Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population.

Sex and chronological age estimation are crucial in forensic investigations and research on individual identification. Although manual methods for sex and age estimation have been proposed, these processes are labor-intensive, time-consuming, and error-prone. The purpose of this study was to estimate sex and chronological age from panoramic radiographs automatically and robustly using a multi-task deep learning network (ForensicNet). ForensicNet consists of a backbone and both sex and age attention branches to learn anatomical context features of sex and chronological age from panoramic radiographs and enables the multi-task estimation of sex and chronological age in an end-to-end manner. To mitigate bias in the data distribution, our dataset was built using 13,200 images with 100 images for each sex and age range of 15-80 years. The ForensicNet with EfficientNet-B3 exhibited superior estimation performance with mean absolute errors of 2.93 ± 2.61 years and a coefficient of determination of 0.957 for chronological age, and achieved accuracy, specificity, and sensitivity values of 0.992, 0.993, and 0.990, respectively, for sex prediction. The network demonstrated that the proposed sex and age attention branches with a convolutional block attention module significantly improved the estimation performance for both sex and chronological age from panoramic radiographs of elderly patients. Consequently, we expect that ForensicNet will contribute to the automatic and accurate estimation of both sex and chronological age from panoramic radiographs.

Developing a three-dimensional statistical shape model of normal dentition using an automated algorithm and normal samples.

OBJECTIVES: The statistical shape model (SSM) is a model of geometric properties of a set of shapes based on statistical shape analysis. The SSM develops an average model of several objects using an automated algorithm that excludes the operator's subjectivity. The aim of this study was to develop a three-dimensional (3D) SSM of normal dentition to provide virtual templates for efficient treatment. MATERIALS AND METHODS: Dental casts were obtained from participants with normal dentition. After acquiring the 3D models, the SSMs of the individual teeth and whole dental arch were generated by an iterative closest point (ICP)-based rigid registration and point correspondences, respectively. Then, the individual tooth SSM was aligned to the whole dental arch SSM using ICP-based registration to generate an average model of normal dentition. RESULTS: The generated 3D SSM showed specific morphological features of normal dentition similar to those previously reported. Moreover, on measuring the arch dimensions, all values in this study were similar to those previously reported using normal dentition. CONCLUSIONS: The 3D SSM of normal dentition may increase the diagnostic efficiency of orthodontic treatments by providing a visual objective. It can be also used as a 3D template in various fields of dentistry. CLINICAL RELEVANCE: Our SSM of normal dentition provides both quantitative and qualitative information on the 3D morphology of teeth and dental arches, which may provide valuable information on 3D virtual-setup, bracket fabrication, and aligner treatment.

Ceph-Net: automatic detection of cephalometric landmarks on scanned lateral cephalograms from children and adolescents using an attention-based stacked regression network.

BACKGROUND: The success of cephalometric analysis depends on the accurate detection of cephalometric landmarks on scanned lateral cephalograms. However, manual cephalometric analysis is time-consuming and can cause inter- and intra-observer variability. The purpose of this study was to automatically detect cephalometric landmarks on scanned lateral cephalograms with low contrast and resolution using an attention-based stacked regression network (Ceph-Net). METHODS: The main body of Ceph-Net compromised stacked fully convolutional networks (FCN) which progressively refined the detection of cephalometric landmarks on each FCN. By embedding dual attention and multi-path convolution modules in Ceph-Net, the network learned local and global context and semantic relationships between cephalometric landmarks. Additionally, the intermediate deep supervision in each FCN further boosted the training stability and the detection performance of cephalometric landmarks. RESULTS: Ceph-Net showed a superior detection performance in mean radial error and successful detection rate, including accuracy improvements in cephalometric landmark detection located in low-contrast soft tissues compared with other detection networks. Moreover, Ceph-Net presented superior detection performance on the test dataset split by age from 8 to 16 years old. CONCLUSIONS: Ceph-Net demonstrated an automatic and superior detection of cephalometric landmarks by successfully learning local and global context and semantic relationships between cephalometric landmarks in scanned lateral cephalograms with low contrast and resolutions.

Comparison of 2D, 2.5D, and 3D segmentation networks for maxillary sinuses and lesions in CBCT images.

