Dental Panoramic Radiographs Research Articles

Possible Association between Methylphenidate and Mandibular Bone Characteristics Detected by Dental Panoramic Radiograph in Children and Adolescents with ADHD.

Some studies have shown that children treated with psychostimulants for attention-deficit hyperactivity disorder (ADHD) have decreased bone mineral density (BMD). Mandibular cortical width (MCW) may be used as a surrogate measure for evaluating BMD. We compared the MCW measured on digital panoramic radiographs (DPR) of 38 children and adolescents with ADHD who were treated with methylphenidate for at least 12 months to the MCW of 58 children and adolescents without ADHD (control). The two groups had a similar mean age (p = 0.3). Mean MCW was significantly lower among children with ADHD compared to those in the control group (2.77 ± 0.33 mm vs. 3.04 ± 0.46 mm, p = 0.004). Additionally, each of the MCW sides were significantly smaller in the group with ADHD compared with the control group. In conclusion, treatment with methylphenidate is associated with low MCW in children and adolescents with ADHD. Analysis of MCW on DPR may help in screening children that are at risk of bone health alterations that may result in low BMD in adulthood. Dentists may be the first to identify bone health abnormalities and should be aware of their role in referring their patients to further follow-up.

Dental Age Estimation Standards for Hispanic Children and Adolescents in California

Background: In recent years, cross-border migrations have resulted in an increase in the number of unaccompanied children apprehended at the United States border, particularly in the state of California. The assessment of the chronological age of a child, in many instances, determines the type of services rendered within the medico-legal system. Age can be determined by using population-specific reference standards, preferably within a geographical area. However, such standards are not available for Hispanic children living in California. Aim: To present new standards by developing and validating a reference data set for dental age estimation in Hispanic children in California. Methods: For the reference dataset, a total of 705 dental panoramic radiographs of healthy children aged 7.00 to 13.99 years belonging to Hispanic ethnicity in California were obtained from the archives of a teaching hospital. All permanent teeth on the left side were scored in automated software, and the average at assessment was calculated for each stage of dental development. For the validation dataset, 133 radiographs that were not part of the reference dataset were obtained based on the above criteria. The difference between the chronological age (CA) and dental age (DA) estimated using the California Hispanic reference dataset was assessed using a paired t-test with a statistical significance of p < 0.05. Results: The overall difference between the chronological age and dental age (CA-DA) was 0.03 years (1.56 weeks) for females and −0.10 years (−5.26 weeks) for males, and the difference was not statistically significant for children aged 8.00 to 12.99 years (p > 0.05). Conclusions: The newly constructed dental reference data can be recommended for age estimation in children belonging to Hispanic ethnicity in California.

A multicenter approach on dento-osseous anomalies in familial adenomatous polyposis

<h3>Objectives</h3> Familial adenomatous polyposis (FAP) is a hereditary disorder characterized by early and unremitting development of intestinal polyps and extraintestinal manifestations requiring multidisciplinary screening and surveillance. Herein we describe a multicenter cross-sectional analysis of the dento-osseous radiographic findings of patients with FAP from South and North America. <h3>Study design</h3> Both cohorts included individuals diagnosed with FAP by standard clinical criteria. Subjects were paired with age- and gender-matched, healthy, non-FAP controls. Dental panoramic radiographs (DPR) of both cohorts, children and adults, were examined. <h3>Results</h3> Of 114 DPRs, 38 were from patients with FAP, composed of Group I (n=22), Group II (n=16), and 76 matched controls. Evaluators had excellent agreement on key findings (ICC=0.89). The prevalence of osseous anomalies was higher in FAP adults (75%), with mean age 35.3 years, than in children (65.4%). We found a high prevalence of multiple areas of idiopathic osteosclerosis (68.4%), a novel observation in the FAP population. Dental alterations such as odontomas and supernumerary teeth were more frequent in FAP children (mean age 13.5 years), with a prevalence of 15.4%. <h3>Conclusions</h3> We described important and significant differences in the prevalence of dento-osseous and dental anomalies in children compared with adult FAP patients. These findings should be considered with caution. The presence of these abnormalities in pediatric dental patients, even if not diagnosed with FAP, should be borne in mind as possibly indicating <i>de novo</i> or unrecognized disease. We recommend that dental examination and radiographic follow-up of FAP children in the mixed dentition (9 years old and older) and adults should be adopted as part of the surveillance protocol for FAP patients. <b>Statement of Ethical Review</b> Human/Animal subjects were used and this study was approved by an institutional ethics panel

