The formula developed through measurements in the maxillary sinus using CBCT scans showed an accuracy of 84% for sex estimation and can be applied as a complementary method for human identification in the Brazilian population.
Objective: To evaluate whether image enhancement filters of VistaScan system improve the diagnostic accuracy of simulated periapical lesions. Methods: 10 sockets were prepared on bovine ribs to fit a bovine tooth. Bone defects were created and successively enlarged providing four groups (n = 10): Group 0, absence of lesions; Group 1, periapical lesions with 1.6 mm in diameter; Group 2, with 1.8 mm in diameter; and Group 3, with 2.1 mm in diameter. Periapical radiographs were taken using a photostimulable storage phosphor plate and DBSWIN software. VistaScan filters were applied and the images were allocated into seven groups: Nonfiltered, Fine, Caries 1, Caries 2, Endodontic, Periodontal and Noise Reduction. All the 280 images were assessed about the presence or absence of periapical lesions. Pixel intensities standard deviation were compared between nonfiltered and filtered images. Two-Way Analysis of Variance and the post hoc Tukey’s test were used to compare area under the ROC curve, sensitivity and specificity. Results: VistaScan filters showed no significant difference for area under receiver operating characteristic curve (p = 0.124), sensitivity (p = 0.835) and specificity (p = 0.832). Area under receiver operating characteristic curve (p = 0.000) and sensitivity (p = 0.000) in 2.1 mm lesions size were significantly higher than in 1.6 mm and 1.8 mm lesions size. Pixel intensities standard deviation was significantly changed in the filtered images compared to nonfiltered ones (p < 0.01), except for Fine in the bone region (p > 0.05). Conclusion: VistaScan enhancement filters do not influence the diagnostic accuracy of simulated periapical lesions. On the other hand, larger lesions were more frequently detected. The filters change the pixel intensities reducing or intensifying the differences between similar regions.
Objective. The aim of this study was to compare the diagnostic performance of convolutional neural networks (CNNs) with the performance of human observers for the detection of simulated periapical lesions on periapical radiographs. Study Design. Ten sockets were prepared in bovine ribs. Periapical defects of 3 sizes were sequentially created. Periapical radiographs were acquired of each socket with no lesion and with each lesion size with a photostimulable storage phosphor system. Radiographs were evaluated with no filter and with 6 image filter settings. A CNN architecture was set up using Keras-TensorFlow. Separate CNNs were evaluated for randomly sampled training/validation data and for data split up by socket (5-fold cross-validation) and filter (7-fold cross-validation). CNN performance on validation data was compared with that of 3 oral radiologists for sensitivity, specificity, and area under the receiver operating characteristic curve (ROC-AUC). Results. Using random sampling, the CNN showed perfect accuracy for the validation data. When data were split up by socket, the mean sensitivity, specificity, and ROC-AUC values were 0.79, 0.88, and 0.86, respectively; when split up by filter, they were 0.87, 0.98, and 0.93, respectively. For radiologists, the values were 0.58, 0.83, and 0.75, respectively. Conclusions. CNNs show promise in periapical lesion detection. The pretrained CNN model yielded in this study can be used for further training on larger samples and/or clinical radiographs. (Oral Surg Oral Med Oral Pathol Oral Radiol 2021;000:1À7)
Statement of Clinical RelevanceConvolutional neural networks are used to develop artificial intelligence systems for diagnostic tasks in oral and maxillofacial radiology. This study indicates that convolutional neural networks can yield diagnostic performance comparable to or better than that of human observers for detection of periapical lesions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.