Pub Date : 2025-11-01Epub Date: 2025-10-16DOI: 10.1016/j.jobcr.2025.10.012
Deepak Agrawal, Sabah Zaheer, Vilas Newaskar
Introduction
Dental extractions in patients on antiplatelet therapy pose a bleeding risk. Current guidelines support continuing antiplatelet therapy during surgery, but effective local hemostasis is crucial. Chitosan, a biopolymer with haemostatic, antimicrobial, and wound-healing properties, may offer advantages over cotton gauze. This study evaluated chitosan dressing vs. standard gauze during dental extractions in patients on antiplatelet therapy.
Methodology
A prospective randomized study was conducted over 18 months at the Department of Oral and Maxillofacial Surgery, Government College of Dentistry, Indore, with 100 patients on antiplatelet therapy. Extraction sites were randomly assigned to Group A (chitosan) or Group B (cotton gauze). The primary outcome was time to hemostasis, with secondary outcomes including pain (VAS), Landry healing index, postoperative bleeding, and complications. Data were analyzed using SPSS v25.0.
Results
Group A showed significantly faster hemostasis (median 0.67 min) compared to Group B (median 4.5 min; p < 0.001). Bleeding ceased within 3 min in all Group A sockets vs. 11 % in Group B (p < 0.001). Group A also had lower pain scores and higher healing index values at Day 7 (both p < 0.001). Dry socket incidence was low and similar between groups.
Conclusion
Chitosan dressing appears to be a promising adjunct for achieving rapid hemostasis, reducing postoperative discomfort, and improving early healing following dental extractions in patients on antiplatelet therapy. Larger multicenter studies with longer follow-up are recommended to confirm these findings and explore broader clinical applications.
{"title":"Efficacy of chitosan dressing as a local haemostatic agent in the management of dental extractions in patients on antiplatelet therapy. A prospective randomized study","authors":"Deepak Agrawal, Sabah Zaheer, Vilas Newaskar","doi":"10.1016/j.jobcr.2025.10.012","DOIUrl":"10.1016/j.jobcr.2025.10.012","url":null,"abstract":"<div><h3>Introduction</h3><div>Dental extractions in patients on antiplatelet therapy pose a bleeding risk. Current guidelines support continuing antiplatelet therapy during surgery, but effective local hemostasis is crucial. Chitosan, a biopolymer with haemostatic, antimicrobial, and wound-healing properties, may offer advantages over cotton gauze. This study evaluated chitosan dressing vs. standard gauze during dental extractions in patients on antiplatelet therapy.</div></div><div><h3>Methodology</h3><div>A prospective randomized study was conducted over 18 months at the Department of Oral and Maxillofacial Surgery, Government College of Dentistry, Indore, with 100 patients on antiplatelet therapy. Extraction sites were randomly assigned to Group A (chitosan) or Group B (cotton gauze). The primary outcome was time to hemostasis, with secondary outcomes including pain (VAS), Landry healing index, postoperative bleeding, and complications. Data were analyzed using SPSS v25.0.</div></div><div><h3>Results</h3><div>Group A showed significantly faster hemostasis (median 0.67 min) compared to Group B (median 4.5 min; p < 0.001). Bleeding ceased within 3 min in all Group A sockets vs. 11 % in Group B (p < 0.001). Group A also had lower pain scores and higher healing index values at Day 7 (both p < 0.001). Dry socket incidence was low and similar between groups.</div></div><div><h3>Conclusion</h3><div>Chitosan dressing appears to be a promising adjunct for achieving rapid hemostasis, reducing postoperative discomfort, and improving early healing following dental extractions in patients on antiplatelet therapy. Larger multicenter studies with longer follow-up are recommended to confirm these findings and explore broader clinical applications.</div></div>","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1715-1720"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145325163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-01Epub Date: 2025-08-28DOI: 10.1016/j.jobcr.2025.08.019
Rini Widyaningrum , Eha Renwi Astuti , Adioro Soetojo , Amalia Nur Faadiya , Aga Satria Nurrachman , Netya Dzihni Kinanggit , Abdul Harits Iftikar Nasution
Background
Periodontal disease is an inflammatory condition causing chronic damage to the tooth-supporting connective tissues, leading to tooth loss in adults. Diagnosing periodontitis requires clinical and radiographic examinations, with panoramic radiographs crucial in identifying and assessing its severity and staging. Convolutional Neural Networks (CNNs), a deep learning method for visual data analysis, and Dense Convolutional Networks (DenseNet), which utilize direct feed-forward connections between layers, enable high-performance computer vision tasks with reduced computational demands. This study aims to evaluate the performance of a hybrid two-stage CNN integrating Mask R-CNN with DenseNet169 for detecting and staging periodontitis in panoramic radiographs.
