Oral Radiology最新文献_第7页

Ultrasonography as an additional tool to localize impacted canines. 超声波检查是定位受影响犬齿的又一工具。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-01-01 Epub Date: 2024-08-10 DOI: 10.1007/s11282-024-00769-z

Marilia Yatabe, Oliver Kripfgans, Hsun-Liang Chan, Jennifer Xu, Jade Cook, Fabiana Soki

{"title":"Ultrasonography as an additional tool to localize impacted canines.","authors":"Marilia Yatabe, Oliver Kripfgans, Hsun-Liang Chan, Jennifer Xu, Jade Cook, Fabiana Soki","doi":"10.1007/s11282-024-00769-z","DOIUrl":"10.1007/s11282-024-00769-z","url":null,"abstract":"Canine impaction is a common dental anomaly that requires a multidisciplinary approach, from diagnosis to treatment. The regular two-dimensional (2D) radiographs are able to visualize if the tooth is impacted, but unable to specifically localize it, and determine if there are any root resorptions associated to it. The cone-beam computed tomography (CBCT) is able to three-dimensionally determine its location, aiding to the diagnosis and treatment plan. The major disadvantage is the amount of radiation that is added to the patient and can be even more significant in pediatric patients. The intra-oral ultrasound (io-US) is a new non-invasive and non-radiating real-time chairside imaging method that has the potential to aid in locating the impacted tooth. This paper presents 4 cases that required a CBCT for the location and treatment planning of impacted maxillary canines and were also scanned with intra-oral ultrasound. The images were then compared to the CBCT exam for validation of the new method. Through these cases, we highlight the capability of the io-US to locate the impacted canines. Other advantages of io-US might include evaluation of soft tissue thickness and vasculature that are important for surgical planning and execution.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"131-143"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141914730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Acceptability of artificial intelligence in dental radiology among patients in India: are we ready for this revolution? 印度患者对人工智能牙科放射学的接受程度：我们准备好迎接这场革命了吗？

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-01-01 Epub Date: 2024-10-09 DOI: 10.1007/s11282-024-00777-z

Preeti Chawla Arora, Komaldeep Kaur Sandhu, Aman Arora, Ambika Gupta, Mandavi Waghmare, Vasundhara Rampal

{"title":"Acceptability of artificial intelligence in dental radiology among patients in India: are we ready for this revolution?","authors":"Preeti Chawla Arora, Komaldeep Kaur Sandhu, Aman Arora, Ambika Gupta, Mandavi Waghmare, Vasundhara Rampal","doi":"10.1007/s11282-024-00777-z","DOIUrl":"10.1007/s11282-024-00777-z","url":null,"abstract":"Objective: In recent times, artificial Intelligence (AI) has gained popularity in medical as well as dental radiology. Studies have been conducted among medical and dental students and professionals about the knowledge and understanding towards AI. The aim of this study was to investigate the perceptions and acceptability of AI in dental radiology among a group of Indian patients seeking dental treatment.Methods: A cross-sectional research was planned with a validated questionnaire, containing ten close ended questions amongst 1562 patients. Their sociodemographic characters, opinions and attitudes regarding AI and feasibility of acceptance of AI-based dental radiological diagnosis among patients was evaluated. The study sample was divided in various groups on the basis of their age; group-1(16-30 years), group-2(31-45 years) and group-3(>45 years), educational status and urban/rural background. Statistical analysis was done by Chi-square test with significance value set at p< 0.005.Results-: The participants possessed impressive knowledge about AI. Patients' awareness, attitudes and acceptability towards AI for dental radiographic diagnosis were substantially influenced by age, education level and residential background. Although many of them, especially the urban and more educated participants believed that AI could be more accurate, they preferred the human judgement. Overall, a negative attitude in terms of acceptability of AI in dental radiology was observed in this study.Conclusions: Participants opined that AI should only be used as an auxiliary tool and valued clinical judgment over AI in ambiguous situations. It is recommended that this promising technological advancement can be used for initial screening in dental radiology.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"69-77"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142395616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of fractal analysis and radiomorphometric measurements of mandibular bone structure in bruxism and non-bruxism paediatric patients. 评估磨牙症和非磨牙症儿科患者下颌骨结构的分形分析和放射形态测量。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-01-01 Epub Date: 2024-10-08 DOI: 10.1007/s11282-024-00776-0

