Dental Panoramic Images Research Articles

LCANet: Learnable Connected Attention Network for Human Identification Using Dental Images.

Forensic odontology is regarded as an important branch of forensics dealing with human identification based on dental identification. This paper proposes a novel method that uses deep convolution neural networks to assist in human identification by automatically and accurately matching 2-D panoramic dental X-ray images. Designed as a top-down architecture, the network incorporates an improved channel attention module and a learnable connected module to better extract features for matching. By integrating associated features among all channel maps, the channel attention module can selectively emphasize interdependent channel information, which contributes to more precise recognition results. The learnable connected module not only connects different layers in a feed-forward fashion but also searches the optimal connections for each connected layer, resulting in automatically and adaptively learning the connections among layers. Extensive experiments demonstrate that our method can achieve new state-of-the-art performance in human identification using dental images. Specifically, the method is tested on a dataset including 1,168 dental panoramic images of 503 different subjects, and its dental image recognition accuracy for human identification reaches 87.21% rank-1 accuracy and 95.34% rank-5 accuracy. Code has been released on Github. (https://github.com/cclaiyc/TIdentify).

MSLPNet: multi-scale location perception network for dental panoramic X-ray image segmentation

Tooth segmentation, as one of the key techniques of medical image segmentation, can be widely applied to various medical applications, e.g., orthodontic treatment, corpse identification, dental training systems, dental disease diagnosis, etc. Although there have been many studies on tooth segmentation, few tooth segmentation studies have focused on enhancing tooth segmentation with fuzzy root boundaries which is a difficult but essential task in dentistry to determine the root resorption and the tooth brace. The existing methods for tooth segmentation usually exploited the contrast enhancement to sharpen the boundaries of teeth, while the final segmentation results heavily depended on the subsequent processing steps of the method. To address the issue of fuzzy boundaries, this paper proposes a novel multi-scale location perception network to segment teeth from panoramic X-ray images. The core of the proposed method stems from three aspects: (1) multi-scale structural similarity loss conducts accurate prediction with clear boundary from patch-level scale; (2) location perception module locates each tooth pixel in the image from the perspective of global-level scale; (3) aggregation module reduces the semantic gap between multi-scale feature branches. Our proposed method was tested on a dataset containing 1500 dental panoramic X-ray images and the Dice score of our method is 93.01%, which outperforms the state-of-the-art approaches. Besides, our proposed method has better boundary quality and the Pratt (1978)’s figure of merit used for boundary quality evaluation reaches 76.56%.

Object detection on dental x-ray images using deep learning method

Radiological examination has an important role in determining the diagnosis of dental problems and making decisions about the right type of treatment according to the case indications. Dental x-ray is a medical procedure for taking pictures of the inside of the mouth using radiation fluid, where the results are used diagnostically to help the dentist see the entire structure of the jaw bone and teeth, and dental problems that cannot be seen directly. Dental radiographic interpretation, which is generally performed by dentists, is a time-consuming and error-prone process due to high variations in tooth structure, low experience levels, and fatigue factors experienced by dentists. The workload of a dentist and the occurrence of misdiagnosis can be reduced by the existence of a system that can automatically interpret the x-ray results. To overcome these problems, a model will be developed to be able to detect objects in the dental panoramic x-ray images using Mask R-CNN, one of the methods in Deep Learning. Deep Learning is an artificial intelligence function that modelled the workings of human brain in processing data and creating patterns for use in decision making. With the detection of objects in panoramic x-ray image automatically, it is expected to save time, improve the quality of dental care, and also the quality of diagnosis made by dentists.

Segmentation of teeth in panoramic dental X-ray images using U-Net with a loss function weighted on the tooth edge.