BACKGROUND: The purpose of this study was to compare the segmentation performances of the 2D, 2.5D, and 3D networks for maxillary sinuses (MSs) and lesions inside the maxillary sinus (MSL) with variations in sizes, shapes, and locations in cone beam CT (CBCT) images under the same constraint of memory capacity. METHODS: The 2D, 2.5D, and 3D networks were compared comprehensively for the segmentation of the MS and MSL in CBCT images under the same constraint of memory capacity. MSLs were obtained by subtracting the prediction of the air region of the maxillary sinus (MSA) from that of the MS. RESULTS: The 2.5D network showed the highest segmentation performances for the MS and MSA compared to the 2D and 3D networks. The performances of the Jaccard coefficient, Dice similarity coefficient, precision, and recall by the 2.5D network of U-net + + reached 0.947, 0.973, 0.974, and 0.971 for the MS, respectively, and 0.787, 0.875, 0.897, and 0.858 for the MSL, respectively. CONCLUSIONS: The 2.5D segmentation network demonstrated superior segmentation performance for various MSLs with an ensemble learning approach of combining the predictions from three orthogonal planes.

Automatic classification of 3D positional relationship between mandibular third molar and inferior alveolar canal using a distance-aware network.

The purpose of this study was to automatically classify the three-dimensional (3D) positional relationship between an impacted mandibular third molar (M3) and the inferior alveolar canal (MC) using a distance-aware network in cone-beam CT (CBCT) images. We developed a network consisting of cascaded stages of segmentation and classification for the buccal-lingual relationship between the M3 and the MC. The M3 and the MC were simultaneously segmented using Dense121 U-Net in the segmentation stage, and their buccal-lingual relationship was automatically classified using a 3D distance-aware network with the multichannel inputs of the original CBCT image and the signed distance map (SDM) generated from the segmentation in the classification stage. The Dense121 U-Net achieved the highest average precision of 0.87, 0.96, and 0.94 in the segmentation of the M3, the MC, and both together, respectively. The 3D distance-aware classification network of the Dense121 U-Net with the input of both the CBCT image and the SDM showed the highest performance of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve, each of which had a value of 1.00. The SDM generated from the segmentation mask significantly contributed to increasing the accuracy of the classification network. The proposed distance-aware network demonstrated high accuracy in the automatic classification of the 3D positional relationship between the M3 and the MC by learning anatomical and geometrical information from the CBCT images.

Correlation between spatial resolution and ball distortion rate of panoramic radiography.

BACKGROUND: The purpose of this study was to analyze the correlation between spatial resolution and ball distortion rate of panoramic radiography and to elucidate the minimum criterion for ball distortion rate, which is very relevant to clinical readability. METHODS: Horizontal and vertical spatial resolution and ball distortion rates were calculated in the same position, such as the incisor, premolar, molar, and temporomandibular joint area with various object depths corresponding to 48 mm. Three devices were evaluated. A region showing spatial resolution above the reference standard was selected, and the ball distortion rate corresponding to the same region was divided into horizontal and vertical phantom groups. The mean and standard deviation of the obtained ball distortion rates were calculated. Student's t-test was used to statistically analyze the mean difference in ball distortion rates between vertical and horizontal phantom groups. RESULTS: In all devices, the horizontal line pair phantom, but not the vertical line pair phantom, was readable in all areas measured at the line pair value of at least 1.88 lp/mm. The line pair value tended to be higher toward the center and lower toward the outside. The ball distortion rate tended to decrease closer to the center and increased further away. In addition, ball distortion rates could not be measured at some areas as they were not recognized as balls due to the high degree of distortion at the outermost and innermost sides. The number of balls satisfying the reference value using the horizontal line pair phantom was 102 (mean of ball distortion rates, 20.98; standard deviation, 15.25). The number of balls satisfying the reference value using the vertical line pair phantom was 49 (mean of ball distortion rates, 16.33; standard deviation, 14.25). However, mean ball distortion rate was not significantly different between the two groups. CONCLUSIONS: Image layer of panoramic radiography could be evaluated by the spatial resolution using horizontal and vertical line pair phantoms and by assessing ball distortion rates through a ball-type panorama phantom. A ball distortion rate of 20% could be used as a threshold to evaluate the image layer of panoramic radiography.