Aslı Soğukpınar Önsüren, Katibe Tuğçe Temur

{"title":"Evaluation of fractal analysis and radiomorphometric measurements of mandibular bone structure in bruxism and non-bruxism paediatric patients.","authors":"Aslı Soğukpınar Önsüren, Katibe Tuğçe Temur","doi":"10.1007/s11282-024-00776-0","DOIUrl":"10.1007/s11282-024-00776-0","url":null,"abstract":"Objectives: The goal of this examination was to compare the impact of probable sleep/awake bruxism on the mandibular trabecular bone structure by fractal analysis (FA) with digital panoramic radiograph (DPR) and radiomorphometric measurements in paediatric patients with bruxism.Methods: The examination included 130 participants with 63 patients with probable sleep/awake bruxism and 67 control groups. Bilateral regions of interest (ROI) in three regions were examined as ROI1: mandibular ramus, ROI2: mandibular angulus, ROI3: anterior to the molar teeth. Radiomorphometric measurements were taken of the mandibular cortical width (MCW), panoramic mandibular index (PMI), and mandibular cortical index (MCI). p < 0.05 was approved for statistical significance.Results: The ROI-1, ROI-2, and ROI-3 values were defined to be statistically significantly high in the bruxism group (p < 0.05). No significant difference was found between the groups in the other values (p > 0.05). There was no difference in the age and gender for any of the parameters (p > 0.05).Conclusion: In children and adolescents, the mandibular trabecular bone can be affected by bruxism. FA can be used as an auxiliary method for finding the mandibular trabecular differences of patients with bruxism in paediatric dentistry just as it can for adults.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"60-68"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142395617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning segmentation of mandible with lower dentition from cone beam CT. 利用锥形束 CT 对下颌骨和下牙进行深度学习分割。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-01-01 Epub Date: 2024-08-14 DOI: 10.1007/s11282-024-00770-6

Daniel C Kargilis, Winnie Xu, Samir Reddy, Shilpa Shree Kuduva Ramesh, Steven Wang, Anh D Le, Chamith S Rajapakse

{"title":"Deep learning segmentation of mandible with lower dentition from cone beam CT.","authors":"Daniel C Kargilis, Winnie Xu, Samir Reddy, Shilpa Shree Kuduva Ramesh, Steven Wang, Anh D Le, Chamith S Rajapakse","doi":"10.1007/s11282-024-00770-6","DOIUrl":"10.1007/s11282-024-00770-6","url":null,"abstract":"Objectives: This study aimed to train a 3D U-Net convolutional neural network (CNN) for mandible and lower dentition segmentation from cone-beam computed tomography (CBCT) scans.Methods: In an ambispective cross-sectional design, CBCT scans from two hospitals (2009-2019 and 2021-2022) constituted an internal dataset and external validation set, respectively. Manual segmentation informed CNN training, and evaluations employed Dice similarity coefficient (DSC) for volumetric accuracy. A blinded oral maxillofacial surgeon performed qualitative grading of CBCT scans and object meshes. Statistical analyses included independent t-tests and ANOVA tests to compare DSC across patient subgroups of gender, race, body mass index (BMI), test dataset used, age, and degree of metal artifact. Tests were powered for a minimum detectable difference in DSC of 0.025, with alpha of 0.05 and power level of 0.8.Results: 648 CBCT scans from 490 patients were included in the study. The CNN achieved high accuracy (average DSC: 0.945 internal, 0.940 external). No DSC differences were observed between test set used, gender, BMI, and race. Significant differences in DSC were identified based on age group and the degree of metal artifact. The majority (80%) of object meshes produced by both manual and automatic segmentation were rated as acceptable or higher quality.Conclusion: We developed a model for automatic mandible and lower dentition segmentation from CBCT scans in a demographically diverse cohort including a high degree of metal artifacts. The model demonstrated good accuracy on internal and external test sets, with majority acceptable quality from a clinical grader.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"1-9"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141977343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of metallic materials on magnetic resonance image uniformity: a quantitative experimental study. 金属材料对磁共振成像均匀性的影响：定量实验研究。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-01-01 Epub Date: 2024-10-15 DOI: 10.1007/s11282-024-00778-y