Panoramic dental X-ray imaging is an established method for the diagnosis of dental problems. However, the resolution of panoramic dental X-ray images is relatively low. Thus, early lesions are often overlooked. As the first step in the development of a computer-aided diagnosis scheme for panoramic dental X-ray images, we propose a computerized method for the segmentation of teeth using U-Net with a loss function weighted on the tooth edge. Our database consisted of 162 panoramic dental X-ray images. The training dataset consisted of 102 images, while the remaining 60 images were used as the test dataset. The loss function obtained by the cross entropy (CE) in the entire image is usually used in training U-Net. To improve the segmentation accuracy of the tooth edge, a loss function weighted on the tooth edge is proposed by adding the CE in the tooth edge region to the CE for the entire image. The mean Jaccard index and Dice index for U-Net with the loss function combining the CEs for the entire image and tooth edge were 0.864 and 0.927, respectively, which were significantly larger than those for U-Net with the CE for the entire image (0.802 and 0.890, p < 0.001) and U-Net with the CE for the tooth edge (0.826 and 0.905, p < 0.001). U-Net with the new loss function exhibited a higher segmentation accuracy of the tooth in panoramic dental X-ray images than that obtained by U-Net with the conventional loss function.

Human Identification with Dental Panoramic Images Based on Deep Learning

Human Identification with Dental Panoramic Images Based on Deep Learning

Biometric identification using panoramic dental radiographic images with few-shot learning

Biometric identification using panoramic dental radiographic images with few-shot learning

SUCCESS OF ARTIFICIAL INTELLIGENCE SYSTEM IN DETERMINING ALVEOLAR BONE LOSS FROM DENTAL PANORAMIC RADIOGRAPHY IMAGES

Objectives: The aim of this study was to detect alveolar bone loss from dental panoramic radiographic images using artificial intelligence systems. Material and Methods: A total of 2276 panoramic radiographic images were used in this study. While 1137 of them belong to cases with bone destruction, 1139 were periodontally healthy. The dataset is divided into three parts as training (n=1856) , validation (n=210) and testing set (n= 210). All images in the data set were resized to 1472x718 pixels before training. A random sequence was created using the open-source python programming language and OpenCV, NumPy, Pandas, and Matplotlib libraries effectively. A pre-trained Google Net Inception v3 CNN network was used for preprocessing and data sets were trained using transfer learning. Diagnostic performance was evaluated with the confusion matrix using sensivitiy, specificity, precision, accuracy and F1 score. Results: Of the 105 cases with bone loss, 99 were detected by the AI system. Sensitivity was 0.94, specificity 0.88, precision 0.89, accuracy 0.91 and F1 score 0.91. Conclusion: The convolutional neural network model is successful in determining periodontal bone losses. It can be used as a system to facilitate the work of physicians in diagnosis and treatment planning in the future.

Individual tooth detection and identification from dental panoramic X-ray images via point-wise localization and distance regularization

Dental panoramic X-ray imaging is a popular diagnostic method owing to its very small dose of radiation. For an automated computer-aided diagnosis system in dental clinics, automatic detection and identification of individual teeth from panoramic X-ray images are critical prerequisites. In this study, we propose a point-wise tooth localization neural network by introducing a spatial distance regularization loss. The proposed network initially performs center point regression for all the anatomical teeth (i.e., 32 points), which automatically identifies each tooth. A novel distance regularization penalty is employed on the 32 points by considering L2 regularization loss of Laplacian on spatial distances. Subsequently, teeth boxes are individually localized using a multitask neural network on a patch basis. A multitask offset training is employed on the final output to improve the localization accuracy. Our method successfully localizes not only the existing teeth but also missing teeth; consequently, highly accurate detection and identification are achieved. The experimental results demonstrate that the proposed algorithm outperforms state-of-the-art approaches by increasing the average precision of teeth detection by 15.71 % compared to the best performing method. The accuracy of identification achieved a precision of 0.997 and recall value of 0.972. Moreover, the proposed network does not require any additional identification algorithm owing to the preceding regression of the fixed 32 points regardless of the existence of the teeth.

Measurement of Entrance Skin Dose and the Dose Received by Different Organs in Panoramic Dental Imaging.