Methods
A total of 600 panoramic radiographs were divided into training (70 %), validation (10 %), and testing (20 %) datasets, with an additional 100 external radiographs used as a final testing set. Four types of annotations were applied: tooth segmentation, radiographic bone loss (RBL), cementoenamel junction (CEJ) area, and periodontitis staging (normal, stage 1, 2, 3, and 4). Mask R-CNN was employed for segmentation training to detect teeth, CEJ, and RBL, while DenseNet169 served as the classifier for periodontitis staging.
Results
The hybrid two-stage CNN achieved a periodontitis staging performance on the external testing set with specificity and accuracy of 0.88 and 0.80, respectively.
Conclusion
These results demonstrate the potential of this hybrid two-stage CNN model as a diagnostic aid for periodontitis in panoramic radiographs. Further development of this approach could enhance its clinical applicability and accuracy.
{"title":"Hybrid two-stage CNN for detection and staging of periodontitis on panoramic radiographs","authors":"Rini Widyaningrum , Eha Renwi Astuti , Adioro Soetojo , Amalia Nur Faadiya , Aga Satria Nurrachman , Netya Dzihni Kinanggit , Abdul Harits Iftikar Nasution","doi":"10.1016/j.jobcr.2025.08.019","DOIUrl":"10.1016/j.jobcr.2025.08.019","url":null,"abstract":"<div><h3>Background</h3><div>Periodontal disease is an inflammatory condition causing chronic damage to the tooth-supporting connective tissues, leading to tooth loss in adults. Diagnosing periodontitis requires clinical and radiographic examinations, with panoramic radiographs crucial in identifying and assessing its severity and staging. Convolutional Neural Networks (CNNs), a deep learning method for visual data analysis, and Dense Convolutional Networks (DenseNet), which utilize direct feed-forward connections between layers, enable high-performance computer vision tasks with reduced computational demands. This study aims to evaluate the performance of a hybrid two-stage CNN integrating Mask R-CNN with DenseNet169 for detecting and staging periodontitis in panoramic radiographs.</div></div><div><h3>Methods</h3><div>A total of 600 panoramic radiographs were divided into training (70 %), validation (10 %), and testing (20 %) datasets, with an additional 100 external radiographs used as a final testing set. Four types of annotations were applied: tooth segmentation, radiographic bone loss (RBL), cementoenamel junction (CEJ) area, and periodontitis staging (normal, stage 1, 2, 3, and 4). Mask R-CNN was employed for segmentation training to detect teeth, CEJ, and RBL, while DenseNet169 served as the classifier for periodontitis staging.</div></div><div><h3>Results</h3><div>The hybrid two-stage CNN achieved a periodontitis staging performance on the external testing set with specificity and accuracy of 0.88 and 0.80, respectively.</div></div><div><h3>Conclusion</h3><div>These results demonstrate the potential of this hybrid two-stage CNN model as a diagnostic aid for periodontitis in panoramic radiographs. Further development of this approach could enhance its clinical applicability and accuracy.</div></div>","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1392-1399"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144908002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<div><h3>Background</h3><div>Dental caries is a significant public health concern, particularly in children, where occlusal surfaces are at high risk due to complex pit and fissure morphology. Pit and fissure sealants are a well-established preventive measure, with resin-based sealants offering superior retention compared to glass ionomer cement (GIC) sealants. Chitosan, a naturally derived biopolymer, may enhance resin-based sealants by improving their mechanical strength, antibacterial action, and adhesion, leading to better retention and reduced need for reapplication. This study evaluated the 6-month retention and caries-preventive effectiveness of a 2 % chitosan-modified resin-based sealant versus a conventional sealant.</div></div><div><h3>Methodology</h3><div>A double-blind, split-mouth randomised clinical trial (CTRI/2023/06/054321) was conducted in a pediatric dental setting. A total of 38 children aged 6–10 years, each with four fully erupted, caries-free permanent first molars, were enrolled, resulting in a total of 152 Molars out of which 32 children (128 teeth) completed the trial. Each participant received both a conventional resin-based sealant (Clinpro™) and a 2 % chitosan-modified Clinpro™ sealant on contralateral molars. Randomisation was performed using a SNOSE (Sequentially Numbered Opaque Sealed Envelope) to determine the allocation of sealants on each side. Teeth were prepared by professional prophylaxis using pumice slurry, followed by etching with 37 % phosphoric acid, rinsing, and drying per manufacturer's instructions before sealant application. Both sealants were light-cured for 20 s and evaluated for proper placement. Clinical assessments were conducted at baseline, 3 months, and 6 months. Primary outcomes included sealant retention, evaluated using modified retention criteria (complete, partial, or total loss), and caries incidence, assessed using the International Caries Detection and Assessment System-II (ICDAS-II). Data were analyzed using STATA 18 software, and statistical significance was determined using Chi-square test to compare categorical variables, Shapiro-Wilk test was used to assess normality. Friedman test was conducted for within-group comparisons over time, followed by the Durbin-Conover post-hoc test for pairwise comparisons. Between-group comparisons of ICDAS-II scores were conducted using the Wilcoxon signed rank test. Statistical significance was set at <em>p</em> < 0.05.