Oral Radiology最新文献_第3页

Evaluation of the mandibular canal and the third mandibular molar relationship by CBCT with a deep learning approach. 基于深度学习方法的CBCT评价下颌管与下颌第三磨牙关系。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-12-11 DOI: 10.1007/s11282-024-00793-z

Suay Yağmur Ünal, Filiz Namdar Pekiner

{"title":"Evaluation of the mandibular canal and the third mandibular molar relationship by CBCT with a deep learning approach.","authors":"Suay Yağmur Ünal, Filiz Namdar Pekiner","doi":"10.1007/s11282-024-00793-z","DOIUrl":"10.1007/s11282-024-00793-z","url":null,"abstract":"Objective: The mandibular canal (MC) houses the inferior alveolar nerve. Extraction of the mandibular third molar (MM3) is a common dental surgery, often complicated by nerve damage. CBCT is the most effective imaging method to assess the relationship between MM3 and MC. With advancements in artificial intelligence, deep learning has shown promising results in dentistry. The aim of this study is to evaluate the MC-MM3 relationship using CBCT and a deep learning technique, as well as to automatically segment the mandibular impacted third molar, mandibular canal, mental and mandibular foramen.Methods: This retrospective study analyzed CBCT data from 300 patients. Segmentation was used for labeling, dividing the data into training (n = 270) and test (n = 30) sets. The nnU-NetV2 architecture was employed to develop an optimal deep learning model. The model's success was validated using the test set, with metrics including accuracy, sensitivity, precision, Dice score, Jaccard index, and AUC.Results: For the MM3 annotated on CBCT, the accuracy was 0.99, sensitivity 0.90, precision 0.85, Dice score 0.85, Jaccard index 0.78, AUC value 0.95. In MC evaluation, accuracy was 0.99, sensitivity 0.75, precision 0.78, Dice score 0.76, Jaccard index 0.62, AUC value 0.88. For the evaluation of mental foramen; accuracy 0.99, sensitivity 0.64, precision 0.66, Dice score 0.64, Jaccard index 0.57, AUC value 0.82. In the evaluation of mandibular foramen, accuracy was found to be 0.99, sensitivity 0.79, precision 0.68, Dice score 0.71, and AUC value 0.90. Evaluating the MM3-MC relationship, the model showed an 80% correlation with observer assessments.Conclusion: The nnU-NetV2 deep learning architecture reliably identifies the MC-MM3 relationship in CBCT images, aiding in diagnosis, surgical planning, and complication prediction.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"222-230"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142808762","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

Prevalence and morphometric evaluation of dilaceration in Indian Tamils: an analysis of 10,089 permanent teeth. 印度泰米尔人牙齿稀疏的发生率和形态评估：对 10,089 颗恒牙的分析。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-11-26 DOI: 10.1007/s11282-024-00789-9

Aditya Mantri, Deepak Pandiar, Reshma Poothakulath Krishnan, T N Uma Maheswari, Jency P Evanjelin

{"title":"Prevalence and morphometric evaluation of dilaceration in Indian Tamils: an analysis of 10,089 permanent teeth.","authors":"Aditya Mantri, Deepak Pandiar, Reshma Poothakulath Krishnan, T N Uma Maheswari, Jency P Evanjelin","doi":"10.1007/s11282-024-00789-9","DOIUrl":"10.1007/s11282-024-00789-9","url":null,"abstract":"Aim: The present radiographic study was conducted to assess the subject and tooth prevalence of dilaceration in a cohort of Tamil population aided by morphometric analysis.Materials and methods: After obtaining clearance from institutional human ethical clearance committee, 575 panoramic radiographs were retrieved. After exclusion of 233 radiographs based on the inclusion and exclusion criteria, a total of 342 panoramic radiographs were included. The angulation was estimated on Angle Meter software and categorized into three classes as mild, moderate and extreme. The data were recorded on Microsoft Excel spreadsheet 2021, and descriptively analyzed using IBM SPSS software.Results: Of the 342 subjects, there were 172 males and 170 females (1.012M:1F). Overall mean age was 33.75 ± 13.86 years. 100/342 subjects showed dilaceration in one or more teeth yielding a subject prevalence of 29.24%. There was no statistically significant difference in age and gender between the individuals who showed dilaceration and those without. The tooth prevalence was 1.49% (150/10089). The mandibular third molars were the most commonly affected teeth. Further, 97/150 teeth were mildly dilacerated (64.67%), 34/150 teeth showed moderate dilaceration (22.67%) and extreme dilaceration was noted in 19 teeth (12.66%).Conclusion: Within the limits of the present study, we reported morphometric analysis of dilacerated teeth from South Indian population after examination of permanent 10,089 teeth from 342 panoramic radiographs. Mandibular third molars were the most commonly affected teeth, which led us to speculate that dilaceration is a true developmental anomaly, unrelated to trauma or other external stimuli.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"190-196"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142717908","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 the effectiveness of panoramic radiography in impacted mandibular third molars on deep learning models developed with findings obtained with cone beam computed tomography. 基于锥束计算机断层扫描结果的深度学习模型评估下颌阻生第三磨牙全景x线摄影的有效性。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-12-27 DOI: 10.1007/s11282-024-00799-7