Quantitative Augmented Reality-Assisted Free-Hand Orthognathic Surgery Using Electromagnetic Tracking and Skin-Attached Dynamic Reference.

The purpose of this study was to develop a quantitative AR-assisted free-hand orthognathic surgery method using electromagnetic (EM) tracking and skin-attached dynamic reference. The authors proposed a novel, simplified, and convenient workflow for augmented reality (AR)-assisted orthognathic surgery based on optical marker-less tracking, a comfortable display, and a non-invasive, skin-attached dynamic reference frame. The 2 registrations between the physical (EM tracking) and CT image spaces and between the physical and AR camera spaces, essential processes in AR-assisted surgery, were pre-operatively performed using the registration body complex and 3D depth camera. The intraoperative model of the maxillary bone segment (MBS) was superimposed on the real patient image with the simulated goal model on a flat-panel display, and the MBS was freely handled for repositioning with respect to the skin-attached dynamic reference tool (SRT) with quantitative visualization of landmarks of interest using only EM tracking. To evaluate the accuracy of AR-assisted Le Fort I surgery, the MBS of the phantom was simulated and repositioned by 6 translational and three rotational movements. The mean absolute deviations (MADs) between the simulation and post-operative positions of MBS landmarks by the SRT were 0.20, 0.34, 0.29, and 0.55 mm in x- (left lateral, right lateral), y- (setback, advance), and z- (impaction, elongation) directions, and RMS, respectively, while those by the BRT were 0.23, 0.37, 0.30, and 0.60 mm. There were no significant differences between the translation and rotation surgeries or among surgeries in the x-, y-, and z-axes for the SRT. The MADs in the x-, y-, and z-axes exhibited no significant differences between the SRT and BRT. The developed method showed high accuracy and reliability in free-hand orthognathic surgery using EM tracking and skin-attached dynamic reference.

Therapeutic effect of intraductal saline irrigation in chronic obstructive sialadenitis.

BACKGROUND: The aim of the present study was to evaluate the effectiveness of intraductal irrigation using normal saline in chronic obstructive sialadenitis. METHODS: Patients who had one of the following symptoms were recruited: pain, swelling, stiffness, and dry mouth. A total of 58 salivary glands in 33 patients were diagnosed as having sialadenitis using sialography and ultrasonography. The patients were divided into two groups (swelling group and dry mouth group), according to the major complaint. Repeated intraductal irrigation was performed on each gland. Difference of symptom severity evaluated using numerical rating scale (NRS), and ductal width measured using ultrasonography were compared between the two groups. RESULTS: The average NRS score was significantly decreased from 6.0 to 3.3 after 3-5 visits of intraductal irrigation (P < 0.05). The reduction in NRS was greater in the swelling group than in the dry mouth group, although the difference between the groups was not statistically significant. There was no change of ductal width before and after the irrigation. CONCLUSIONS: Intraductal irrigation according to this study method using normal saline is a simple treatment for the patients with chronic obstructive sialadenitis. It provides a conservative treatment option reducing the subjective symptoms.

Validation of Freezing-of-Gait Monitoring Using Smartphone.

BACKGROUND: Freezing of gait (FOG) is a commonly observed motor symptom for patients with Parkinson's disease (PD). The symptoms of FOG include reduced step lengths or motor blocks, even with an evident intention of walking. FOG should be monitored carefully because it not only lowers the patient's quality of life, but also significantly increases the risk of injury. INTRODUCTION: In previous studies, patients had to wear several sensors on the body and another computing device was needed to run the FOG detection algorithm. Moreover, the features used in the algorithm were based on low-level and hand-crafted features. In this study, we propose a FOG detection system based on a smartphone, which can be placed in the patient's daily wear, with a novel convolutional neural network (CNN). METHODS: The walking data of 32 PD patients were collected from the accelerometer and gyroscope embedded in the smartphone, located in the trouser pocket. The motion signals measured by the sensors were converted into the frequency domain and stacked into a 2D image for the CNN input. A specialized CNN model for FOG detection was determined through a validation process. RESULTS: We compared our performances with the results acquired by the previously reported settings. The proposed architecture discriminated the freezing events from the normal activities with an average sensitivity of 93.8% and a specificity of 90.1%. CONCLUSIONS: Using our methodology, the precise and continuous monitoring of freezing events with unconstrained sensing can assist patients in managing their chronic disease in daily life effectively.

