ABSTRACT
OBJECTIVE: The purpose of the study was to create an artificial intelligence (AI) system for detecting idiopathic osteosclerosis (IO) on panoramic radiographs for automatic, routine, and simple evaluations. SUBJECT AND METHODS: In this study, a deep learning method was carried out with panoramic radiographs obtained from healthy patients. 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 archives of the Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University. GoogLeNet Inception v2 model implemented with TensorFlow library was used for the detection of IOs. Confusion matrix was used to predict model achievements. RESULTS: Fifty IOs were detected accurately 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. CONCLUSION: Deep learning-based AI algorithm has the potential to detect IOs accurately on panoramic radiographs. AI systems may reduce the workload of dentists in terms of diagnostic efforts.
Subject(s)
Deep Learning , Osteosclerosis , Humans , Artificial Intelligence , Radiography, Panoramic , Algorithms , Osteosclerosis/diagnostic imagingABSTRACT
Objectives: To compare the volume and voxel intensity of articular disc and lateral pterygoid muscle (LPM) between a group of migraine patients and a control group (those without history of headache) by using magnetic resonance imaging (MRI).Patients and methods: MRI scans of 17 migraine patients and 15 healthy controls subjects were analysed and processed, using ITK-SNAP software, by a single investigator, for calculation of volumes and voxel intensity of articular disc and superior and inferior head of LPM.Results: There were statistically significant differences between migraine patients and controls regarding the volume and voxel intensity of articular disc and inferior head of LPM, increasing in migraine patients. Intra-rater was highly consistent and reproducible (intra-class correlation coefficient [ICC] = 1).Conclusions: Higher voxel intensity in disc and inferior head of LPM of MRI scans was linked to the increased volume of articular disc, inferior head of LPM and migraine.
Subject(s)
Magnetic Resonance Imaging/methods , Migraine Disorders/diagnosis , Pterygoid Muscles/diagnostic imaging , Temporomandibular Joint/diagnostic imaging , Adolescent , Adult , Aged , Case-Control Studies , Female , Humans , Male , Middle Aged , Young AdultABSTRACT
PURPOSE: The sphenoid sinus is the most inaccessible part of the face, being inside the sphenoid bone and closely related to numerous vital neural and vascular structures. The objective of this study was to analyze and evaluate the variation of anatomy and the volume of the sphenoid sinus using helical computed tomography and medical imaging software. MATERIALS AND METHODS: A total of 47 helical CT scans of sinuses of male and female individuals aged 18-86 years were selected. The images were formatted using ITK-SNAP software, consisting of three steps: (1) segmentation; (2) volumetric analysis and (3) 3D reconstruction. The sphenoid sinuses were also classified according to Hammer, i.e., in conchal, pre-sellar, sellar and post-sellar types. A single investigator, who is specialist in dental radiology and was trained and calibrated, performed the volume and image analysis. After 15 days, the segmentations were repeated. RESULTS: The Dunn's multiple comparison test revealed significant differences in the volume rankings between the right and left sides (P = 0.0002), with the post-sellar type presenting the greatest volume on the right side compared to pre-sellar and sellar types. In the left sphenoid sinuses, the post-sellar type showed the greatest volume. The Lin's correlation coefficient showed excellent reproducibility values. CONCLUSIONS: According to the applied methodology, it was found that the volume of the sphenoid sinus was influenced by neither age nor gender (P > 0.005). There was difference in the volumes of sphenoid sinus on the right and left sides and in the anatomical classification.