Background: Thermoluminescence dosimetry(TLD) has been known as one of the most effective methods for dose estimation in diagnostic radiology. Orthopantomogram (OPG) imaging is used by many dentists, oral and maxillofacial surgeons as an effective tool for choosing an appropriate treatment plan.Objective: This study aims to measure the entrance skin dose and the dose values received by different head and neck organs in OPG imaging using TLD dosimeters (TLD-100).Material and Methods: In this experimental study, the entrance skin dose and doses of various organs during imaging were measured by TLD dosimeters inside and on the surface of the Rando-Phantom. Doses to various organs, including thyroid, eye, esophagus, parotid and sublingual and submandibular salivary glands were measured. The measurements were repeated twice, and the dose values obtained in the two steps were compared.Results: Based on the results obtained in this study, the minimum dose values were found in Esophagus; 65.81, and 59.31 µGy, respectively. The maximum organ dose value was found for left parotid glands, 3842.42, and 3399.58 for the two measurements, respectively. Conclusion: The results show that the dose values can vary based on devices, exposure conditions, and TLD positioning.

TSASNet: Tooth segmentation on dental panoramic X-ray images by Two-Stage Attention Segmentation Network

Tooth segmentation acts as a crucial and fundamental role in dentistry for doctors to make diagnosis and treatment plans. In this paper, we propose a Two-Stage Attention Segmentation Network (TSASNet) on dental panoramic X-ray images to address the issues suffered in the tooth boundary and tooth root segmentation task which are caused by the low contrast and uneven intensity distribution. We firstly adopt an attention model which is embedded with global and local attention modules to roughly localize the tooth region in the first stage. Without any interactive operator, the attention model so constructed can automatically aggregate pixel-wise contextual information and identify coarse tooth boundaries. To better obtain final boundary information, we use a fully convolutional network as the second stage to further segment the real tooth area from the attention maps obtained from the first stage. The effectiveness of TSASNet is substantiated on the benchmark dataset containing 1,500 dental panoramic X-ray images, our proposed method achieves 96.94% of accuracy, 92.72% of dice and 93.77% of recall, significantly superior to the current state-of-the-art methods.

Reconstruction of Panoramic Dental Images Through Bézier Function Optimization.

Computed tomography (CT) and X-ray images have been extensively used as a valuable diagnostic tool in dentistry for surgical planning and treatment. Nowadays, dental cone beam CT has been extensively used in dental clinics. Therefore, it is possible to employ three-dimensional (3D) data from the CT to reconstruct a two-dimensional (2D) panoramic dental image that provides a longitudinal view of the mandibular region of the patient, avoiding an additional exposure to X-ray. In this work, we developed a new automatic method for reconstructing 2D panoramic images of the dental arch based on 3D CT images, using Bézier curves and optimization techniques. The proposed method was applied to five patients, some of them with missing teeth, and smooth panoramic images with good contrast were obtained.

SEPARATION OF OVERLAPPING OBJECT SEGMENTATION USING LEVEL SET WITH AUTOMATIC INITALIZATION ON DENTAL PANORAMIC RADIOGRAPH

To extract features on dental objects, it is necessary to segment the teeth. Segmentation is separating between the teeth (objects) with another part than teeth (background). The process of segmenting individual teeth has done a lot of the recently research and obtained good results. However, when faced with overlapping teeth, this is quite challenging. Overlapping tooth segmentation using the latest algorithm produces an object that should be segmented into two objects, instantly becoming one object. This is due to the overlapping between two teeth. To separate overlapping teeth, it is necessary to extract the overlapping object first. Level set method is widely used to segment overlap objects, but it has a limitation that needs to define the initial level set method manually by the user. In this study, an automatic initialization strategy is proposed for the level set method to segment overlapping teeth using hierarchical cluster analysis on dental panoramic radiographs images. The proposed strategy was able to initialize overlapping objects properly with accuracy of 73%. Evaluation to measure quality of segmentation result are using misscassification error (ME) and relative foreground area error (RAE). ME and RAE were calculated based on the average results of individual tooth segmentation and obtain 16.41% and 52.14%, respectively. This proposed strategy are expected to be able to help separate the overlapping teeth for human age estimation through dental images in forensic odontology.