</div></div><div><h3>Results</h3><div>At 3 months, complete retention was observed in 95.31 % of molars treated with the chitosan-modified sealant, compared to 81.25 % in the conventional sealant group. By 6 months, retention rates declined slightly to 92.19 % in the study group and 76.56 % in the control group, with the differences remaining statistically significant (p < 0.05). Regarding caries prevention, at 3 months, 100 % of teeth in the study group remained caries-free (ICDAS-II score 0), compared to 89.06 % in the cont
{"title":"Evaluation of sealant retention and caries prevention of 2 % chitosan-based pit and fissure sealants in permanent 1st molars – A randomised trial","authors":"Naina Kumar, Kavita Rai, Krithika Shetty, Manju Raman Nair","doi":"10.1016/j.jobcr.2025.08.032","DOIUrl":"10.1016/j.jobcr.2025.08.032","url":null,"abstract":"<div><h3>Background</h3><div>Dental caries is a significant public health concern, particularly in children, where occlusal surfaces are at high risk due to complex pit and fissure morphology. Pit and fissure sealants are a well-established preventive measure, with resin-based sealants offering superior retention compared to glass ionomer cement (GIC) sealants. Chitosan, a naturally derived biopolymer, may enhance resin-based sealants by improving their mechanical strength, antibacterial action, and adhesion, leading to better retention and reduced need for reapplication. This study evaluated the 6-month retention and caries-preventive effectiveness of a 2 % chitosan-modified resin-based sealant versus a conventional sealant.</div></div><div><h3>Methodology</h3><div>A double-blind, split-mouth randomised clinical trial (CTRI/2023/06/054321) was conducted in a pediatric dental setting. A total of 38 children aged 6–10 years, each with four fully erupted, caries-free permanent first molars, were enrolled, resulting in a total of 152 Molars out of which 32 children (128 teeth) completed the trial. Each participant received both a conventional resin-based sealant (Clinpro™) and a 2 % chitosan-modified Clinpro™ sealant on contralateral molars. Randomisation was performed using a SNOSE (Sequentially Numbered Opaque Sealed Envelope) to determine the allocation of sealants on each side. Teeth were prepared by professional prophylaxis using pumice slurry, followed by etching with 37 % phosphoric acid, rinsing, and drying per manufacturer's instructions before sealant application. Both sealants were light-cured for 20 s and evaluated for proper placement. Clinical assessments were conducted at baseline, 3 months, and 6 months. Primary outcomes included sealant retention, evaluated using modified retention criteria (complete, partial, or total loss), and caries incidence, assessed using the International Caries Detection and Assessment System-II (ICDAS-II). Data were analyzed using STATA 18 software, and statistical significance was determined using Chi-square test to compare categorical variables, Shapiro-Wilk test was used to assess normality. Friedman test was conducted for within-group comparisons over time, followed by the Durbin-Conover post-hoc test for pairwise comparisons. Between-group comparisons of ICDAS-II scores were conducted using the Wilcoxon signed rank test. Statistical significance was set at <em>p</em> < 0.05.</div></div><div><h3>Results</h3><div>At 3 months, complete retention was observed in 95.31 % of molars treated with the chitosan-modified sealant, compared to 81.25 % in the conventional sealant group. By 6 months, retention rates declined slightly to 92.19 % in the study group and 76.56 % in the control group, with the differences remaining statistically significant (p < 0.05). Regarding caries prevention, at 3 months, 100 % of teeth in the study group remained caries-free (ICDAS-II score 0), compared to 89.06 % in the cont","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1490-1496"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145018545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-01Epub Date: 2025-09-10DOI: 10.1016/j.jobcr.2025.08.027
Sonal Bhatia , Vinay Kumar Gupta , Sumit Kumar , Gaurav Mishra , Seema Malhotra , Khushboo Arif , Atrey Pai Khot , Aman Rajput , Angad Mahajan
Objective
The purpose of this scoping review was to systematically search through the evidence for the applications of artificial intelligence (AI) for caries risk assessment (CRA) or prediction (CRP), determine the scope of the methodologies used, summarize their performance metrics, and report limitations and challenges (if any).
Design
A structured and comprehensive search of three electronic databases, MEDLINE, EMBASE, and Google Scholar, was performed to yield results from 2013 to 2023. Studies were selected through title, abstract, and full-text screening based on the selection criteria. Charting of the extracted data was performed using a self-designed checklist with eight dimensions.