Subject(s)
Anatomic Variation , Sphenoid Bone/anatomy & histology , Sphenoid Sinus/anatomy & histology , Adolescent , Adult , Age Factors , Aged , Aged, 80 and over , Female , Humans , Image Processing, Computer-Assisted , Male , Middle Aged , Reproducibility of Results , Sex Factors , Sphenoid Bone/diagnostic imaging , Sphenoid Sinus/diagnostic imaging , Tomography, Spiral Computed , Young AdultABSTRACT
AIM: The purpose of this study was to evaluate the dentoskeletal and soft tissue effects resulting from treatment with Klammt's elastic open activator (EOA) functional orthopedic appliance in patients with Class II malocclusion characterized by mandibular deficiency. MATERIALS AND METHODS: Teleradiographs were evaluated in the lateral aspect of the initial (T1) and final (T2) orthopedic phases for 16 patients with Class II, Division 1 malocclusion. The age range was from 9 to 11.2 years, with a mean age of 9.9 years. The cephalometric points were demarcated, and cephalometric measurements were obtained by the same investigator to avoid interobserver variability. RESULTS: The EOA promoted increased lower anterior facial height (LAFH), increased effective mandibular length, clockwise rotation of the mandible, retrusion and verticalization of the upper incisors, proclination and protrusion of the lower incisors, extrusion of the upper molars, mesial movement of the lower molars and anterior projection of the lower lip. CONCLUSION: Skeletal changes characterized by an increase in mandibular length and dentoalveolar changes with an emphasis on the verticalization and retrusion of the upper incisors, proclination of the lower incisors and mesial positioning of the lower molars were key to improving the occlusal relationship and esthetic facial factors. CLINICAL SIGNIFICANCE: The EOA is well indicated in patients with Class II malocclusion due to mandibular deficiency with increased overbite, proclined upper incisors and verticalized lower incisors.
Subject(s)
Activator Appliances , Malocclusion, Angle Class II/therapy , Cephalometry , Child , Female , Humans , Male , Malocclusion , MandibleABSTRACT
Introduction Onodi cells (OCs) are posterior ethmoid cells that are located above the sphenoid sinus, close to or even surrounding the carotid artery and optic nerve. Objective To investigate and evaluate the volumetric variation of OCs through multi-slice computed tomography (MSCT) scans. Methods We performed a retrospective review of MSCT scans of 79 subjects, 40 male and 39 female patients, Whose age ranged from 18 to 83 (mean: 39.6) years. The volumes of the OCs on the right and left sides were measured using the ITK-SNAP software (open-source) with semiautomatic segmentation. The possible relationships involving age, gender, contact with the optic nerve, extension of the pneumatization of the posterior ethmoid cells into the clinoid processes, mucous thickening in the anterior and posterior ethmoid cells, and obliteration of the sphenoethmoidal complex were analyzed with the Pearson correlation and Chi-squared tests according to the type of data compared and logistic regression models ( p < 0.05). Results We observed that an increase of one unit in the volume of OCs also increases the chance of extension of pneumatization into the clinoid processes by 0.15% ( p = 0.001). No significant correlations were identified regarding age, gender, and volume of the OCs. Conclusion The volume of the OCs has effects on the extension of pneumatization into the clinoid processes.
ABSTRACT
The purpose of this study was to identify changes in the temporomandibular joint disc affected by effusion by using texture analysis of magnetic resonance images (MRIs). METHODS: A total of 223 images of the TMJ, 42 with joint effusion and 181 without, were analyzed. Three consecutive slices were then exported to MaZda software, in which two oval ROIs (one in the anterior band and another in the intermediate zone of the joint disc) were determined in each slice and eleven texture parameters were calculated by using a gray-level co-occurrence matrix. Spearman's correlation coefficient test was used to assess the correlation between texture variables and to select variables for analysis. The Mann-Whitney test was used to compare the groups. RESULTS: The significance level was set at 5%, with the results demonstrating that there was no high correlation between the parameter directions. It was possible to observe a trend between the average parameters, in which the group with effusion always had smaller values than the group without effusion, except for the parameter measuring the difference in entropy. CONCLUSION: The trend towards lower overall values for the texture parameters suggested a different behavior between TMJ discs affected by effusion and those not affected, indicating that there may be intrinsic changes.
ABSTRACT
This study explores the efficacy of texture analysis by using preoperative multi-slice spiral computed tomography (MSCT) to non-invasively determine the grade of cellular differentiation in head and neck squamous cell carcinoma (HNSCC). In a retrospective study, MSCT scans of patients with HNSCC were analyzed and classified based on its histological grade as moderately differentiated, well-differentiated, or poorly differentiated. The location of the tumor was categorized as either in the bone or in soft tissues. Segmentation of the lesion areas was conducted, followed by texture analysis. Eleven GLCM parameters across five different distances were calculated. Median values and correlations of texture parameters were examined in relation to tumor differentiation grade by using Spearman's correlation coefficient and Kruskal-Wallis and Dunn tests. Forty-six patients were included, predominantly female (87%), with a mean age of 66.7 years. Texture analysis revealed significant parameter correlations with histopathological grades of tumor differentiation. The study identified no significant age correlation with tumor differentiation, which underscores the potential of texture analysis as an age-independent biomarker. The strong correlations between texture parameters and histopathological grades support the integration of this technique into the clinical decision-making process.