A deep-learning model for idiopathic osteosclerosis detection on dental panoramic radiographs

<h3>Objectives</h3> The purpose of the study was to propose an automatic idiopathic osteosclerosis (IO) detection model based on the convolutional neural network (CNN) algorithms in panoramic radiographs using GoogleNet Inception V2 architecture and assess the performance of the artificial intelligence (AI) model compared to the human observer. <h3>Study Design</h3> A total of 493 anonymized panoramic radiographs were used to develop the AI system (CranioCatch, Eskisehir-Turkey) for the detection of IOs. The panoramic radiographs were acquired from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Eskisehir Osmangazi University. GoogleNet Inception V2 model implemented with TensorFlow library was used for the detection of IOs. A confusion matrix was used to predict model achievements. <h3>Results</h3> 50 IOs were detected by the AI model from the 52 test images, which had 57 IOs. The sensitivity, precision, and F-measure values were 0.88, 0.83, and 0.86, respectively. <h3>Conclusion</h3> Deep learning-based AI models have the potential to detect IOs accurately on panoramic radiographs. AI systems can be used to support clinicians for baseline diagnosis of panoramic radiographs and may eventually replace human observers' evaluation and support performance in the future. <b>Statement of Ethical Review</b> Human/Animal subjects were used and this study was approved by an institutional ethics panel

Evaluation of bone changes on dental panoramic radiography using mandibular indexes and fractal dimension analysis in children with familial Mediterranean fever.

It was aimed to evaluate the bone microarchitecture of children with FMF in the city of Tokat, where the disease is highly prevalent, in Turkey, one of the countries where familial Mediterranean Fever (FMF) disease is the most common, using mandibular indexes and fractal dimension analysis on panoramic radiography. In this retrospective study, the results were evaluated and compared using the mandibular cortical index (MCI), the mental index (MI), the panoramic mandibular index (PMI), and the fractal dimension analysis of six different regions (condyle, angulus, and interdental) on dental panoramic radiographs in 124 children with FMF and 124 healthy children. The data were analyzed using the IBM SPSS V23. The distribution of MCI in children with FMF was similar to the control group (p > 0.05). The mean MI (3.59) values in FMF patients were statistically higher than the control group (p = 0.016). No statistically significant difference was found in PMI between the patients with FMF and the control group (p > 0.05). No statistically significant difference was found between the mean fractal dimension (FD) values according to the groups (p > 0.05). Trabecular bone microarchitecture of children with FMF is similar to healthy children. There is no correlation between the duration of colchicine use and bone microarchitecture.

Root canal width as a mandibular maturity marker at the 18-year threshold in the Maltese population.

The determination of age of majority (the 18-year-old threshold) using the popular Demirjian tooth staging method is unreliable, so other maturity markers are required. This study examines whether the ratio of the root canal widths (RCW) of the mandibular first, second and third molars is a useful indicator of age. Nine hundred eighteen dental panoramic radiographs (DPT) were examined and the ratio of the mid-points of the distal roots of the left mandibular first, second and third molars assessed according to the RCW stages as described by Roberts (J Forensic Sci 62:351-354, 2017). Individuals who had reached stages RCW-A and RCW-B were represented in a wide range of ages spanning the 18-year-old threshold. Individuals who had reached Stage RCW-C were all above the 18-year-old threshold. It was not possible to analyse a large number of DPTs for various reasons. Individuals categorised as stage RCW-C may be deemed to have reached the 18-year-old threshold. These results are consistent with other published studies. Variation in root morphology and in the rate of development of the third molar limits the applicability of this method. RCW staging is an accurate method of determining the 18-year-old threshold. Its limited applicability requires the use of substitute markers in a large number of cases.

Tooth recognition of 32 tooth types by branched single shot multibox detector and integration processing in panoramic radiographs.