Results
The electronic database search retrieved 3059 articles. Ultimately, 13 articles were included in the review. The most used methods were logistic regression (n = 9) and random forest (n = 8). The performance of the included models was measured variably. The reported performance metrics of the models were heterogeneous in nature; the sensitivity ranged from 0.59 to 0.996, while the specificity ranged from 0.531 to 0.943. The most frequently utilized predictors include socio-demographic factors, oral hygiene habits, and dietary habits.
Conclusion
Of the AI-based CRA models analyzed, machine learning algorithms were most frequently used. This review highlights that AI methods most probably show superior specificity and better performance than traditional methods. The application of these algorithms can have significant implications for the population impacted by pertinent chronic diseases that are avoidable through risk reduction, such as dental caries.
{"title":"Artificial intelligence based techniques for caries risk prediction and assessment: A scoping review","authors":"Sonal Bhatia , Vinay Kumar Gupta , Sumit Kumar , Gaurav Mishra , Seema Malhotra , Khushboo Arif , Atrey Pai Khot , Aman Rajput , Angad Mahajan","doi":"10.1016/j.jobcr.2025.08.027","DOIUrl":"10.1016/j.jobcr.2025.08.027","url":null,"abstract":"<div><h3>Objective</h3><div>The purpose of this scoping review was to systematically search through the evidence for the applications of artificial intelligence (AI) for caries risk assessment (CRA) or prediction (CRP), determine the scope of the methodologies used, summarize their performance metrics, and report limitations and challenges (if any).</div></div><div><h3>Design</h3><div>A structured and comprehensive search of three electronic databases, MEDLINE, EMBASE, and Google Scholar, was performed to yield results from 2013 to 2023. Studies were selected through title, abstract, and full-text screening based on the selection criteria. Charting of the extracted data was performed using a self-designed checklist with eight dimensions.</div></div><div><h3>Results</h3><div>The electronic database search retrieved 3059 articles. Ultimately, 13 articles were included in the review. The most used methods were logistic regression (n = 9) and random forest (n = 8). The performance of the included models was measured variably. The reported performance metrics of the models were heterogeneous in nature; the sensitivity ranged from 0.59 to 0.996, while the specificity ranged from 0.531 to 0.943. The most frequently utilized predictors include socio-demographic factors, oral hygiene habits, and dietary habits.</div></div><div><h3>Conclusion</h3><div>Of the AI-based CRA models analyzed, machine learning algorithms were most frequently used. This review highlights that AI methods most probably show superior specificity and better performance than traditional methods. The application of these algorithms can have significant implications for the population impacted by pertinent chronic diseases that are avoidable through risk reduction, such as dental caries.</div></div>","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1497-1507"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145026800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Introduction: and aim: Due to its excellent mechanical strength and biocompatibility, Polyetherketoneketone (PEKK) is emerging as a potential substitute for titanium in dental implant applications. The aim of the study was to evaluate its cytotoxicity, pro-inflammatory responses, and molecular interactions to assess its potential in implant applications.
Methods: This study evaluated the cytotoxicity, pro-inflammatory cytokine responses, and molecular interactions of PEKK compared to titanium. Disc-shaped samples (10 mm × 2 mm) were fabricated for each material following ISO standards. Human periodontal fibroblast cells were cultured and treated with the samples for cytotoxicity assessment using the MTT assay, while pro-inflammatory cytokine gene expression (IL-1β, TNF-α) was analyzed via real-time PCR. Molecular docking was conducted using AutoDock to investigate PEKK's binding interactions with cytokines, and data was analyzed with one-way ANOVA and post hoc test (P < 0.05).
Results: PEKK showed comparable cytocompatibility to titanium, yielding similar outcomes in cell viability (P > 0.05) or pro-inflammatory cytokine expression (P > 0.05). Molecular docking revealed strong interactions with IL-1β (-8.9 kcal/mol) and TNF-α (-7.3 kcal/mol).
Conclusion: This study demonstrates that PEKK exhibits comparable cytocompatibility and pro-inflammatory responses to titanium, with a potential to modulate inflammatory pathways. Further in vivo studies are needed to confirm its clinical viability as an implant material.
Clinical relevance: This study gives the clue of PEKK as an aesthetic implant biomaterial and it can be useful as an alternative to Titanium dental implant.