ABSTRACT
BACKGROUND: Torquetenovirus (TTV) is a small DNA virus constituting the human virome. High levels of TTV-DNA have been shown to be associated with immunosuppression and inflammatory chronic disorders. AIM: To assess the possible association between the salivary viral load of TTV-DNA in patients hospitalised due to COVID-19 and disease severity. METHODS: Saliva samples collected from 176 patients infected with SARS-CoV-2 were used to investigate the presence of SARS-CoV-2 and TTV-DNA by use of real-time RT-PCR. RESULTS: The majority of patients were male with severe COVID-19. Presence of SARS-CoV-2 was observed in the saliva of 64.77% of patients, showing TTV-DNA in 55.68% of them. Patients with impaired clinical conditions (p < 0.001), which evolved to death (p = 0.003), showed a higher prevalence of TTV-DNA. The median viral load in patients with severe condition was 4.99 log10 copies/mL, in which those who were discharged and those evolving to death had values of 3.96 log10 copies/mL and 6.27 log10 copies/mL, respectively. A statistically significant association was found between the distribution of TTV-DNA viral load in saliva samples and severity of COVID-19 (p = 0.004) and disease outcomes (p < 0.001). CONCLUSIONS: These results indicate that TTV-DNA in saliva could be a useful biomarker of COVID-19 severity and prognosis.
Subject(s)
COVID-19 , SARS-CoV-2 , Saliva , Severity of Illness Index , Torque teno virus , Viral Load , Virus Shedding , Humans , Male , Saliva/virology , COVID-19/virology , Female , Middle Aged , SARS-CoV-2/genetics , SARS-CoV-2/isolation & purification , Aged , Torque teno virus/isolation & purification , Torque teno virus/genetics , Adult , Hospitalization , DNA, Viral/genetics , Aged, 80 and over , DNA Virus Infections/virologyABSTRACT
OBJECTIVES: Artificial intelligence (AI) techniques like convolutional neural network (CNN) are a promising breakthrough that can help clinicians analyze medical imaging, diagnose taurodontism, and make therapeutic decisions. The purpose of the study is to develop and evaluate the function of CNN-based AI model to diagnose teeth with taurodontism in panoramic radiography. METHODS: 434 anonymized, mixed-sized panoramic radiography images over the age of 13 years were used to develop automatic taurodont tooth segmentation models using a Pytorch implemented U-Net model. Datasets were split into train, validation, and test groups of both normal and masked images. The data augmentation method was applied to images of trainings and validation groups with vertical flip images, horizontal flip images, and both flip images. The Confusion Matrix was used to determine the model performance. RESULTS: Among the 43 test group images with 126 labels, there were 109 true positives, 29 false positives, and 17 false negatives. The sensitivity, precision, and F1-score values of taurodont tooth segmentation were 0.8650, 0.7898, and 0.8257, respectively. CONCLUSIONS: CNN's ability to identify taurodontism produced almost identical results to the labeled training data, and the CNN system achieved close to the expert level results in its ability to detect the taurodontism of teeth.
Subject(s)
Artificial Intelligence , Deep Learning , Radiography, Panoramic , Neural Networks, Computer , AlgorithmsABSTRACT
OBJECTIVE: To assess volume and surface of the mandibular condyle on cone beam computed tomography (CBCT) scans by comparing Class I, II, and III malocclusions. METHODS: CBCT scans of 55 patients were assessed to measure ANB angle, condyle volume, and surface by using VistaDent software. The values were compared between the different skeletal malocclusions and correlated to gender and sides. Kruskal-Wallis test was used for comparison of malocclusions and Mann-Whitney test and Wilcoxon test for comparisons of genders and sides. Statistical significance was defined as p < 0.05. RESULTS: There were no significant differences in volume (p = 0.588) and surface (p = 0.830) between the malocclusion classes. The comparison between sides showed a statistically significant difference for surface (p = 0.038). CONCLUSION: Condylar volume and surface evaluated on CBCT scans showed no statistically different values for Class I, II, and III malocclusions.