Purpose: The purpose of our study was to analyze dental panoramic radiographs and contribute to dentists' diagnosis by automatically extracting the information necessary for reading them. As the initial step, we detected teeth and classified their tooth types in this study. Approach: We propose single-shot multibox detector (SSD) networks with a side branch for 1-class detection without distinguishing the tooth type and for 16-class detection (i.e., the central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, and third molar, distinguished by the upper and lower jaws). In addition, post-processing was conducted to integrate the results of the two networks and categorize them into 32 classes, differentiating between the left and right teeth. The proposed method was applied to 950 dental panoramic radiographs obtained at multiple facilities, including a university hospital and dental clinics. Results: The recognition performance of the SSD with a side branch was better than that of the original SSD. In addition, the detection rate was improved by the integration process. As a result, the detection rate was 99.03%, the number of false detections was 0.29 per image, and the classification rate was 96.79% for 32 tooth types. Conclusions: We propose a method for tooth recognition using object detection and post-processing. The results show the effectiveness of network branching on the recognition performance and the usefulness of post-processing for neural network output.

Correlations between skeletal maturity and dental calcification stages in Korean children.

To evaluate the relationship between dental calcification and skeletal maturity and to identify the tooth with the highest correlation with skeletal maturity index in Korean children. For 447 children (205 boys and 242 girls) aged between 5 and 13 years, hand-wrist and lateral cephalometric radiographs were taken to assess skeletal maturity by Fishman's skeletal maturity indicators (SMI) and Baccetti's cervical vertebrae maturation (CVM) stages. Dental panoramic radiographs were taken to assess dental maturity of the permanent mandibular canine, first and second premolar, and second molar using the method devised by Dermirjian. Dental calcification stages determined by panoramic radiographs can be clinically used as useful indices to predict skeletal maturity in Korean children.

Accuracy of Iranian Cameriere and Willems methods for estimating dental age in a population of Iranian children

Age estimation methods based on dental radiographs are of the most accurate and popular methods for age estimation. The accuracy of these methods might vary between different ethnic groups. Therefore, the present study was performed in order to evaluate and update the Cameriere dental age estimation method in a population of Iranian children and compare it with the Willems dental age estimation method. A retrospective cross-sectional study was performed, using dental records and digital dental panoramic radiographs of 110 six- to 12-year-old patients (55 girls and 55 boys). In order to assess the accuracy of both methods, the difference between the estimated dental age and the Chronological age was calculated and compared. Results of the present study showed Willems method overestimated the age and the updated Iranian Cameriere method underestimated the age, but the over/underestimations were not significant, except for the boys in Willems group. Both Willems dental age estimation (WDA) and Iranian Cameriere dental age estimation (ICDA) methods were applicable in the selected population of Iranian children, although the WDA estimations were less accurate, especially for boys.

Hybrid HCNN-KNN Model Enhances Age Estimation Accuracy in Orthopantomography.

Age estimation in dental radiographs Orthopantomography (OPG) is a medical imaging technique that physicians and pathologists utilize for disease identification and legal matters. For example, for estimating post-mortem interval, detecting child abuse, drug trafficking, and identifying an unknown body. Recent development in automated image processing models improved the age estimation's limited precision to an approximate range of +/- 1 year. While this estimation is often accepted as accurate measurement, age estimation should be as precise as possible in most serious matters, such as homicide. Current age estimation techniques are highly dependent on manual and time-consuming image processing. Age estimation is often a time-sensitive matter in which the image processing time is vital. Recent development in Machine learning-based data processing methods has decreased the imaging time processing; however, the accuracy of these techniques remains to be further improved. We proposed an ensemble method of image classifiers to enhance the accuracy of age estimation using OPGs from 1 year to a couple of months (1-3-6). This hybrid model is based on convolutional neural networks (CNN) and K nearest neighbors (KNN). The hybrid (HCNN-KNN) model was used to investigate 1,922 panoramic dental radiographs of patients aged 15 to 23. These OPGs were obtained from the various teaching institutes and private dental clinics in Malaysia. To minimize the chance of overfitting in our model, we used the principal component analysis (PCA) algorithm and eliminated the features with high correlation. To further enhance the performance of our hybrid model, we performed systematic image pre-processing. We applied a series of classifications to train our model. We have successfully demonstrated that combining these innovative approaches has improved the classification and segmentation and thus the age-estimation outcome of the model. Our findings suggest that our innovative model, for the first time, to the best of our knowledge, successfully estimated the age in classified studies of 1 year old, 6 months, 3 months and 1-month-old cases with accuracies of 99.98, 99.96, 99.87, and 98.78 respectively.