Automatic detection of posterior superior alveolar artery in dental cone-beam CT images using a deeply supervised multi-scale 3D network.

OBJECTIVES: This study aimed to develop a robust and accurate deep learning network for detecting the posterior superior alveolar artery (PSAA) in dental cone-beam CT (CBCT) images, focusing on the precise localization of the centre pixel as a critical centreline pixel. METHODS: PSAA locations were manually labelled on dental CBCT data from 150 subjects. The left maxillary sinus images were horizontally flipped. In total, 300 datasets were created. Six different deep learning networks were trained, including 3D U-Net, deeply supervised 3D U-Net (3D U-Net DS), multi-scale deeply supervised 3D U-Net (3D U-Net MSDS), 3D Attention U-Net, 3D V-Net, and 3D Dense U-Net. The performance evaluation involved predicting the centre pixel of the PSAA. This was assessed using mean absolute error (MAE), mean radial error (MRE), and successful detection rate (SDR). RESULTS: The 3D U-Net MSDS achieved the best prediction performance among the tested networks, with an MAE measurement of 0.696 ± 1.552 mm and MRE of 1.101 ± 2.270 mm. In comparison, the 3D U-Net showed the lowest performance. The 3D U-Net MSDS demonstrated a SDR of 95% within a 2 mm MAE. This was a significantly higher result than other networks that achieved a detection rate of over 80%. CONCLUSIONS: This study presents a robust deep learning network for accurate PSAA detection in dental CBCT images, emphasizing precise centre pixel localization. The method achieves high accuracy in locating small vessels, such as the PSAA, and has the potential to enhance detection accuracy and efficiency, thus impacting oral and maxillofacial surgery planning and decision-making.

CACSNet for automatic robust classification and segmentation of carotid artery calcification on panoramic radiographs using a cascaded deep learning network.

Stroke is one of the major causes of death worldwide, and is closely associated with atherosclerosis of the carotid artery. Panoramic radiographs (PRs) are routinely used in dental practice, and can be used to visualize carotid artery calcification (CAC). The purpose of this study was to automatically and robustly classify and segment CACs with large variations in size, shape, and location, and those overlapping with anatomical structures based on deep learning analysis of PRs. We developed a cascaded deep learning network (CACSNet) consisting of classification and segmentation networks for CACs on PRs. This network was trained on ground truth data accurately determined with reference to CT images using the Tversky loss function with optimized weights by balancing between precision and recall. CACSNet with EfficientNet-B4 achieved an AUC of 0.996, accuracy of 0.985, sensitivity of 0.980, and specificity of 0.988 in classification for normal or abnormal PRs. Segmentation performances for CAC lesions were 0.595 for the Jaccard index, 0.722 for the Dice similarity coefficient, 0.749 for precision, and 0.756 for recall. Our network demonstrated superior classification performance to previous methods based on PRs, and had comparable segmentation performance to studies based on other imaging modalities. Therefore, CACSNet can be used for robust classification and segmentation of CAC lesions that are morphologically variable and overlap with surrounding structures over the entire posterior inferior region of the mandibular angle on PRs.

Primary malignant melanoma of the parotid gland, a rare case arising from a duct: a case report and literature review.

Malignant melanoma of the parotid gland is an unusual tumor in the head and neck region, and most parotid melanoma is reported as a metastatic lesion of cutaneous malignant melanoma. We report a case of primary malignant melanoma arising in the parotid gland duct with diagnostic challenge. The patient was a 68-year-old man who complained of repeated right facial swelling that presented 3 months prior. Swelling was detected along the Stensen's duct of the cheek, and brown-colored saliva-like fluid was aspirated. On MR and CT images, a fluid-filled duct with small nodule and heterogeneously enhancing mass in the parotid parenchyma was detected. The nodular mass on the ductal wall grew rapidly, and the hyperintense T1 signal became significant on follow-up images. The final diagnosis via histopathologic examination using biopsy and parotidectomy specimen revealed the lesion as malignant melanoma of the duct and pleomorphic adenoma of the parenchyma. Even if the incidence of primary malignant melanoma is very low among tumors occurring in the parotid gland, efforts supporting an early diagnosis using imaging characteristics are important.