Mustafa Taha Güller, Nida Kumbasar, Özkan Miloğlu

{"title":"Evaluation of the effectiveness of panoramic radiography in impacted mandibular third molars on deep learning models developed with findings obtained with cone beam computed tomography.","authors":"Mustafa Taha Güller, Nida Kumbasar, Özkan Miloğlu","doi":"10.1007/s11282-024-00799-7","DOIUrl":"10.1007/s11282-024-00799-7","url":null,"abstract":"Objective: The aim of this study is to determine the contact relationship and position of impacted mandibular third molar teeth (IMM3) with the mandibular canal (MC) in panoramic radiography (PR) images using deep learning (DL) models trained with the help of cone beam computed tomography (CBCT) and DL to compare the performances of the architectures.Methods: In this study, a total of 546 IMM3s from 290 patients with CBCT and PR images were included. The performances of SqueezeNet, GoogLeNet, and Inception-v3 architectures in solving four problems on two different regions of interest (RoI) were evaluated.Results: The SqueezeNet architecture performed the best on the vertical RoI, showing 93.2% accuracy in the identification of the 2nd problem (contact relationship buccal or lingual). Inception-v3 showed the highest performance with 84.8% accuracy in horizontal RoI for the 1st problem (contact relationship-no contact relationship), GoogLeNet showed 77.4% accuracy in horizontal RoI for the 4th problem (contact relationship buccal, lingual, other category, or no contact relationship), and GoogLeNet showed 70.0% accuracy in horizontal RoI for the 3rd problem (contact relationship buccal, lingual, or other category).Conclusion: This study found that the Inception-v3 model showed the highest accuracy values in determining the contact relationship, and SqueezeNet architecture showed the highest accuracy values in determining the position of IMM3 relative to MC in the presence of a contact relationship.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"260-275"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142900606","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

Sporadic vs. basal cell nevus syndrome associated odontogenic keratocysts: focus on CT and MRI including DWI. 散发性与基底细胞痣综合征相关的牙源性角化囊肿：重点关注CT和MRI包括DWI。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-12-20 DOI: 10.1007/s11282-024-00797-9

Hirotaka Muraoka, Takashi Kaneda, Takumi Kondo, Yuta Kohinata, Satoshi Tokunaga

{"title":"Sporadic vs. basal cell nevus syndrome associated odontogenic keratocysts: focus on CT and MRI including DWI.","authors":"Hirotaka Muraoka, Takashi Kaneda, Takumi Kondo, Yuta Kohinata, Satoshi Tokunaga","doi":"10.1007/s11282-024-00797-9","DOIUrl":"10.1007/s11282-024-00797-9","url":null,"abstract":"Purpose: This study aimed to evaluate odontogenic keratocysts associated with basal cell nevus syndrome (BCNS) using computed tomography (CT) and magnetic resornance imaging (MRI) including diffusion-weighted imaging (DWI) and compare them with sporadic cases.Materials and methods: This study investigated 17 outpatients who underwent panoramic radiography, CT, and MRI between August 2012 and January 2021. Five of these patients had BCNS had 16 odontogenic keratocysts, for which the authors recorded detailed findings. DWI analysis compared the apparent diffusion coefficient (ADC) values of odontogenic keratocysts in patients with BCNS and sporadic cases. The Mann-Whitney test was used to analyse bivariate statistics.Results: Patients with BCNS had an average of 3.2 lesions in the jaw. On DWI, the ADC value ranged from 0.58 to 2.66 × 10-3 mm2/s. The values for sporadic odontogenic keratocysts ranged from 0.67 to 1.11 × 10-3 mm2/s. The median values were 0.94 and 0.89 for BCNS-associated and sporadic odontogenic keratocysts cases, respectively (P = .478).Conclusion: This study presented detailed imaging findings of odontogenic keratocysts in patients with BCNS. Furthermore, the authors revealed a wide range of ADC values for BCNS-associated odontogenic keratocysts.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"238-247"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866529","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