Numbering and Classification of Panoramic Dental Images Using 6-Layer Convolutional Neural Network

Deep Convolution Neural Network is one of the most powerful tools to solve complex problems of image classification, image recognition, financial analysis, medical diagnosis and many similar problems. A dental panoramic image consists of collection of teeth of both upper jaw and lower jaw. Automatic classification of dental panoramic images into various tooth types such as canines, incisors, premolars and molars has been a challenging task and involves crucial role of an experienced dentist. In this paper, we propose a technique for numbering and classification of the panoramic dental images. The proposed algorithm consists of four stages namely pre-processing, segmentation, numbering and classification. The pre-processed panoramic dental images are segmented using fuzzy c-mean clustering and subjected to vertical integral projection to extract a single tooth. The image dataset consists of 400 dental panoramic images collected from various dental clinics. The 400 dental images are divided into 240 training samples and 160 testing samples. The image data set is augmented by applying various transformations. Panoramic dental images are further numbered using a universal dental numbering system. Finally, the classification is done with the help of 6-layer deep convolution neural network (DCNN) consisting of 3 convolutional neural network and 3 fully connected network. The tooth is classified as canine, incisor, molar and premolar. An accuracy of 95% has been achieved for augmented database and 92% for original dataset with the proposed algorithm. The proposed numbering and classification of dental panoramic images is useful in biomedical application and postmortem recording of dental records. In case of big calamity, the system can also assist the dentist in recording post mortem dental record that is a very lengthy and arduous task.

Application of a fully deep convolutional neural network to the automation of tooth segmentation on panoramic radiographs.

To evaluate a fully deep learning mask region-based convolutional neural network (R-CNN) method for automated tooth segmentation using individual annotation of panoramic radiographs. In total, 846 images with tooth annotations from 30 panoramic radiographs were used for training, and 20 panoramic images as the validation and test sets. An oral radiologist manually performed individual tooth annotation on the panoramic radiographs to generate the ground truth of each tooth structure. We used the augmentation technique to reduce overfitting and obtained 1024 training samples from 846 original data points. A fully deep learning method using the mask R-CNN model was implemented through a fine-tuning process to detect and localize the tooth structures. For performance evaluation, the F1 score, mean intersection over union (IoU), and visual analysis were utilized. The proposed method produced an F1 score of 0.875 (precision: 0.858, recall: 0.893) and a mean IoU of 0.877. A visual evaluation of the segmentation method showed a close resemblance to the ground truth. The method achieved high performance for automation of tooth segmentation on dental panoramic images. The proposed method might be applied in the first step of diagnosis automation and in forensic identification, which involves similar segmentation tasks.

Fuzzy Features for Facial Shape Classification on Panoramic Dental Image

Research on human face shape identification can assist forensic teams in reconstructing an unidentified victim’s facial features. Human face shape identification using panoramic dental imaging is suitable for use by forensic teams in identifying a large number of victims due to the teeth’s ability to withstand heat of up to 1,000°C. This study proposes an application for face shapes classification on panoramic dental image using fuzzy features and decision tree method. It will be used to assist forensic scientists in reconstructing unidentified people identifying numerous victims from their facial features. There are three classifications of human face shapes, namely oval, tapered, and square. The steps in this study are digitizing panoramic dental images into files; segmenting the upper jaw’s incisor teeth; then extracting the features by area, parameter, width, length, width-to-length ratio, area-to-parameter ratio, center_x and center_y. Fuzzy theory is used to convert numeric features into category features, while decision tree method will be used for training features. The experimental results show that the proposed method obtain accuracy 67% of 42 panoramic dental image.

Improving of classification accuracy of cyst and tumor using local polynomial estimator

Cyst and tumor in oral cavity are seriously noticed by health experts along with increasing death cases of oral cancer in developing country. Early detection of cyst and tumor using dental panoramic image is needed since its initial growth does not cause any complaints. Image processing is done by mean for distinguishing the classification of cyst and tumor. The results in previous studies about classification of cyst and tumor were done by using a mathematical computation approach namely supports vector machine method that have still not satisfied and have not been validated. Therefore, in this study we propose a method, i.e., nonparametric regression model based on local polynomial estimator that can be improve the classification accuracy of cyst and tumor on human dental panoramic image. By using the proposed method, we get the classification accuracy of cyst and tumor, i.e., 90.91% which is greater than those by using the support vector machine method, i.e., 76.67%. Also, in validation process we obtain that the nonparametric regression model approach gives a significant Press’s Q statistical testing value. So, we conclude that the nonparametric regression model approach improves the classification accuracy and gives better outcome to classify cyst and tumor using dental panoramic image than the support vector machine method.