Radiological manifestations and clinical findings of patients with oncologic and osteoporotic medication-related osteonecrosis of the jaw.

Medication-related osteonecrosis of the jaw (MRONJ) poses a challenging form of osteomyelitis in patients undergoing antiresorptive therapies in contrast to conventional osteomyelitis. This study aimed to compare the clinical and radiological features of MRONJ between patients receiving low-dose medications for osteoporosis and those receiving high-dose medications for oncologic purposes. The clinical, panoramic radiographic, and computed tomography data of 159 patients with MRONJ (osteoporotic group, n = 120; oncologic group, n = 39) who developed the condition after using antiresorptive medications for the management of osteoporosis or bone malignancy were analyzed. The osteoporotic group was older (75.8 vs. 60.4 years, p < 0.01) and had a longer duration of medication usage than the oncologic group (58.1 vs. 28.0 months, p < 0.01). Pus discharge and swelling were more common in the osteoporotic group (p < 0.05), whereas bone exposure was more frequent in the oncologic group (p < 0.01). The mandibular cortical index (MCI) in panoramic radiographs was higher in the osteoporotic group (p < 0.01). The mean sequestra size was larger in the oncologic group than in the osteoporotic group (15.3 vs. 10.6 mm, p < 0.05). The cured rate was significantly higher in the osteoporotic group (66.3% vs. 33.3%, p < 0.01). Oncologic MRONJ exhibited distinct clinical findings including rapid disease onset, fewer purulent signs, and lower cure rates than osteoporotic MRONJ. Radiological features such as sequestrum size on CT scan, and MCI values on panoramic radiographs, may aid in differentiating MRONJ in osteoporotic and oncologic patients.

Clinical and radiological features of malformed mesiodens in the nasopalatine canal: an observational study.

OBJECTIVES: The purpose of this study is to investigate the morphological changes that occur when mesiodens is located within the nasopalatine canal, as well as clinical characteristics. METHODS: Clinical records and CT images of patients who had mesiodens in the nasopalatine canal were retrospectively analysed. In addition to demographic information, clinical symptoms and complications associated with extraction of mesiodens were recorded. Using CT images, number, location, size, and tooth morphology were evaluated. RESULTS: This study included 32 patients and 38 mesiodens within the nasopalatine canal. Supernumerary teeth exhibited a characteristic feature of thin and elongated shape in the canal (narrow width and elongation were observed in 96.6% and 53.3% of the patients, respectively). Fusion was found in 4 patients and dilaceration in 12. A complication occurred in 2 patients, which was tooth remnant, not a neurologic complication. Only 5 mesiodens could be detected in the nasopalatine canal on panoramic images. CONCLUSIONS: Morphological abnormalities in mesiodens within the nasopalatine canal were frequently detected, and these could be effectively diagnosed through 3D imaging analysis.

Automatic detection and classification of nasopalatine duct cyst and periapical cyst on panoramic radiographs using deep convolutional neural networks.

OBJECTIVE: The aim of this study was to evaluate a deep convolutional neural network (DCNN) method for the detection and classification of nasopalatine duct cysts (NPDC) and periapical cysts (PAC) on panoramic radiographs. STUDY DESIGN: A total of 1,209 panoramic radiographs with 606 NPDC and 603 PAC were labeled with a bounding box and divided into training, validation, and test sets with an 8:1:1 ratio. The networks used were EfficientDet-D3, Faster R-CNN, YOLO v5, RetinaNet, and SSD. Mean average precision (mAP) was used to assess performance. Sixty images with no lesion in the anterior maxilla were added to the previous test set and were tested on 2 dentists with no training in radiology (GP) and on EfficientDet-D3. The performances were comparatively examined. RESULTS: The mAP for each DCNN was EfficientDet-D3 93.8%, Faster R-CNN 90.8%, YOLO v5 89.5%, RetinaNet 79.4%, and SSD 60.9%. The classification performance of EfficientDet-D3 was higher than that of the GPs' with accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 94.4%, 94.4%, 97.2%, 94.6%, and 97.2%, respectively. CONCLUSIONS: The proposed method achieved high performance for the detection and classification of NPDC and PAC compared with the GPs and presented promising prospects for clinical application.