Radiological assessment of Sella Turcica morphology correlates with skeletal classes in an Austrian population: an observational study. 在奥地利人口中，蝶鞍形态的放射学评估与骨骼等级相关：一项观察性研究。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-11-13 DOI: 10.1007/s11282-024-00785-z

Julia Schwab, Lars Stucki, Sebastian Fitzek, Aliza Tithphit, Andreas Hönigl, Sarah Stackmann, Ina Horn, Hanna Thenner, Philipp Dasser, Ramona Woitek, Kyung-Eun Choi, Sepideh Hatamikia, Julia Furtner

{"title":"Radiological assessment of Sella Turcica morphology correlates with skeletal classes in an Austrian population: an observational study.","authors":"Julia Schwab, Lars Stucki, Sebastian Fitzek, Aliza Tithphit, Andreas Hönigl, Sarah Stackmann, Ina Horn, Hanna Thenner, Philipp Dasser, Ramona Woitek, Kyung-Eun Choi, Sepideh Hatamikia, Julia Furtner","doi":"10.1007/s11282-024-00785-z","DOIUrl":"10.1007/s11282-024-00785-z","url":null,"abstract":"Objectives: This study aimed to analyze variations in the sella turcica (ST) concerning its size, shape, and bridging, providing first reference values in Austrian individuals. Additionally, it assessed associations between these morphological and demographic parameters and their correlation with patients' skeletal class.Methods: 208 lateral cephalometric radiographs (154 female, 54 male; age 8-58 years) from DPU Dental Clinic (Austria) were included. Size, skeletal class, shape, age, and gender of ST were tested for significance in correlation using, (M)ANOVA, and chi-square.Results: Linear dimensions of ST ranged from 11.1 to 12.9 mm across readers, with a standard deviation of 2.0-2.2 mm. Normal ST (49.76%) and round ST (58.77%) were the most frequent. ST bridging was detected in 6.97%. Skeletal class I appeared most frequently (54.8%). Statistical significance was observed between age, gender, and ST length, with further significant age effects on ST shape. Moreover, age showed significant modification of ST shape, while skeletal parameters appeared unaffected by other ST parameters.Conclusions: These preliminary findings define normal ST dimensions in an Austrian population, offering reference values for clinical interpretation and broadening the available European data. Clear associations between morphological and demographic parameters were detected. Additionally, these findings may contribute to diagnostic and therapeutic strategies in orthodontics and craniofacial pathology. Future studies employing cone beam computed tomography (CBCT) along a larger sample size could enhance the generalizability of these findings.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"169-179"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11909075/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142633392","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

Radiographic biomarkers on grayscale gradient transition zone improve differentiation of deep caries/reversible pulpitis and chronic pulpitis through diagnostic model analysis. 灰度梯度过渡区的放射学生物标志物通过诊断模型分析提高了深龋/可逆性牙髓炎与慢性牙髓炎的鉴别能力。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-12-09 DOI: 10.1007/s11282-024-00792-0

Yuebo Liu, Ge Kong, Xiaoping Lu, Fantai Meng, Jizhi Zhao, Chunlan Guo, Kuo Wan

{"title":"Radiographic biomarkers on grayscale gradient transition zone improve differentiation of deep caries/reversible pulpitis and chronic pulpitis through diagnostic model analysis.","authors":"Yuebo Liu, Ge Kong, Xiaoping Lu, Fantai Meng, Jizhi Zhao, Chunlan Guo, Kuo Wan","doi":"10.1007/s11282-024-00792-0","DOIUrl":"10.1007/s11282-024-00792-0","url":null,"abstract":"Objectives: To explore the effectiveness of radiographic biomarkers on transition area (TA)-the grayscale gradient zone from carious lesion to normal dentine on radiographs-for identifying deep caries/reversible pulpitis and chronic pulpitis via diagnostic model analysis.Methods: This retrospective study included 392 caries cases. Canny edge detection was used to define the TA region. Texture parameters were extracted from the carious lesions (S1) and TA region (S2) by MaZda software on radiographs. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to select biomarkers. Diagnostic models were fitted and model performance was furtherly evaluated by internal and external validation, decision curve analysis was applied to evaluate clinical benefits.Results: TA-based biomarkers (e.g., TA thickness, TA ratio, S2-S(5,-5) contrast and S2-WavEnLL-s-4) were significantly associated with the diagnosis of deep caries/reversible pulpitis versus chronic pulpitis, model performance significantly improved when adding the above biomarkers (likelihood-ratio test; p < 0.05, with an increase of AUC from 0.67 (reference model) to 0.89), and these results were maintained in a small external validation cohort. Clinical benefit was greater with the application of TA-based biomarkers.Conclusion: TA-based biomarkers are proven to be an effective tool in differentiating deep caries/reversible pulpitis and chronic pulpitis, preoperative diagnosis was improved with the above biomarkers compared to the reference model.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"197-206"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142803428","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