{"title":"Assessing the role of PEKK implant material on cytotoxicity, inflammatory response, and molecular interactions with pro-inflammatory cytokines: An in-vitro and in-silico study.","authors":"Amrutha Shenoy, Subhabrata Maiti, Selvaraj Jayaram, Pradeep Kumar Yadalam, Jessy Paulraj","doi":"10.1016/j.jobcr.2025.08.004","DOIUrl":"10.1016/j.jobcr.2025.08.004","url":null,"abstract":"<p><strong>Introduction: </strong>and aim: Due to its excellent mechanical strength and biocompatibility, Polyetherketoneketone (PEKK) is emerging as a potential substitute for titanium in dental implant applications. The aim of the study was to evaluate its cytotoxicity, pro-inflammatory responses, and molecular interactions to assess its potential in implant applications.</p><p><strong>Methods: </strong>This study evaluated the cytotoxicity, pro-inflammatory cytokine responses, and molecular interactions of PEKK compared to titanium. Disc-shaped samples (10 mm × 2 mm) were fabricated for each material following ISO standards. Human periodontal fibroblast cells were cultured and treated with the samples for cytotoxicity assessment using the MTT assay, while pro-inflammatory cytokine gene expression (IL-1β, TNF-α) was analyzed via real-time PCR. Molecular docking was conducted using AutoDock to investigate PEKK's binding interactions with cytokines, and data was analyzed with one-way ANOVA and post hoc test (P < 0.05).</p><p><strong>Results: </strong>PEKK showed comparable cytocompatibility to titanium, yielding similar outcomes in cell viability (P > 0.05) or pro-inflammatory cytokine expression (P > 0.05). Molecular docking revealed strong interactions with IL-1β (-8.9 kcal/mol) and TNF-α (-7.3 kcal/mol).</p><p><strong>Conclusion: </strong>This study demonstrates that PEKK exhibits comparable cytocompatibility and pro-inflammatory responses to titanium, with a potential to modulate inflammatory pathways. Further in vivo studies are needed to confirm its clinical viability as an implant material.</p><p><strong>Clinical relevance: </strong>This study gives the clue of PEKK as an aesthetic implant biomaterial and it can be useful as an alternative to Titanium dental implant.</p>","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"1218-1223"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12357294/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144873665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-01Epub Date: 2025-12-20DOI: 10.1016/j.jobcr.2025.11.002
Anand Gupta , Naveen Aggarwal
{"title":"Editorial: Special issue on application of artificial intelligence in oral and craniofacial care","authors":"Anand Gupta , Naveen Aggarwal","doi":"10.1016/j.jobcr.2025.11.002","DOIUrl":"10.1016/j.jobcr.2025.11.002","url":null,"abstract":"","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1874-1875"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145796590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-01Epub Date: 2025-09-22DOI: 10.1016/j.jobcr.2025.09.015
Pradeep Kumar Yadalam
<div><h3>Introduction</h3><div>Complex regulatory networks controlled by transcription factor (TF)–gene interactions are involved in inflammatory bone diseases, such as periodontitis. Understanding these networks is crucial for identifying master regulators and potential treatment targets. Current models frequently use correlation-based or black-box machine learning techniques, which are not structurally accurate or biologically interpretable. Moreover, most frameworks do not utilize the representational power of quantum-derived data features. This study overcomes these constraints by combining quantum-enhanced graph neural networks to decode TF-gene regulatory networks implicated in periodontal bone inflammation.</div></div><div><h3>Methods</h3><div>We constructed a directed transcription factor (TF)- gene regulatory network using 1207 carefully selected interactions from the TRRUST v2 human database, which encompassed 231 transcription factors and 536 target genes. One-hot encoded node features were used to train the Graph Autoencoder (GAE) and Graph Generative Adversarial Network (Graph GAN) architectures. We applied quantum data feature extraction to enhance node representation using variational quantum circuits constructed in PennyLane, where classical embeddings were encoded into qubit rotations and entangled states. New quantum features were created by measuring the expectation values of Pauli-Z operators. Distribution divergence measures (KL, JS, Wasserstein, MMD), embedding quality metrics (silhouette score, centrality correlation), and link prediction metrics (AUC, Average Precision) were used to assess performance.</div></div><div><h3>Results</h3><div>On every metric, GAE performed noticeably better than Graph GAN. It performed better in clustering (silhouette score = 0.272 vs. 0.107 for GAN) and link prediction accuracy (AUC = 0.997, AP = 0.994). While GAN embeddings displayed little structural alignment, GAE-generated embeddings strongly correlated with network centrality measures, emphasizing biological interpretability. Quantum-enhanced features revealed distinct regulatory modules associated with inflammation and bone resorption pathways, and they maintained the network topology more effectively. We found central regulators with high embedding scores, including NF-κB and STAT3. Distributional analyses validated the fundamental differences between GAE and GAN embeddings with a symmetric KL divergence of 6.76 and a Jensen-Shannon distance of 0.47.</div></div><div><h3>Conclusion</h3><div>Our results demonstrate that Graph Autoencoders provide a reliable and comprehensible framework for simulating TF-gene regulatory networks, particularly when combined with quantum-derived feature extraction. The GAE is ideally suited to elucidating the molecular underpinnings of periodontal bone inflammation due to its ability to maintain biological structure, pinpoint important regulatory hubs, and enhance downstream analyses, such as clustering. Th