Subject(s)
Malocclusion, Angle Class II , Malocclusion , Spiral Cone-Beam Computed Tomography , Humans , Female , Male , Malocclusion/diagnostic imaging , Mandibular Condyle/diagnostic imaging , Cone-Beam Computed Tomography/methods , Cephalometry/methods , Imaging, Three-Dimensional/methodsABSTRACT
Purpose: The aim of this study was to evaluate changes in the trabecular bone through texture analysis and compare the texture analysis characteristics of different areas in patients with medication-related osteonecrosis of the jaw (MRONJ). Materials and Methods: Cone-beam computed tomographic images of 16 patients diagnosed with MRONJ were used. In sagittal images, 3 regions were chosen: active osteonecrosis (AO); intermediate tissue (IT), which presented a zone of apparently healthy tissue adjacent to the AO area; and healthy bone tissue (HT) (control area). Texture analysis was performed evaluating 7 parameters: secondary angular momentum, contrast, correlation, sum of squares, inverse moment of difference, sum of entropies, and entropy. Data were analyzed using the Kruskal-Wallis test with a significance level of 5%. Results: Comparing the areas of AO, IT, and HT, significant differences (P<0.05) were observed. The IT and AO area images showed higher values for parameters such as contrast, entropy, and secondary angular momentum than the HT area, indicating greater disorder in these tissues. Conclusion: Through texture analysis, changes in the bone pattern could be observed in areas of osteonecrosis. The texture analysis demonstrated that areas visually identified and classified as IT still had necrotic tissue, thereby increasing the accuracy of delimiting the real extension of MRONJ.
ABSTRACT
OBJECTIVES: Juvenile idiopathic arthritis (JIA) is a chronic inflammatory disease that affects the joints and other organs, including the development of the former in a growing child. This study aimed to evaluate the feasibility of texture analysis (TA) based on magnetic resonance imaging (MRI) to provide biomarkers that serve to identify patients likely to progress to temporomandibular joint damage by associating JIA with age, gender and disease onset age. METHODS: The radiological database was retrospectively reviewed. A total of 45 patients were first divided into control group (23) and JIA group (22). TA was performed using grey-level co-occurrence matrix (GLCM) parameters, in which 11 textural parameters were calculated using MaZda software. These 11 parameters were ranked based on the p value obtained with ANOVA and then correlated with age, gender and disease onset age. RESULTS: Significant differences in texture parameters of condyle were demonstrated between JIA group and control group (p < 0.05). There was a progressive loss of uniformity in the grayscale pixels of MRI with an increasing age in JIA group. CONCLUSIONS: MRI TA of the condyle can make it possible to detect the alterations in bone marrow of patients with JIA and promising tool which may help the image analysis.
Subject(s)
Arthritis, Juvenile , Mandibular Condyle , Child , Humans , Mandibular Condyle/diagnostic imaging , Mandibular Condyle/pathology , Arthritis, Juvenile/diagnostic imaging , Arthritis, Juvenile/complications , Retrospective Studies , Temporomandibular Joint , Magnetic Resonance Imaging/methodsABSTRACT
OBJECTIVE: Texture analysis is an image processing method that aims to assess the distribution of gray-level intensity and spatial organization of the pixels in the image. The purpose of this study was to investigate whether the texture analysis applied to cone beam computed tomography (CBCT) images could detect variation in the condyle trabecular bone of individuals from different age groups and genders. METHODS: The sample consisted of imaging exams from 63 individuals divided into three groups according to age groups of 03-13, 14-24 and 25-34. For texture analysis, the MaZda® software was used to extract the following parameters: second angular momentum, contrast, correlation, sum of squares, inverse difference moment, sum entropy and entropy. Statistical analysis was performed using Mann-Whitney test for gender and Kruskal-Wallis test for age (P = 5%). RESULTS: No statistically significant differences were found between age groups for any of the parameters. Males had lower values for the parameter correlation than those of females (P < 0.05). CONCLUSION: Texture analysis proved to be useful to discriminate mandibular condyle trabecular bone between genders.