Hiroaki Shimamoto, Doaa Felemban, Yuka Uchimoto, Nobuhiko Matsuda, Naoko Takagawa, Ami Takeshita, Yuri Iwamoto, Ryoko Okahata, Tomomi Tsujimoto, Sven Kreiborg, Sanjay M Mallya, Fan-Pei Gloria Yang

{"title":"Effect of metallic materials on magnetic resonance image uniformity: a quantitative experimental study.","authors":"Hiroaki Shimamoto, Doaa Felemban, Yuka Uchimoto, Nobuhiko Matsuda, Naoko Takagawa, Ami Takeshita, Yuri Iwamoto, Ryoko Okahata, Tomomi Tsujimoto, Sven Kreiborg, Sanjay M Mallya, Fan-Pei Gloria Yang","doi":"10.1007/s11282-024-00778-y","DOIUrl":"10.1007/s11282-024-00778-y","url":null,"abstract":"Objective: To assess quantitatively the effect of metallic materials on MR image uniformity using a standardized method.Methods: Six types of 1 cm cubic metallic materials (i.e., Au, Ag, Al, Au-Ag-Pd alloy, Ti, and Co-Cr alloy) embedded in a glass phantom filled were examined and compared with no metal condition inserted as a reference. The phantom was scanned five times under each condition using a 1.5-T MR superconducting magnet scanner with an 8-channel phased-array brain coil and head and neck coil. For each examination, the phantom was scanned in three planes: axial, coronal, and sagittal using T1-weighted spin echo (SE) and gradient echo (GRE) sequences in accordance with the American Society for Testing and Materials (ASTM) F2119-07 standard. Image uniformity was assessed using the non-uniformity index (NUI), which was developed by the National Electrical Manufacturers Association (NEMA), as an appropriate standardized measure for investigating magnetic field uniformity.Results: T1-GRE images with Co-Cr typically elicited the lowest uniformity, followed by T1-GRE images with Ti, while all other metallic materials did not affect image uniformity. In particular, T1-GRE images with Co-Cr showed significantly higher NUI values as far as 6.6 cm at maximum equivalent to 11 slices centering around it in comparison with the measurement uncertainty from images without metallic materials.Conclusion: We found that MR image uniformity was influenced by the scanning sequence and coil type when Co-Cr and Ti were present. It is assumed that the image non-uniformity in Co-Cr and Ti is caused by their high magnetic susceptibility.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"78-87"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11723845/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142481828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved soft-tissue visibility on cone-beam computed tomography with an image-generating artificial intelligence model using a cyclic generative adversarial network. 利用循环生成对抗网络的图像生成人工智能模型提高锥束计算机断层扫描的软组织可见度。

IF 1.6 3区医学

Oral Radiology Pub Date : 2024-10-01 Epub Date: 2024-06-28 DOI: 10.1007/s11282-024-00763-5

Motoki Fukuda, Michihito Nozawa, Hironori Akiyama, Eiichiro Ariji, Yoshiko Ariji

{"title":"Improved soft-tissue visibility on cone-beam computed tomography with an image-generating artificial intelligence model using a cyclic generative adversarial network.","authors":"Motoki Fukuda, Michihito Nozawa, Hironori Akiyama, Eiichiro Ariji, Yoshiko Ariji","doi":"10.1007/s11282-024-00763-5","DOIUrl":"10.1007/s11282-024-00763-5","url":null,"abstract":"Objectives: The objective of this study was to enhance the visibility of soft tissues on cone-beam computed tomography (CBCT) using a CycleGAN network trained on CT images.Methods: Training and evaluation of the CycleGAN were conducted using CT and CBCT images collected from Aichi Gakuin University (α facility) and Osaka Dental University (β facility). Synthesized images (sCBCT) output by the CycleGAN network were evaluated by comparing them with the original images (oCBCT) and CT images, and assessments were made using histogram analysis and human scoring of soft-tissue anatomical structures and cystic lesions.Results: The histogram analysis showed that on sCBCT, soft-tissue anatomical structures showed significant shifts in voxel intensity toward values resembling those on CT, with the mean values for all structures approaching those of CT and the specialists' visibility scores being significantly increased. However, improvement in the visibility of cystic lesions was limited.Conclusions: Image synthesis using CycleGAN significantly improved the visibility of soft tissue on CBCT, with this improvement being particularly notable from the submandibular region to the floor of the mouth. Although the effect on the visibility of cystic lesions was limited, there is potential for further improvement through refinement of the training method.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"508-519"},"PeriodicalIF":1.6,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141473105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Osteosarcoma associated with cemento-osseous dysplasia: co-incidence or two related entities? 伴有骨水泥骨发育不良的骨肉瘤：巧合还是两个相关实体？