Dental Anomalies in Children with Cleft Lip and Palate at a Tertiary Care Hospital

Objective: To determine the dental anomalies in children with cleft lip and palate at a tertiary care hospital. Design of the Study: descriptive cross-sectional. Study Settings: Study was conducted at conducted in the OPD of Dentistry at Abbottabad International Medical Institute between the months of January 2021to June 2021. Material and Methods: The convenience sampling strategy was used to obtain the 208 radiographs of patients with cleft lip and/or palate for Data A. In order to conduct the study, the Institutional Review Board granted its approval. Radiographs were examined for suspected dental defects and demographic information was gathered. Results of the Study: A total of 76 (38 in group A and B) patients were included. Mean age in groups A and B was 39.25±3.91 and 38.71±4.01. Out of 38 patients in group A and B, effectiveness of large antecubital vein versus small vein on dorsum of hand in prevention of propofol injection was 81.6% vs. 36.87%. Conclusion: A high rate of dental abnormalities has been found in patients who have had a cleft lip or palate. The most common aberration in the study was tooth agenesis, with the lateral incisor having the highest rate of agenesis. Keywords: Dental Anomalies, Panoramic Radiograph, Cleft Lip and Palate

Tooth Localization using YOLOv3 for Dental Diagnosis on Panoramic Radiographs

Oral health is one of most major concerns that affect the life quality of billions of people around the world. Diagnosis treatment usually takes time due to the lack of doctors compared to a huge number of patients. Many researchers proposed methods to make an early disease detection for patients to assist doctors using computer aid diagnosis (CAD). However, most previous methods are not end-to-end methods and still require human involvement. The biggest challenge is that most researchers do not provide a good tooth detection technique before diagnosis. Therefore, the main objective, that builds a system to assist doctors, remains unaccomplished or just fairly successful. This paper proposed a detection method to localize the tooth using the Yolov3 model as a base network in the dental panoramic radiograph. The method consists of two main parts: image preprocessing and tooth localization. Firstly, because deep learning requires a big dataset, the original image is applied augmentation technique to improve the size of the dataset as well as diversity. Then, each image is resized to fit the input layer of the network; however, to prevent the information loss and boost the performance, we keep the original ratio of the images and change the ratio of the input layer in the model that can fit the image ratio. Next, we feed images into Yolov3, which is specially modified to fit the problem, for training. We add more detection heads into the backbone and concatenate the previous head detection's result with a proper layer to produce a more preeminent result. The final assessment shows an impressive result that the method reaches 95.58% and 94.90% for precision and recall, respectively. As a result, our proposed method is more reliable and practical in the tooth localization field, as well as helpful to reduce the doctor’s effort.

Identification of osteoporosis using ensemble deep learning model with panoramic radiographs and clinical covariates

Osteoporosis is becoming a global health issue due to increased life expectancy. However, it is difficult to detect in its early stages owing to a lack of discernible symptoms. Hence, screening for osteoporosis with widely used dental panoramic radiographs would be very cost-effective and useful. In this study, we investigate the use of deep learning to classify osteoporosis from dental panoramic radiographs. In addition, the effect of adding clinical covariate data to the radiographic images on the identification performance was assessed. For objective labeling, a dataset containing 778 images was collected from patients who underwent both skeletal-bone-mineral density measurement and dental panoramic radiography at a single general hospital between 2014 and 2020. Osteoporosis was assessed from the dental panoramic radiographs using convolutional neural network (CNN) models, including EfficientNet-b0, -b3, and -b7 and ResNet-18, -50, and -152. An ensemble model was also constructed with clinical covariates added to each CNN. The ensemble model exhibited improved performance on all metrics for all CNNs, especially accuracy and AUC. The results show that deep learning using CNN can accurately classify osteoporosis from dental panoramic radiographs. Furthermore, it was shown that the accuracy can be improved using an ensemble model with patient covariates.