A retrospective comparative fractal and radiomorphometric analysis of the effect of bisphosphonate use pattern and duration on the mandible. 双膦酸盐使用方式和持续时间对下颌骨影响的回顾性比较分形和放射形态分析。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2025-01-08 DOI: 10.1007/s11282-024-00801-2

Nida Geçkil, Katibe Tuğçe Temur

{"title":"A retrospective comparative fractal and radiomorphometric analysis of the effect of bisphosphonate use pattern and duration on the mandible.","authors":"Nida Geçkil, Katibe Tuğçe Temur","doi":"10.1007/s11282-024-00801-2","DOIUrl":"10.1007/s11282-024-00801-2","url":null,"abstract":"Aims: The aim of this study was to investigate the effect of two different bisphosphonate types on bone using dental panoramic radiographs (DPRs) and to compare these findings with a healthy cohort.Study design: Panoramic dental radiographs of bisphosphonate users (30) and healthy individuals (30) were retrospectively evaluated for the study. Regarding FA, standardized 50 × 50 pixel regions of interest (ROI) were identified for each patient. Moreover, the assessment encompassed Mandibular Cortical Width (MCW), Panoramic Mandibular Index (PMI), and Mandibular Cortical Index (MCI). A significance level of p < 0.05 was deemed to be statistically significant.Results: The case group showed significantly higher MCW and PMI measurements than the control group (p < 0.001). Right and left MCI measurements differed depending on the type of drug used (p = 0.008 and p = 0.019, respectively). No discernible correlation was found between the time elapsed since the last dose and any measurement values (p > 0.05).Conclusion: This study showed that bisphosphonate type and duration of drug use have a significant effect on changes in cortical bone structure. The persistence of these effects, unaffected by the time since the previous dose, suggests that bisphosphonates have a long-lasting effect on bone.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"276-284"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142959217","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

A novel deep learning-based pipeline architecture for pulp stone detection on panoramic radiographs. 一种新的基于深度学习的管道结构用于全景x光片上的牙髓结石检测。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2025-01-14 DOI: 10.1007/s11282-025-00804-7

Ceyda Gürhan, Hasan Yiğit, Selim Yılmaz, Cihat Çetinkaya

{"title":"A novel deep learning-based pipeline architecture for pulp stone detection on panoramic radiographs.","authors":"Ceyda Gürhan, Hasan Yiğit, Selim Yılmaz, Cihat Çetinkaya","doi":"10.1007/s11282-025-00804-7","DOIUrl":"10.1007/s11282-025-00804-7","url":null,"abstract":"Objectives: Pulp stones are ectopic calcifications located in pulp tissue. The aim of this study is to introduce a novel method for detecting pulp stones on panoramic radiography images using a deep learning-based two-stage pipeline architecture.Materials and methods: The first stage involved tooth localization with the YOLOv8 model, followed by pulp stone classification using ResNeXt. 375 panoramic images were included in this study, and a comprehensive set of evaluation metrics, including precision, recall, false-negative rate, false-positive rate, accuracy, and F1 score was employed to rigorously assess the performance of the proposed architecture.Results: Despite the limited annotated training data, the proposed method achieved impressive results: an accuracy of 95.4%, precision of 97.1%, recall of 96.1%, false-negative rate of 3.9%, false-positive rate of 6.1%, and a F1 score of 96.6%, outperforming existing approaches in pulp stone detection.Conclusions: Unlike current studies, this approach adopted a more realistic scenario by utilizing a small dataset with few annotated samples, acknowledging the time-consuming and error-prone nature of expert labeling. The proposed system is particularly beneficial for dental students and newly graduated dentists who lack sufficient clinical experience, as it aids in the automatic detection of pulpal calcifications. To the best of our knowledge, this is the first study in the literature that propose a pipeline architecture to address the PS detection tasks on panoramic images.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"285-295"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980664","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

