Deep-learning performance in identifying and classifying dental implant systems from dental imaging: a systematic review and meta-analysis.

Deep learning (DL) offers promising performance in computer vision tasks and is highly suitable for dental image recognition and analysis. We evaluated the accuracy of DL algorithms in identifying and classifying dental implant systems (DISs) using dental imaging. In this systematic review and meta-analysis, we explored the MEDLINE/PubMed, Scopus, Embase, and Google Scholar databases and identified studies published between January 2011 and March 2022. Studies conducted on DL approaches for DIS identification or classification were included, and the accuracy of the DL models was evaluated using panoramic and periapical radiographic images. The quality of the selected studies was assessed using QUADAS-2. This review was registered with PROSPERO (CRDCRD42022309624). From 1,293 identified records, 9 studies were included in this systematic review and meta-analysis. The DL-based implant classification accuracy was no less than 70.75% (95% confidence interval [CI], 65.6%-75.9%) and no higher than 98.19 (95% CI, 97.8%-98.5%). The weighted accuracy was calculated, and the pooled sample size was 46,645, with an overall accuracy of 92.16% (95% CI, 90.8%-93.5%). The risk of bias and applicability concerns were judged as high for most studies, mainly regarding data selection and reference standards. DL models showed high accuracy in identifying and classifying DISs using panoramic and periapical radiographic images. Therefore, DL models are promising prospects for use as decision aids and decision-making tools; however, there are limitations with respect to their application in actual clinical practice.

Federated vs Local vs Central Deep Learning of Tooth Segmentation on Panoramic Radiographs.

OBJECTIVE: Federated Learning (FL) enables collaborative training of artificial intelligence (AI) models from multiple data sources without directly sharing data. Due to the large amount of sensitive data in dentistry, FL may be particularly relevant for oral and dental research and applications. This study, for the first time, employed FL for a dental task, automated tooth segmentation on panoramic radiographs. METHODS: We employed a dataset of 4,177 panoramic radiographs collected from nine different centers (n = 143 to n = 1881 per center) across the globe and used FL to train a machine learning model for tooth segmentation. FL performance was compared against Local Learning (LL), i.e., training models on isolated data from each center (assuming data sharing not to be an option). Further, the performance gap to Central Learning (CL), i.e., training on centrally pooled data (based on data sharing agreements) was quantified. Generalizability of models was evaluated on a pooled test dataset from all centers. RESULTS: For 8 out of 9 centers, FL outperformed LL with statistical significance (p<0.05); only the center providing the largest amount of data FL did not have such an advantage. For generalizability, FL outperformed LL across all centers. CL surpassed both FL and LL for performance and generalizability. CONCLUSION: If data pooling (for CL) is not feasible, FL is shown to be a useful alternative to train performant and, more importantly, generalizable deep learning models in dentistry, where data protection barriers are high. CLINICAL SIGNIFICANCE: This study proves the validity and utility of FL in the field of dentistry, which encourages researchers to adopt this method to improve the generalizability of dental AI models and ease their transition to the clinical environment.

Surgical treatment of hereditary gingival fibromatosis by diode laser: Report of five rare cases in the same family.

The pathogenesis of hereditary gingival fibromatosis (HGF) is largely unknown; however, the removal of excess tissue may often be necessary as it often causes aesthetic and functional problems. Gingivectomy is usually a treatment option that can be performed using a scalpel, cryotherapy, electrosurgery, or laser. This paper aims to evaluate the results of HGF treatments using a diode laser of five people from the same family. Three members of a family of five (two females and three males; 9-36 years old) underwent gingivectomy with a 3 W 300-micron fiber-tipped diode laser (Doctor Smile, Vicenza, Italy) at 810 nm wavelength. While all teeth of one member were extracted, the other member refused treatment. Relapse occurred in three members due to poor oral hygiene. The diode laser was reapplied and oral hygiene instructions were repeated. Patients were followed during the postoperative period for up to two years. HGF is a rare condition that clinicians should pay attention to in the diagnosis, treatment, and follow-ups. Since recurrences are due to dental plaque, oral hygiene instructions are essential and compliance is mandatory. Although there are many treatment approaches, the diode laser is the most indicated method due to many advantages such as providing a bloodless and more sterile operation field, performing an atraumatic surgery, ensuring earlier and ideal recovery, and minimizing postoperative pain.