Iterated Region for Interactive Image Segmentation on Dental Panoramic Radiograph

Image Segmentation is a process to separate between foreground and background. Segmentation process in low contrast image such as dental panoramic radiograph image is not easily determined. Image segmentation accuracy determines the success or failure of the final analysis process. The process of segmentation can occur ambiguity. This ambiguity is due to an ambiguous area if it is not selected as a region so it may have occurred cluster errors. To solve this ambiguity, we proposed a new region merging by iterated region merging process on dental panoramic radiograph image. The proposed method starts from the user marking and works iteratively to label the surrounding regions. In each iteration, the minimal gray-levels value is merged so the unknown regions significantly reduced. This experiment shows that the proposed method is effective with an average of ME and RAE of 0.04% and 0.06%.

Prevalence of detected soft tissue calcifications on digital panoramic radiographs

Objectives: Some calcifications of the head and neck region may be seen on dental panoramic images due to the superimpositions and proximity of structures. The aim of the present study was to evaluate the prevalence of soft tissue calcifications observed on digital panoramic images and the relationship of the calcifications with age and gender. Materials and Methods: Four thousand two hundred and sixty-three digital dental panoramic radiographs of the individuals aged between 6 and 89 who had visited the faculty of dentistry for different oral and dental complaints were evaluated retrospectively and detected calcifications were recorded with the age and gender information. Data were analyzed by means of descriptive statistics, Pearson Chi-squared, and independent samples t-test. Results: Two hundred and seventy calcifications (6.4%) were detected in the whole study population. Observed calcification types were tonsillolith (2.5%), carotid artery calcification (2.3%), sialolith (1%), and calcified lymph node (0.6%). The prevalence of calcifications for all types increased with age (P < 0.001). Conclusions: The prevalence of calcifications seen on the dental panoramic images is relatively rare, but the detection during routine dental examinations is important in terms of the need for more detailed evaluation of the patients.

New approaches to determine age and gender in image processing techniques using multilayer perceptron neural network

As a result of some events (disasters, inheritance, disappearances etc.), age and gender determination can be vital for people. Forensic medical institutions make the determination of age by examining the structures such as teeth and bones. Procedures for forensic science are currently estimated manually according to certain morphological findings on the tooth. In this study, 1313 panoramic dental images were used automatically to estimate age. Image preprocessing is applied on these images. Trapezoidal teeth are corrected in the coordinate plane to obtain more accurate and standard results. In the study, the correction process is done with original and novel developed algorithm. Dental images are automatically and dynamically segmented and feature vectors are created by extracting their features. The generated feature vectors are dynamic and presented as inputs to the Multilayer Perceptron Neural Network. Depending on the request, the number of input count reduction process can be performed. In this study, age and gender were determined from dental x-ray images with novel and originally developed algorithm. The application is written in C # programming language. In some tooth groups, the highest classification rate of 100% and age determination with 0 error were performed. With this study, age determination in forensic science will be more accurate.

Büyükten Küçüğe Oto-kodlayıcılar ile dişlerin konumlandırılması*

Localization of teeth is a prerequisite task for most of the computerized methods for dental images such as medical diagnosis and human identification. Classical deep learning architectures like convolutional neural networks and auto-encoders seem to work well for tooth detection, however, it is non-trivial because of the large image size. In this study, a coarse-to-fine stacked auto-encoder architecture is presented for detection of teeth in dental panoramic images. The proposed architecture involves cascaded stacked auto-encoders where sizes of the input patches increase with the successive steps. Only the detected candidate tooth patches are fed into the successive layers, thus the irrelevant patches are eliminated. The proposed architecture decreases the cost of detection process while providing precise localization. The method is tested and validated on a dataset containing 206 dental panoramic images and the results are promising.