Diagnostic performance of depth of invasion, thickness, and styloglossus and hyoglossus muscle invasion on magnetic resonance imaging in predicting potential neck lymph node metastasis in clinical N0 tongue cancer. 磁共振成像浸润深度、厚度及茎突舌骨和舌水肌浸润对临床N0舌癌颈部淋巴结转移的诊断价值。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-12-20 DOI: 10.1007/s11282-024-00796-w

Chika Yamada, Akira Baba, Satoshi Matsushima, Hideomi Yamauchi, Masato Nagaoka, Tomoya Suzuki, Yuika Kato, Hiroya Ojiri

{"title":"Diagnostic performance of depth of invasion, thickness, and styloglossus and hyoglossus muscle invasion on magnetic resonance imaging in predicting potential neck lymph node metastasis in clinical N0 tongue cancer.","authors":"Chika Yamada, Akira Baba, Satoshi Matsushima, Hideomi Yamauchi, Masato Nagaoka, Tomoya Suzuki, Yuika Kato, Hiroya Ojiri","doi":"10.1007/s11282-024-00796-w","DOIUrl":"10.1007/s11282-024-00796-w","url":null,"abstract":"Objectives: To evaluate previously reported quantitative (tumor thickness 11 mm and depth of invasion [DOI] 7.5 mm) and qualitative (styloglossus/hyoglossus muscle invasion [SHMI]) magnetic resonance imaging (MRI) parameters for predicting occult neck node metastasis in clinical N0 oral tongue squamous cell carcinoma.Methods: This single-center retrospective study included 76 patients. MRI images were independently reviewed by two radiologists for tumor thickness, DOI, and SHMI. Statistical analysis assessed the predictive capability of these parameters for 2-year potential lymph node metastasis.Results: Among the 76 cases, 30.2% developed 2-year potential lymph node metastasis. For tumor thickness ≥ 11 mm, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were 0.46, 0.68, 0.37, 0.75, and 0.61, respectively. DOI ≥ 7.5 mm exhibited a sensitivity, specificity, PPV, NPV, and accuracy of 0.73, 0.59, 0.42, 0.84, and 0.63, respectively. SHMI demonstrated a sensitivity, specificity, PPV, NPV, and accuracy of 0.87, 0.51, 0.46, 0.89, and 0.63, respectively.Conclusion: DOI ≥ 7.5 mm and SHMI demonstrated comparable diagnostic accuracy in predicting neck metastasis, surpassing tumor thickness of > 11 mm. These findings underscore their potential utility in guiding decisions concerning elective neck dissection.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"231-237"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866549","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

Automated segmentation of dental restorations using deep learning: exploring data augmentation techniques. 使用深度学习的牙修复体自动分割：探索数据增强技术。

IF 1.6 3区医学

Oral Radiology Pub Date : 2025-04-01 Epub Date: 2024-12-09 DOI: 10.1007/s11282-024-00794-y

Berrin Çelik, Muhammed Emin Baslak, Mehmet Zahid Genç, Mahmut Emin Çelik

{"title":"Automated segmentation of dental restorations using deep learning: exploring data augmentation techniques.","authors":"Berrin Çelik, Muhammed Emin Baslak, Mehmet Zahid Genç, Mahmut Emin Çelik","doi":"10.1007/s11282-024-00794-y","DOIUrl":"10.1007/s11282-024-00794-y","url":null,"abstract":"Objectives: Deep learning has revolutionized image analysis for dentistry. Automated segmentation of dental radiographs is of great importance towards digital dentistry. The performance of deep learning models heavily relies on the quality and diversity of the training data. Data augmentation is a widely used technique implemented in machine learning and deep learning to artificially increase the size and diversity of a training dataset by applying various transformations to the original data.Methods: This work aims to automatically segment implants, prostheses, and fillings in panoramic images using 9 different deep learning segmentation models. Later, it explores the effect of data augmentation methods on segmentation performance of the models. Eight different data augmentation techniques are examined. Performance is evaluated by well-accepted metrics such as intersection over union (IoU) and Dice coefficient.Results: While averaging the segmentation results for the three classes, IoU varies between 0.62 and 0.82 while Dice score is between 0.75 and 0.9 among deep learning models used. Augmentation techniques provided performance improvements of up to 3.37%, 5.75% and 8.75% for implant, prosthesis and filling classes, respectively.Conclusions: Findings reveal that choosing optimal augmentation strategies depends on both model architecture and dental structure type.","PeriodicalId":56103,"journal":{"name":"Oral Radiology","volume":" ","pages":"207-215"},"PeriodicalIF":1.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142803425","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