Subject(s)
Cone-Beam Computed Tomography , Mandibular Condyle , Humans , Male , Female , Mandibular Condyle/diagnostic imaging , Cone-Beam Computed Tomography/methods , Image Processing, Computer-Assisted/methods , Cancellous BoneABSTRACT
This study aims to develop an algorithm for the automatic segmentation of the parotid gland on CT images of the head and neck using U-Net architecture and to evaluate the model's performance. In this retrospective study, a total of 30 anonymized CT volumes of the head and neck were sliced into 931 axial images of the parotid glands. Ground truth labeling was performed with the CranioCatch Annotation Tool (CranioCatch, Eskisehir, Turkey) by two oral and maxillofacial radiologists. The images were resized to 512 × 512 and split into training (80%), validation (10%), and testing (10%) subgroups. A deep convolutional neural network model was developed using U-net architecture. The automatic segmentation performance was evaluated in terms of the F1-score, precision, sensitivity, and the Area Under Curve (AUC) statistics. The threshold for a successful segmentation was determined by the intersection of over 50% of the pixels with the ground truth. The F1-score, precision, and sensitivity of the AI model in segmenting the parotid glands in the axial CT slices were found to be 1. The AUC value was 0.96. This study has shown that it is possible to use AI models based on deep learning to automatically segment the parotid gland on axial CT images.
ABSTRACT
Purpose: This study aimed to assess texture analysis (TA) of cone-beam computed tomography (CBCT) images as a quantitative tool for the differential diagnosis of odontogenic and non-odontogenic maxillary sinusitis (OS and NOS, respectively). Materials and Methods: CBCT images of 40 patients diagnosed with OS (N=20) and NOS (N=20) were evaluated. The gray level co-occurrence (GLCM) matrix parameters, and gray level run length matrix texture (GLRLM) parameters were extracted using manually placed regions of interest on lesion images. Seven texture parameters were calculated using GLCM and 4 parameters using GLRLM. The Mann-Whitney test was used for comparisons between the groups, and the Levene test was performed to confirm the homogeneity of variance (α=5%). Results: The results showed statistically significant differences (P<0.05) between the OS and NOS patients regarding 3 TA parameters. NOS patients presented higher values for contrast, while OS patients presented higher values for correlation and inverse difference moment. Greater textural homogeneity was observed in the OS patients than in the NOS patients, with statistically significant differences in standard deviations between the groups for correlation, sum of squares, sum of entropy, and entropy. Conclusion: TA enabled quantitative differentiation between OS and NOS on CBCT images by using the parameters of contrast, correlation, and inverse difference moment.
ABSTRACT
This study aims to investigate the effect of using an artificial intelligence (AI) system (Diagnocat, Inc., San Francisco, CA, USA) for caries detection by comparing cone-beam computed tomography (CBCT) evaluation results with and without the software. 500 CBCT volumes are scored by three dentomaxillofacial radiologists for the presence of caries separately on a five-point confidence scale without and with the aid of the AI system. After visual evaluation, the deep convolutional neural network (CNN) model generated a radiological report and observers scored again using AI interface. The ground truth was determined by a hybrid approach. Intra- and inter-observer agreements are evaluated with sensitivity, specificity, accuracy, and kappa statistics. A total of 6008 surfaces are determined as 'presence of caries' and 13,928 surfaces are determined as 'absence of caries' for ground truth. The area under the ROC curve of observer 1, 2, and 3 are found to be 0.855/0.920, 0.863/0.917, and 0.747/0.903, respectively (unaided/aided). Fleiss Kappa coefficients are changed from 0.325 to 0.468, and the best accuracy (0.939) is achieved with the aided results. The radiographic evaluations performed with aid of the AI system are found to be more compatible and accurate than unaided evaluations in the detection of dental caries with CBCT images.
ABSTRACT
OBJECTIVES: This study aimed to assess the morphological differences in the articular disc (AD) between hemophilic patients and healthy individuals of the control group for further association with signs and symptoms. METHODS: Fourteen severe hemophilic patients had their AD evaluated by magnetic resonance imaging (MRI). The morphological findings were compared to those of a control group consisting of 14 healthy individuals. MRI was used to evaluate all the components of the temporomandibular (TMJ), including the AD, resulting in sequential T1-weighted parasagittal images. All the images were acquired with teeth in maximum intercuspation position. RESULTS: Morphological alterations showed significant statistical differences (P-value = 0.0068), whereas no statistical differences were found in the other variables, including TMJ pain, headache, bruxism and mouth opening limitation. In the group of non-hemophilic individuals, only two (14.29%) presented AD with non-biconcave features, whereas in the group of hemophilic patients, nine (64.29%) presented AD with a morphology other than biconcave. CONCLUSIONS: In patients with severe hemophilia, there seems to be a pattern of morphological alterations in the articular disc over time. The standard biconcave morphology of AD tends to change into other ones, particularly biplanar, hemiconvex and folded.