{"title":"Quantum graph embedding of transcription factor–gene networks reveals key modules in periodontal bone inflammation: Comparative analysis of GAE and GAN","authors":"Pradeep Kumar Yadalam","doi":"10.1016/j.jobcr.2025.09.015","DOIUrl":"10.1016/j.jobcr.2025.09.015","url":null,"abstract":"<div><h3>Introduction</h3><div>Complex regulatory networks controlled by transcription factor (TF)–gene interactions are involved in inflammatory bone diseases, such as periodontitis. Understanding these networks is crucial for identifying master regulators and potential treatment targets. Current models frequently use correlation-based or black-box machine learning techniques, which are not structurally accurate or biologically interpretable. Moreover, most frameworks do not utilize the representational power of quantum-derived data features. This study overcomes these constraints by combining quantum-enhanced graph neural networks to decode TF-gene regulatory networks implicated in periodontal bone inflammation.</div></div><div><h3>Methods</h3><div>We constructed a directed transcription factor (TF)- gene regulatory network using 1207 carefully selected interactions from the TRRUST v2 human database, which encompassed 231 transcription factors and 536 target genes. One-hot encoded node features were used to train the Graph Autoencoder (GAE) and Graph Generative Adversarial Network (Graph GAN) architectures. We applied quantum data feature extraction to enhance node representation using variational quantum circuits constructed in PennyLane, where classical embeddings were encoded into qubit rotations and entangled states. New quantum features were created by measuring the expectation values of Pauli-Z operators. Distribution divergence measures (KL, JS, Wasserstein, MMD), embedding quality metrics (silhouette score, centrality correlation), and link prediction metrics (AUC, Average Precision) were used to assess performance.</div></div><div><h3>Results</h3><div>On every metric, GAE performed noticeably better than Graph GAN. It performed better in clustering (silhouette score = 0.272 vs. 0.107 for GAN) and link prediction accuracy (AUC = 0.997, AP = 0.994). While GAN embeddings displayed little structural alignment, GAE-generated embeddings strongly correlated with network centrality measures, emphasizing biological interpretability. Quantum-enhanced features revealed distinct regulatory modules associated with inflammation and bone resorption pathways, and they maintained the network topology more effectively. We found central regulators with high embedding scores, including NF-κB and STAT3. Distributional analyses validated the fundamental differences between GAE and GAN embeddings with a symmetric KL divergence of 6.76 and a Jensen-Shannon distance of 0.47.</div></div><div><h3>Conclusion</h3><div>Our results demonstrate that Graph Autoencoders provide a reliable and comprehensible framework for simulating TF-gene regulatory networks, particularly when combined with quantum-derived feature extraction. The GAE is ideally suited to elucidating the molecular underpinnings of periodontal bone inflammation due to its ability to maintain biological structure, pinpoint important regulatory hubs, and enhance downstream analyses, such as clustering. Th","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1563-1572"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-01Epub Date: 2025-09-22DOI: 10.1016/j.jobcr.2025.09.010
Abhinav Chopra , Anand Gupta , Naveen Aggarwal
Background
Dental age estimation constitutes a cornerstone in forensic odontology, pediatric dentistry, and medico-legal investigations. Traditional radiographic methods such as those by Demirjian, Willems, and Cameriere, though widely validated, are limited by examiner subjectivity, population-specific calibration, and low scalability. This narrative review examines the current landscape of artificial intelligence (AI)-driven dental age estimation, with a focus on deep learning technologies, comparative advantages over conventional methodologies, and applicability across clinical, forensic, and legal domains.
Methods
A literature search was conducted to identify original studies and systematic reviews that employed machine learning (ML) and convolutional neural networks (CNNs) for dental age estimation using panoramic radiographs or cone-beam computed tomography (CBCT). Emphasis was placed on studies reporting model architecture, mean absolute error (MAE), classification accuracy, and external validation.
Results
AI-based models, particularly CNNs, demonstrated superior diagnostic performance with MAEs ranging from 0.03 to 0.7 years and classification accuracies exceeding 90 % at critical legal thresholds. These systems provide automated tooth detection, segmentation, and staging, with outputs that are rapid, objective, and reproducible. Nonetheless, critical limitations persist, including algorithmic opacity, demographic bias due to non-representative training datasets, and absence of international validation standards.
Conclusion
AI technologies represent a paradigm shift in dental age estimation, offering enhanced precision and operational efficiency. To facilitate clinical translation and forensic admissibility, future efforts must prioritize population-diverse training datasets, transparent algorithmic design, and consensus-driven regulatory frameworks.