Development and Validation of a Visually Explainable Deep Learning Model for Classification of C-shaped Canals of the Mandibular Second Molars in Periapical and Panoramic Dental Radiographs

IntroductionThe purpose of this study was to develop and validate a visually explainable deep learning model for the classification of C-shaped canals of the mandibular second molars in dental radiographs. MethodsThe periapical and panoramic images of 1000 mandibular second molars were collected from 372 patients. The diagnostic performance of the deep learning system using periapical and panoramic radiographs was investigated in respect to its ability to determine whether the second mandibular molar showed a C-shaped canal configuration. The assessment of the canal configuration of cone-beam computed tomographic volumes from 372 patients (740 mandibular second molars) was used as a gold standard. ResultsThe deep convolutional neural network algorithm model showed high accuracy in predicting the C-shaped canal variation among mandibular second molars in both periapical and panoramic images. The model demonstrated best results when using image patches including only the root portion of the tooth and when using both periapical and panoramic images for training (area under the curve [AUC] = 0.99). The model's diagnostic performance using only the root portion of the tooth (AUC: periapical = 0.98 and panoramic = 0.95) was similar to a specialist (AUC: periapical = 0.95 and panoramic = 0.96) and better than a novice general clinician (AUC: periapical = 0.89 and panoramic = 0.91). Both the specialist and general clinician showed better diagnostic performance when reading panoramic radiographs compared with periapical images. ConclusionsWith further optimization of the test data using a larger data set and improvements made in the model, a deep learning system may be expected to effectively diagnose C-shaped canals and aid clinicians in practice and education.

Tufts Dental Database: A Multimodal Panoramic X-Ray Dataset for Benchmarking Diagnostic Systems.

The application of Artificial Intelligence in dental healthcare has a very promising role due to the abundance of imagery and non-imagery-based clinical data. Expert analysis of dental radiographs can provide crucial information for clinical diagnosis and treatment. In recent years, Convolutional Neural Networks have achieved the highest accuracy in various benchmarks, including analyzing dental X-ray images to improve clinical care quality. The Tufts Dental Database, a new X-ray panoramic radiography image dataset, has been presented in this paper. This dataset consists of 1000 panoramic dental radiography images with expert labeling of abnormalities and teeth. The classification of radiography images was performed based on five different levels: anatomical location, peripheral characteristics, radiodensity, effects on the surrounding structure, and the abnormality category. This first-of-its-kind multimodal dataset also includes the radiologist's expertise captured in the form of eye-tracking and think-aloud protocol. The contributions of this work are 1) publicly available dataset that can help researchers to incorporate human expertise into AI and achieve more robust and accurate abnormality detection; 2) a benchmark performance analysis for various state-of-the-art systems for dental radiograph image enhancement and image segmentation using deep learning; 3) an in-depth review of various panoramic dental image datasets, along with segmentation and detection systems. The release of this dataset aims to propel the development of AI-powered automated abnormality detection and classification in dental panoramic radiographs, enhance tooth segmentation algorithms, and the ability to distill the radiologist's expertise into AI.

Detecting 17 fine-grained dental anomalies from panoramic dental radiography using artificial intelligence

Panoramic dental radiography is one of the most common examinations performed in dental clinics. Compared with other dental images, it covers a wide area from individual teeth to the maxilla and mandibular area. Dental clinicians can get much information about patients’ health. However, it is time-consuming and laborious to detect all signs of anomalies because these regions are very complicated. So it is needed to filter out healthy images to save clinicians’ time to examine. For this, we applied modern artificial intelligence-based computer vision techniques. In this study, we built a model to detect 17 fine-grained dental anomalies which are critical to patients’ dental health and quality of life. We used about 23,000 anonymized panoramic dental images taken from local dental clinics from July 2020 to July 2021. Our model can detect these abnormal signs and filter out normal images with high sensitivity of about 0.99. The result indicates that our model can be used in real clinical practice to alleviate the burden of clinicians.

Entrance Surface Dose Measurement at Thyroid and Parotid Gland Regions in Cone-Beam Computed Tomography and Panoramic Radiography