Subject(s)
Hemophilia A , Temporomandibular Joint Disorders , Humans , Temporomandibular Joint Disc/diagnostic imaging , Hemophilia A/diagnostic imaging , Hemophilia A/pathology , Temporomandibular Joint Disorders/diagnostic imaging , Temporomandibular Joint Disorders/pathology , Temporomandibular Joint , Magnetic Resonance Imaging/methodsABSTRACT
INTRODUCTION: The present study evaluated the effect of two protocols of Pulsed Electromagnetic Field (PEMF) therapy on bone neoformation on calvaria critical defects in rats. MATERIAL & METHODS: 96 rats were randomly divided into 3 groups: Control Group (CG; n=32); Test Group - PEMF 1 hour (TG1h; n=32) and Test Group - PEMF 3 hour (TG3h; n=32). A Critical-size Bone Defect (CSD) was surgically created in the calvaria of rats. The animals in the test groups were exposure to PEMF for 5 days a week. The animals were euthanized at 14, 21, 45 and 60 days. The specimens were processed for volume and texture (TAn) analysis, by Cone Beam Computed Tomography (CBCT) and histomorphometric analysis, RESULTS: Histomorphometric and volume analyses revealed that there was no statistically significant difference in the repair of bone defects between groups receiving PEMF therapy and CG. TAn revealed a statistically significant difference between the groups only for the entropy parameter, in which TG1h group presented a higher value compared to CG on 21 days. TG1h and TG3h did not accelerate bone repair in calvarial critical size defect and the parameters of PEMF should be considered. DISCUSSION: This study showed that PEMF application on CSD in rats does not accelerate bone repair. Although literature showed a positive association in biostimulation on bone tissue with the parameters applied, studies with other PEMF parameters are essential to verify improving this study design.
Subject(s)
Electromagnetic Fields , Spiral Cone-Beam Computed Tomography , Rats , Humans , Animals , Skull/surgery , Cone-Beam Computed TomographyABSTRACT
OBJECTIVE: The aim of this study was to investigate the TMJ components in patients with juvenile idiopathic arthritis (JIA) and to compare them with a control group based on magnetic resonance imaging (MRI) measurements. METHODS: This study comprised an assessment of MRI measurements of 96 temporomandibular joints (TMJ) following classification criteria set by the International League of Associations for Rheumatology (ILAR). Three measurements were considered for study: condyle excursion angle (CEA), height of articular eminence (HAE) and inclination of articular eminence (IAE). All TMJs were assessed by linear measurements made by using the OnDemand 3D software. The comparison between the groups was performed by using Mann-Whitney's test. RESULTS: Lower measurement values were found for IAE, HAE and CEA in JIA patients (P-values < 0.001, 0.005 and < 0.001, respectively). CONCLUSION: The study showed the differences in MRI measurements between JIA patients and controls, with the former with the lowest indices.
Subject(s)
Arthritis, Juvenile , Temporomandibular Joint Disorders , Arthritis, Juvenile/diagnostic imaging , Arthritis, Juvenile/pathology , Humans , Magnetic Resonance Imaging/methods , Retrospective Studies , Temporomandibular Joint/diagnostic imaging , Temporomandibular Joint Disorders/diagnostic imagingABSTRACT
In the present study, we aimed to assess frontal ethmoidal cells by using segmentation 3D software to establish a possible correlation between volume variation and both gender and age, as well as a relationship with Keros classification. Helical computed tomography images were obtained from 71 patients for analysis, in which the agger nasi cell, supra agger cell, supra agger frontal cell, supra bulla frontal cell, supraorbital ethmoidal cell, supra bulla cell, and frontal septal cell were identified and segmented to obtain their volume. Significant differences in volume were found for age and gender regarding agger nasi cells (p-value = 0.017), supra agger cells (p-value < 0.001), and frontal septal cells (p-value = 0.049). In the frontal septal cells, an increase of one year in age reduced the volume by 0.309, on average. According to Keros classification, the mean volumes were 10.07 and 25.64, respectively, for types II and III, both being greater than that of type I. Extracting volumetric data by using segmentation software in agger nasi cells, supra agger cells, and frontal septal cells may be useful for obtaining additional information related to age, in addition to possibly contributing to elucidating the anatomical variations in the region and an identification forensic tool.