Automatic segmentation and classification of frontal sinuses for sex determination from CBCT scans using a two-stage anatomy-guided attention network.

Sex determination is essential for identifying unidentified individuals, particularly in forensic contexts. Traditional methods for sex determination involve manual measurements of skeletal features on CBCT scans. However, these manual measurements are labor-intensive, time-consuming, and error-prone. The purpose of this study was to automatically and accurately determine sex on a CBCT scan using a two-stage anatomy-guided attention network (SDetNet). SDetNet consisted of a 2D frontal sinus segmentation network (FSNet) and a 3D anatomy-guided attention network (SDNet). FSNet segmented frontal sinus regions in the CBCT images and extracted regions of interest (ROIs) near them. Then, the ROIs were fed into SDNet to predict sex accurately. To improve sex determination performance, we proposed multi-channel inputs (MSIs) and an anatomy-guided attention module (AGAM), which encouraged SDetNet to learn differences in the anatomical context of the frontal sinus between males and females. SDetNet showed superior sex determination performance in the area under the receiver operating characteristic curve, accuracy, Brier score, and specificity compared with the other 3D CNNs. Moreover, the results of ablation studies showed a notable improvement in sex determination with the embedding of both MSI and AGAM. Consequently, SDetNet demonstrated automatic and accurate sex determination by learning the anatomical context information of the frontal sinus on CBCT scans.

Deep learning-based automatic segmentation of the mandibular canal on panoramic radiographs: A multi-device study.

Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion: This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.

Nasal cavity perforation by implant fixtures: case series with emphasis on panoramic imaging of nasal cavity extending posteriorly.

The nasal cavity is an important landmark when considering implant insertion into the anterior region of the maxillary arch. The perforation of implants into the nasal cavity may cause complications, such as implant migration, inflammation, or changes in nasal airflow; thus, precise assessment of the nasal cavity is mandatory.Three cases of nasal cavity perforation by dental implants are presented, including one case of implant fixture migration into the nasal cavity. On panoramic radiographs of the patients, the following common features were observed: the horizontal radiopaque line of the hard palate was observed to be inferior to or similar to that of the antral floor and the bone between the lateral wall of the nasal cavity and the medial wall of the maxillary sinus was emphasized in a triangular shape.When the maxillary sinus is small and alveolar bone resorption is severe, panoramic evaluation may cause overestimation of the available residual bone, particularly in the maxillary canine/premolar region. Therefore, the residual bone should be reevaluated three-dimensionally to measure the exact bony shape and volume.

Structure-preserving quality improvement of cone beam CT images using contrastive learning.

Cone-beam CT (CBCT) is widely used in dental clinics but exhibits limitations in assessing soft tissue pathology because of its lack of contrast resolution and low Hounsfield Units (HU) quantification accuracy. We aimed to increase the image quality and HU accuracy of CBCTs while preserving anatomical structures. We generated CT-like images from CBCT images using a patchwise contrastive learning-based GAN model. Our model was trained on unpaired CT and CBCT datasets with the novel combination of losses and the feature extractor pretrained on our training dataset. We evaluated the quality of the images generated by our model in terms of Fréchet inception distance (FID), peak signal-to-noise ratio (PSNR), mean absolute error (MAE), and root mean square error (RMSE). Additionally, the structure preservation performance was assessed by the structure score. As a result, the generated CT-like images by our model were significantly superior to those generated by various baseline models in terms of FID, PSNR, MAE, RMSE, and structure score. Therefore, we demonstrated that our model provided the complementary benefits of preserving the anatomical structures of the input CBCT images and improving the image quality to be similar to those of CT images.