Purpose: Ionizing radiation-absorbed doses is a crucial concern in Cone-Beam Computed Tomography (CBCT) and panoramic radiography. This study aimed to evaluate and compare the Entrance Skin Doses (ESD) of thyroid and parotid gland regions in CBCT and panoramic radiography in Yazd province, Iran.&#x0D; Materials and Methods: In this cross-sectional study, 332 patients were included, who were then divided into two age groups (adult and pediatric) and underwent dental CBCT and panoramic radiography. Twelve Thermoluminescence Dosimeters (TLD- GR200) were used for each patient to measure the ESD of thyroid and parotid glands. The differences between the ESD values in CBCT and panoramic examinations as well as between the adults and children groups were evaluated by one-way ANOVA and Man-Whitney tests.&#x0D; Results: The mean and Standard Deviation (SD) values of ESD in panoramic imaging were equal to 61 ± 4 and 290 ± 12 µGy for the thyroid and parotid glands of the adult groups, respectively. Notably, these values for CBCT were significantly higher (P&lt;0.01), as 377 ± 139 and 1554 ± 177 µGy, respectively. Moreover, the mean ESD values in the panoramic examination were 41 ± 3 and 190 ± 16 µGy for thyroid and parotid glands for the children group, while they were 350 ± 120 and 990 ± 107 µGy in CBCT (P&lt;0.01), respectively. The ESD values in the parotid gland were approximately 3.4 (2.8-4.1) and 4.7 (4.6-4.8) times greater than those for CBCT and panoramic examinations, respectively.&#x0D; Conclusion: Although CBCT provides supplementary diagnostic advantages, the thyroid and parotid glands’ doses are higher than panoramic radiography. Therefore, the risks and benefits of each method should be considered before their prescription.

Age estimation using the London Atlas in a Thai population

ABSTRACT Dental development and eruption charts are widely used to evaluate chronological age and physical maturity, especially in children and adolescents. The objective of this study was to test the accuracy of the London Atlas dental age estimation method in Thai samples. This study consisted of digital panoramic radiographs of Thai individuals (n = 396) aged between 7 and 15 years (198 males and 198 females). The accuracy of age estimation using the London Atlas method was evaluated on the pooled and split sex sample using digital panoramic dental radiographs. The results showed that there was no significant difference between the dental age and the chronological age for pooled sex group (p = 0.115). The mean error values were −0.19 years in males, 0.33 years in females, and 0.07 years for the pooled sample. Moreover, the mean absolute error values were 0.71 years in males, 0.67 years in females, and 0.69 years for the pooled sample. In conclusion, the London Atlas method has potential for application for age estimation in a Thai population.

A Radiographic Study of the Root-to-Crown Ratio of Natural Permanent Teeth in 81 Saudi Adults.

BackgroundThe ratio between a tooth root and its crown is an essential diagnostic parameter that determines treatment options. This radiographic study used panoramic dental radiographs or orthopantograms to measure the mean root (R)-to-crown (C) ratios (R/C) of the permanent teeth in 81 Saudi adults.Material/MethodsA total of 81 panoramic radiographs of Saudi adult patients (40 males and 41 females) previously treated in the College of Dentistry, Saudi Arabia, aged 16–35 years, were selected. The crown height and root length for each tooth were measured on the digital panoramic radiographs. The correlation coefficient (intra-class) was calculated to assess the intra-examiner reproducibility and a good agreement was achieved (ICC=0.79–0.89).ResultsFor both males and females, the highest mean R/C ratio was for maxillary canine (1.91) and for mandibular second premolar (2.0) while the lowest R/C ratio was for maxillary first molar (1.64) and for mandibular central incisor (1.59). Except for the maxillary second premolar, no significant differences in R/C ratios were observed for maxillary arch. In the mandibular arch, the R/C ratio for lateral incisor, both premolars, and molars differed significantly (P<0.05). Among males, statistically significant differences between teeth existed in R/C ratios for central and lateral incisors, second premolar, and both molars (P>0.05). For females, significant differences between teeth in R/C ratios were observed for both premolars and both molars (P>0.05).ConclusionsThis study supports the findings from previous studies that orthopantograms can be used to calculate root/crown ratios, which varies between males and females and the dental arch among Saudi adults.

Tooth Instance Segmentation on Panoramic Dental Radiographs Using U-Nets and Morphological Processing

Automatic teeth segmentation in panoramic x-ray images is an important research subject of the image analysis in dentistry. In this study, we propose a post-processing stage to obtain a segmentation map in which the objects in the image are separated, and apply this technique to tooth instance segmentation with U-Net network. The post-processing consists of grayscale morphological and filtering operations, which are applied to the sigmoid output of the network before binarization. A dice overlap score of 95.4±0.3% is obtained in overall teeth segmentation. The proposed post-processing stages reduce the mean error of tooth count to 6.15%, whereas the error without post-processing is 26.81%. The performances of both segmentation and tooth counting are the highest in the literature, to our knowledge. Moreover, this is achieved by using a relatively small training dataset, which consists of 105 images. Although the aim in this study is to segment tooth instances, the presented method is applicable to similar problems in other domains, such as separating the cell instances.