IF 1.6 3区医学

Oral Radiology Pub Date : 2024-10-01 Epub Date: 2024-06-09 DOI: 10.1007/s11282-024-00758-2

Suvarna Indermun, Fadi Titinchi, Julandi Alwan, Jean Morkel, Christoffel Johannes Nortje

{"title":"Osteosarcoma associated with cemento-osseous dysplasia: co-incidence or two related entities?","authors":"Suvarna Indermun, Fadi Titinchi, Julandi Alwan, Jean Morkel, Christoffel Johannes Nortje","doi":"10.1007/s11282-024-00758-2","DOIUrl":"10.1007/s11282-024-00758-2","url":null,"abstract":"Background: Osteosarcoma of the jaws is a rare primary malignant tumor of bone. The clinical, radiological and histopathological features of a case associated with cemento-osseous dysplasia is presented.Case report: A 57-year-old mixed-race female presented with a large, progressive, swelling of the right mandible. Radiographic examination revealed two associated lesions. Partially defined irregular radiopacities were noted in the left mandible, extending from the premolar to the molar region. The lesion had a cotton-wool appearance and resembled a fibro-osseous lesion; i.e. cemento-osseous dysplasia. A second large, expansive and irregular, radiopaque lesion was noted on the right angle of the mandible, extending beyond the inferior cortex of the mandible. The internal structure was heterogeneous and resembled irregular bone formation. The classic \"sunburst\" appearance of radiating bony spicules can be seen in the posterior-anterior view and the CBCT 3D reconstruction, indicating the outgrowth of the tumor matrix. Histopathological exam confirmed a final diagnosis of osteosarcoma closely associated with cemento-osseous dysplasia. The patient underwent a fludeoxyglucose-18 (FDG) positron emission tomography (PET) scan which indicated metastasis in the left lung and increased uptake in the right mandible. Chemotherapy was initially administered with a plan to resect the tumor, however, the patient demised as a result of medical complications.Conclusion: The question in the literature remains whether these two entities are coincidentally found or arise from each other. Nevertheless, it is important for clinicians to closely monitor patients with cemento-osseous dysplasia and biopsy any suspicious lesions that may develop into osteosarcoma.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"546-554"},"PeriodicalIF":1.6,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11379726/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141293941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of canalis sinuosus and accessory canal morphology by cone-beam computed tomography. 通过锥形束计算机断层扫描评估鼻窦和附属管形态。

IF 1.6 3区医学

Oral Radiology Pub Date : 2024-10-01 Epub Date: 2024-07-26 DOI: 10.1007/s11282-024-00767-1

