeled as "separated instrument" and 498 are labeled as "healthy root canal treatment" were included. A total of six deep learning models, four of which are some varieties of CNN (Raw -CNN, Augmented -CNN, Gabor filtered -CNN, Gabor-filtered -augmented -CNN) and two of which are some varieties of LSTM model (Raw- LSTM, Augmented-LSTM) were trained based on several feature extraction methods with an applied or not applied an augmentation procedure. The diagnostic performances of the models were compared in terms of accuracy, sensitivity, specificity, positive-and negative-predictive value using 10 -fold cross-validation. A McNemar's tests was employed to figure out if there is a statistically significant difference between performances of the models. Receiver operating characteristic (ROC) curves were developed to assess the quality of the performance of the most promising model (Gabor filtered -CNN model) by exploring different cut -off levels in the last decision layer of the model.Results: The Gabor filtered -CNN model showed the highest accuracy (84.37 +/- 2.79), sensitivity (81.26 +/- 4.79), positive-predictive value (84.16 +/- 3.35) and negative-predictive value (84.62 +/- 4.56 with a confidence interval of 80.6 +/- 0.0076. McNemar's tests yielded that the performance of the Gabor filtered -CNN model significantly different from both LSTM models (p < 0.01).Conclusions: Both CNN and LSTM models were achieved a high predictive performance on to distinguish separated endodontic instruments in radiographs. The Gabor filtered -CNN model without data augmentation gave the best predictive performance.