{"title":"Artificial intelligence in dental age estimation- applications, technological advances and legal aspects: A narrative review","authors":"Abhinav Chopra , Anand Gupta , Naveen Aggarwal","doi":"10.1016/j.jobcr.2025.09.010","DOIUrl":"10.1016/j.jobcr.2025.09.010","url":null,"abstract":"<div><h3>Background</h3><div>Dental age estimation constitutes a cornerstone in forensic odontology, pediatric dentistry, and medico-legal investigations. Traditional radiographic methods such as those by Demirjian, Willems, and Cameriere, though widely validated, are limited by examiner subjectivity, population-specific calibration, and low scalability. This narrative review examines the current landscape of artificial intelligence (AI)-driven dental age estimation, with a focus on deep learning technologies, comparative advantages over conventional methodologies, and applicability across clinical, forensic, and legal domains.</div></div><div><h3>Methods</h3><div>A literature search was conducted to identify original studies and systematic reviews that employed machine learning (ML) and convolutional neural networks (CNNs) for dental age estimation using panoramic radiographs or cone-beam computed tomography (CBCT). Emphasis was placed on studies reporting model architecture, mean absolute error (MAE), classification accuracy, and external validation.</div></div><div><h3>Results</h3><div>AI-based models, particularly CNNs, demonstrated superior diagnostic performance with MAEs ranging from 0.03 to 0.7 years and classification accuracies exceeding 90 % at critical legal thresholds. These systems provide automated tooth detection, segmentation, and staging, with outputs that are rapid, objective, and reproducible. Nonetheless, critical limitations persist, including algorithmic opacity, demographic bias due to non-representative training datasets, and absence of international validation standards.</div></div><div><h3>Conclusion</h3><div>AI technologies represent a paradigm shift in dental age estimation, offering enhanced precision and operational efficiency. To facilitate clinical translation and forensic admissibility, future efforts must prioritize population-diverse training datasets, transparent algorithmic design, and consensus-driven regulatory frameworks.</div></div>","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1534-1538"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The success of pulpotomy depends significantly on the choice of materials and techniques used, including hemostatic agents. Despite extensive research, there remains a lack of consensus on the most effective hemostatic agent for pulpotomy. This study aimed to systematically review the literature on the efficacy of hemostatic agents on the outcome of pulpotomy.
Methods
A comprehensive literature search was done in the different electronic databases namely PubMed, Scopus, EBSCO host. Supplementary search included grey literature The literature search performed included all the relevant articles published up to 31st March 2025. The risk of Bias for the in vivo studies was evaluated by JBI critical appraisal tool and New Castle Ottawa scale for cohort study and retrospective studies and qualitative synthesis was evaluated using National Services Scotland guidelines Meta analysis could not be performed because of the heterogeneity of the studies.
Results
A total of eight studies were included in this review. Five studies concluded that sodium hypochlorite was more effective as a hemostatic agent in both primary teeth and permanent teeth. Two studies found potassium titanyl phosphate (KTP) laser treatment produced superior clinical and radiographic outcomes in permanent teeth. Another study showed better results with cryotherapy in the permanent teeth.
Conclusion
Sodium hypochlorite demonstrated superior hemostatic potential in primary teeth, whereas in permanent teeth, potassium titanyl phosphate (KTP) laser and cryotherapy yielded promising results in clinical and radiographic outcomes with no statistically significant results when compared to sodium hypochlorite.