Ceren Aktuna Belgin, Gozde Serindere, Zarif Ece Hammudioglu, Merve Kucuk

{"title":"Evaluation of canalis sinuosus and accessory canal morphology by cone-beam computed tomography.","authors":"Ceren Aktuna Belgin, Gozde Serindere, Zarif Ece Hammudioglu, Merve Kucuk","doi":"10.1007/s11282-024-00767-1","DOIUrl":"10.1007/s11282-024-00767-1","url":null,"abstract":"Objective: To evaluate canalis sinuosus (CS) and accessory canalis sinuosus (AC) morphology and their relationship with the impacted canine on cone-beam computed tomography (CBCT) images.Methods: The diameter and location of the CS, its distance from the nasal cavity (NC-CS), its distance from the buccal cortical plate (BC-CS), and its distance from the alveolar ridge crest (AR-CS) were evaluated on 1000 CBCT scans. The prevalence and termination of AC and the presence of impacted canines were also evaluated.Results: CS was detected in 89 (8.9%) of 1000 CBCTs. The mean CS diameter was found as 1.34 ± 0.53 mm. No statistically significant difference was found between gender, age, direction, and CS presence and diameter. CS was most frequently seen in regions 11 (23.6%) and 13 (23.6%). The average NC-CS, BC-CS, and AR-CS length was 6.14, 6.06 and 4.35 mm, respectively. AC was detected in 22 patients (24.71%). There was no statistically significant difference between the presence of AC and gender, age, CS diameter, NC-CS, BC-CS, and AR-CS distance. BC-CS length and AR-CS length were statistically significantly higher in patients with impacted canines.Conclusions: It should be kept in mind that the CS diameter, NC-CS, BC-CS, and AR-CS distance may increase in the presence of an impacted canine and the integrity of the neurovascular structure should be preserved. The fact that the CS is often localized in the palatial region requires a detailed evaluation of the anterior maxillary region with three-dimensional imaging methods.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"530-537"},"PeriodicalIF":1.6,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141768116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Arteriovenous fistula of the mandible: a case report. 下颚动静脉瘘：病例报告。

IF 1.6 3区医学

Oral Radiology Pub Date : 2024-10-01 Epub Date: 2024-06-19 DOI: 10.1007/s11282-024-00762-6

Mattia Todaro, Ermal Pashaj, Alessandro Pedicelli, Andrea Alexandre, Gianmarco Saponaro, Giulio Gasparini, Alessandro Moro

引用次数: 0

Deep learning classification performance for diagnosing condylar osteoarthritis in patients with dentofacial deformities using panoramic temporomandibular joint projection images. 利用颞下颌关节全景投影图像诊断颌面部畸形患者髁状突骨关节炎的深度学习分类性能。

IF 1.6 3区医学

Oral Radiology Pub Date : 2024-10-01 Epub Date: 2024-07-11 DOI: 10.1007/s11282-024-00768-0

Yukiko Iwase, Tomoya Sugiki, Yoshitaka Kise, Masako Nishiyama, Michihito Nozawa, Motoki Fukuda, Yoshiko Ariji, Eiichiro Ariji

{"title":"Deep learning classification performance for diagnosing condylar osteoarthritis in patients with dentofacial deformities using panoramic temporomandibular joint projection images.","authors":"Yukiko Iwase, Tomoya Sugiki, Yoshitaka Kise, Masako Nishiyama, Michihito Nozawa, Motoki Fukuda, Yoshiko Ariji, Eiichiro Ariji","doi":"10.1007/s11282-024-00768-0","DOIUrl":"10.1007/s11282-024-00768-0","url":null,"abstract":"Objective: The present study aimed to assess the consistencies and performances of deep learning (DL) models in the diagnosis of condylar osteoarthritis (OA) among patients with dentofacial deformities using panoramic temporomandibular joint (TMJ) projection images.Methods: A total of 68 TMJs with or without condylar OA in dentofacial deformity patients were tested to verify the consistencies and performances of DL models created using 252 TMJs with or without OA in TMJ disorder and dentofacial deformity patients; these models were used to diagnose OA on conventional panoramic (Con-Pa) images and open (Open-TMJ) and closed (Closed-TMJ) mouth TMJ projection images. The GoogLeNet and VGG-16 networks were used to create the DL models. For comparison, two dental residents with < 1 year of experience interpreting radiographs evaluated the same condyle data that had been used to test the DL models.Results: On Open-TMJ images, the DL models showed moderate to very good consistency, whereas the residents' demonstrated fair consistency on all images. The areas under the curve (AUCs) of both DL models on Con-Pa (0.84 for GoogLeNet and 0.75 for VGG-16) and Open-TMJ images (0.89 for both models) were significantly higher than the residents' AUCs (p < 0.01). The AUCs of the DL models on Open-TMJ images (0.89 for both models) were higher than the AUCs on Closed-TMJ images (0.72 for both models).Conclusions: The DL models created in this study could help residents to interpret Con-Pa and Open-TMJ images in the diagnosis of condylar OA.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"538-545"},"PeriodicalIF":1.6,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141581652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0