Automatic Segmentation of Teeth, Crown-Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls.

BACKGROUND: The aim of our study is to provide successful automatic segmentation of various objects on orthopantomographs (OPGs). METHODS: 8138 OPGs obtained from the archives of the Department of Dentomaxillofacial Radiology were included. OPGs were converted into PNGs and transferred to the segmentation tool's database. All teeth, crown-bridge restorations, dental implants, composite-amalgam fillings, dental caries, residual roots, and root canal fillings were manually segmented by two experts with the manual drawing semantic segmentation technique. RESULTS: The intra-class correlation coefficient (ICC) for both inter- and intra-observers for manual segmentation was excellent (ICC > 0.75). The intra-observer ICC was found to be 0.994, while the inter-observer reliability was 0.989. No significant difference was detected amongst observers (p = 0.947). The calculated DSC and accuracy values across all OPGs were 0.85 and 0.95 for the tooth segmentation, 0.88 and 0.99 for dental caries, 0.87 and 0.99 for dental restorations, 0.93 and 0.99 for crown-bridge restorations, 0.94 and 0.99 for dental implants, 0.78 and 0.99 for root canal fillings, and 0.78 and 0.99 for residual roots, respectively. CONCLUSIONS: Thanks to faster and automated diagnoses on 2D as well as 3D dental images, dentists will have higher diagnosis rates in a shorter time even without excluding cases.

Deep convolutional neural network algorithm for the automatic segmentation of oral potentially malignant disorders and oral cancers.

This study aimed to develop an algorithm to automatically segment the oral potentially malignant diseases (OPMDs) and oral cancers (OCs) of all oral subsites with various deep convolutional neural network applications. A total of 510 intraoral images of OPMDs and OCs were collected over 3 years (2006-2009). All images were confirmed both with patient records and histopathological reports. Following the labeling of the lesions the dataset was arbitrarily split, using random sampling in Python as the study dataset, validation dataset, and test dataset. Pixels were classified as the OPMDs and OCs with the OPMD/OC label and the rest as the background. U-Net architecture was used and the model with the best validation loss was chosen for the testing among the trained 500 epochs. Dice similarity coefficient (DSC) score was noted. The intra-observer ICC was found to be 0.994 while the inter-observer reliability was 0.989. The calculated DSC and validation accuracy across all clinical images were 0.697 and 0.805, respectively. Our algorithm did not maintain an excellent DSC due to multiple reasons for the detection of both OC and OPMDs in oral cavity sites. A better standardization for both 2D and 3D imaging (such as patient positioning) and a bigger dataset are required to improve the quality of such studies. This is the first study which aimed to segment OPMDs and OCs in all subsites of oral cavity which is crucial not only for the early diagnosis but also for higher survival rates.

Artificial intelligence-based algorithm for cervical vertebrae maturation stage assessment.

OBJECTIVE: The aim of this study was to develop an artificial intelligence (AI) algorithm to automatically and accurately determine the stage of cervical vertebra maturation (CVM) with the main purpose being to eliminate the human error factor. SETTING AND SAMPLE POPULATION: Archives of the cephalometric images were reviewed and the data of 1501 subjects with fully visible cervical vertebras were included in this retrospective study. MATERIALS AND METHODS: Lateral cephalometric (LC) that met the inclusion criteria were used in the training process, labeling was carried out using a computer vision annotation tool (CVAT), tracing was done by an experienced orthodontist as a gold standard and, in order to limit the effect of the uneven distribution of the training data set, maturation stage was classified with a modified Bachetti method by the operator who labelled them. The labelled data were split randomly into a training set (80%), a testing set (10%) and an validation set (10%), to measure intra-observer, inter-observer reliability, intraclass correlation coefficient (ICC) and weighted Cohen's kappa test was carried out. RESULTS: The ICC was valued at 0.973, weighted Cohen's kappa standard error was 0.870 ± 0.027 which shows high reliability of the observers and excellent level of agreement between them, the segmentation network achieved a global accuracy of 0.99 and the average dice score overall images was 0.93. The classification network achieved an accuracy of 0.802, class sensitivity of (pre-pubertal 0.78; pubertal 0.45; post-pubertal 0.98), respectively, per class specificity of (pre-pubertal 0.94; pubertal 0.94; post-pubertal 0.75), respectively. CONCLUSION: The developed algorithm showed the ability to determine the cervical vertebrae maturation stage which might aid in a faster diagnosis process by eliminating human intervention, which might lead to wrong decision-making procedures that might affect the outcome of the treatment plan. The developed algorithm proved reliable in determining the pre-pubertal and post-pubertal growth stages with high accuracy.

A Fused Deep Learning Architecture for the Detection of the Relationship between the Mandibular Third Molar and the Mandibular Canal.

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.

A deep learning algorithm proposal to automatic pharyngeal airway detection and segmentation on CBCT images.

OBJECTIVES: This study aims to evaluate an automatic segmentation algorithm for pharyngeal airway in cone-beam computed tomography (CBCT) images using a deep learning artificial intelligence (AI) system. SETTING AND SAMPLE POPULATION: Archives of the CBCT images were reviewed, and the data of 306 subjects with the pharyngeal airway were included in this retrospective study. MATERIAL AND METHODS: A machine learning algorithm, based on Convolutional Neural Network (CNN), did the segmentation of the pharyngeal airway on serial CBCT images. Semi-automatic software (ITK-SNAP) was used to manually generate the airway, and the results were compared with artificial intelligence. Dice similarity coefficient (DSC) and Intersection over Union (IoU) were used as the accuracy of segmentation in comparing the measurements of human measurements and artificial intelligence algorithms. RESULTS: The human observer found the average volume of the pharyngeal airway to be 18.08 cm3 and artificial intelligence to be 17.32 cm3 . For pharyngeal airway segmentation, a dice ratio of 0.919 and a weighted IoU of 0.993 is achieved. CONCLUSIONS: In this study, a successful AI algorithm that automatically segments the pharyngeal airway from CBCT images was created. It can be useful in the quick and easy calculation of pharyngeal airway volume from CBCT images for clinical application.

Brain-Computer Interface for Control of Wheelchair Using Fuzzy Neural Networks.

The design of brain-computer interface for the wheelchair for physically disabled people is presented. The design of the proposed system is based on receiving, processing, and classification of the electroencephalographic (EEG) signals and then performing the control of the wheelchair. The number of experimental measurements of brain activity has been done using human control commands of the wheelchair. Based on the mental activity of the user and the control commands of the wheelchair, the design of classification system based on fuzzy neural networks (FNN) is considered. The design of FNN based algorithm is used for brain-actuated control. The training data is used to design the system and then test data is applied to measure the performance of the control system. The control of the wheelchair is performed under real conditions using direction and speed control commands of the wheelchair. The approach used in the paper allows reducing the probability of misclassification and improving the control accuracy of the wheelchair.