{"title":"Effect of hemostatic agents on the outcome of pulpotomy in primary and permanent teeth: A systematic review","authors":"Aakash Kumar, Monika Tandan, Mrinalini Mrinalini, Sucheta Jala, Anabathula Praharsha, Vishakha Kumar Mendiratta","doi":"10.1016/j.jobcr.2025.10.019","DOIUrl":"10.1016/j.jobcr.2025.10.019","url":null,"abstract":"<div><h3>Aim</h3><div>The success of pulpotomy depends significantly on the choice of materials and techniques used, including hemostatic agents. Despite extensive research, there remains a lack of consensus on the most effective hemostatic agent for pulpotomy. This study aimed to systematically review the literature on the efficacy of hemostatic agents on the outcome of pulpotomy.</div></div><div><h3>Methods</h3><div>A comprehensive literature search was done in the different electronic databases namely PubMed, Scopus, EBSCO host. Supplementary search included grey literature The literature search performed included all the relevant articles published up to 31<sup>st</sup> March 2025. The risk of Bias for the <em>in vivo</em> studies was evaluated by JBI critical appraisal tool and New Castle Ottawa scale for cohort study and retrospective studies and qualitative synthesis was evaluated using National Services Scotland guidelines Meta analysis could not be performed because of the heterogeneity of the studies.</div></div><div><h3>Results</h3><div>A total of eight studies were included in this review. Five studies concluded that sodium hypochlorite was more effective as a hemostatic agent in both primary teeth and permanent teeth. Two studies found potassium titanyl phosphate (KTP) laser treatment produced superior clinical and radiographic outcomes in permanent teeth. Another study showed better results with cryotherapy in the permanent teeth.</div></div><div><h3>Conclusion</h3><div>Sodium hypochlorite demonstrated superior hemostatic potential in primary teeth, whereas in permanent teeth, potassium titanyl phosphate (KTP) laser and cryotherapy yielded promising results in clinical and radiographic outcomes with no statistically significant results <u>when</u> compared to sodium hypochlorite.</div></div>","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1813-1823"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145415860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-01Epub Date: 2025-10-04DOI: 10.1016/j.jobcr.2025.09.025
M. Madhumitha , Devika S. Pillai , Pradeep Kumar Yadalam , Prasanthi Sitaraman
Background
Artificial Intelligence (AI) significantly enhances the diagnosis of pericoronal radiolucency by accurately interpreting dental radiographs. Through advanced algorithms, AI can identify early signs of abnormalities near unerupted teeth. This helps clinicians differentiate between benign and malignant conditions, leading to more informed decisions; improved treatment plans, ultimately benefiting patient care and outcomes.
Method
ology: A total of 2500 radiographs were screened of which 1070 radiographs were used in the study. 315 images of pericoronal radiolucency in mandibular third molars and 755 images of the normal mandibular third molars were included. The AI algorithms employed in the study were Logistic regression and Naive Bayes. Accuracy, sensitivity, specificity, precision, recall, F1, AUC-ROC curve were used for performance evaluation.
Results
This study found that Logistic regression model showed slightly higher accuracy than Naive Bayes model in predicting peri coronal radiolucency. In performance prediction for logistic regression model in predicting pericoronal radiolucency in third molars in 315 images, showed a slightly higher rate of prediction of 58.3 %, whereas, Naive Bayes model showed a comparatively lower prediction of pericoronal radiolucency, 52.2 %. During performance evaluation, Logistic regression performed better in CA, F1, and Recall, and Naive Bayes performed better in AUC and Precision model.
Conclusion
The current study demonstrated that Logistic regression have slightly highest accuracy in detecting pericoronal radiolucency in digital orthopantomogram images, which is consistent with the normal radiographic evaluation. Also, the Naive Bayes algorithm showed a fairly considerable performance in the classification of pericoronal radiolucencies.
{"title":"Role of artificial intelligence in diagnosing pericoronal radiolucency","authors":"M. Madhumitha , Devika S. Pillai , Pradeep Kumar Yadalam , Prasanthi Sitaraman","doi":"10.1016/j.jobcr.2025.09.025","DOIUrl":"10.1016/j.jobcr.2025.09.025","url":null,"abstract":"<div><h3>Background</h3><div>Artificial Intelligence (AI) significantly enhances the diagnosis of pericoronal radiolucency by accurately interpreting dental radiographs. Through advanced algorithms, AI can identify early signs of abnormalities near unerupted teeth. This helps clinicians differentiate between benign and malignant conditions, leading to more informed decisions; improved treatment plans, ultimately benefiting patient care and outcomes.</div></div><div><h3>Method</h3><div>ology: A total of 2500 radiographs were screened of which 1070 radiographs were used in the study. 315 images of pericoronal radiolucency in mandibular third molars and 755 images of the normal mandibular third molars were included. The AI algorithms employed in the study were Logistic regression and Naive Bayes. Accuracy, sensitivity, specificity, precision, recall, F1, AUC-ROC curve were used for performance evaluation.</div></div><div><h3>Results</h3><div>This study found that Logistic regression model showed slightly higher accuracy than Naive Bayes model in predicting peri coronal radiolucency. In performance prediction for logistic regression model in predicting pericoronal radiolucency in third molars in 315 images, showed a slightly higher rate of prediction of 58.3 %, whereas, Naive Bayes model showed a comparatively lower prediction of pericoronal radiolucency, 52.2 %. During performance evaluation, Logistic regression performed better in CA, F1, and Recall, and Naive Bayes performed better in AUC and Precision model.</div></div><div><h3>Conclusion</h3><div>The current study demonstrated that Logistic regression have slightly highest accuracy in detecting pericoronal radiolucency in digital orthopantomogram images, which is consistent with the normal radiographic evaluation. Also, the Naive Bayes algorithm showed a fairly considerable performance in the classification of pericoronal radiolucencies.</div></div>","PeriodicalId":16609,"journal":{"name":"Journal of oral biology and craniofacial research","volume":"15 6","pages":"Pages 1648-1654"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145265436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号