Roles of exosomes in regenerative periodontology: a narrative review.

Periodontitis is the primary cause of irreversible destruction of the periodontium surrounding teeth. Proinflammatory cytokines are secreted by pathogens in the biofilm and destroy the periodontium. Exosomes released into all biological fluids from saliva have enabled many innovations in the early diagnosis and treatment of periodontal diseases. This narrative review describes the role of exosomes in various diseases, and their involvement in periodontal diseases and periodontal regeneration primarily. Since guided tissue regeneration offers unpredictable results that vary according to the case, new developments in periodontal treatment are needed. Exosomes are suitable drug carriers for periodontal regeneration due to their isolation from every biological fluid, biocompatibility, low toxicity and high concentration of drugs reaching the target tissue. Exosomes obtained from mesenchymal stem cells can be used for periodontal regeneration in periodontal flaps, scaffolds, or periodontal defect areas through biomaterials such as drugs and hydrogels. Exosomes are significant in the early diagnosis and development of treatment of many diseases such as cardiovascular, neurodegenerative, diabetes and prognostic markers in cancer. Future studies are needed to elucidate the effects and possible mechanisms of exosomes in periodontitis and periodontal diseases and other systemic diseases, as they have many promises in diagnosis, treatment, and prognosis.

Relationship of NLRP3 inflammasome with periodontal, endodontic and related systemic diseases.

NLRP3 (NOD-, LRR- and pyrin domain-containing protein 3) is an inflammasome associated with oral and general health. There is a bidirectional relationship between the oral cavity and systemic health. The primary reason for this situation is the similarity in pathways for chronic inflammatory diseases both in the oral cavity and systemically. Periodontal and periapical diseases are some of the most common inflammatory conditions in adults and are associated with bacterial infection and host inflammation. The pathogenesis of periodontal and periapical lesions is complex and multifactorial, and the host inflammatory response determines the progression and pattern of the diseases. Inflammasomes, innate immune system receptors and sensors, are the key components in the pathogenesis of the inflammatory conditions. They are reported to be responsible for the initiation of the inflammatory reaction, maturation of proinflammatory cytokines and pyroptosis. The NLRP3 inflammasome is a multi-protein complex that contributes to immune responses during infection or injury. NLRP3 is implicated in several diseases such as diabetes, rheumatoid arthritis, cardiovascular diseases, inflammatory bowel diseases, multiple sclerosis, and Alzheimer's disease. There have been many recent advances in our knowledge concerning the essential role of NLRP3 inflammasome in periodontal and periapical inflammation. Therefore, the NLRP3 inflammasome may be a promising target for anti-inflammatory therapies. This paper will provide an overview of the role of NLRP3 inflammasome on periodontal and endodontic diseases with their links between systemic conditions, and presents a future perspective for the treatment of these inflammatory conditions.

Ultrasonographic evaluation of the titanium-prepared platelet-rich fibrin effect in free gingival graft procedures.

BACKGROUND: Complications after free gingival graft (FGG) operations are generally related to the donor site. The titanium-prepared, platelet-rich fibrin (T-PRF) placement in the donor site accelerate the wound healing and prevent postoperative complications such as pain and hemorrhage. We aim to evaluate the effect of T-PRF regarding vascularization and tissue thickness and to report the advantages of the ultrasonography (US) in FGG. METHODS: Ten individuals were divided into two groups as T-PRF and control. While the T-PRF membrane was placed at the donor site in the T-PRF group, a gelatin sponge was placed in the control group. All patients underwent US examination in terms of vascularization and tissue thickness of left and right donor sites. The correlation between the right and left donor sites was analyzed with the Pearson correlation test. Tissue thicknesses and pulsatility index (PI) were analyzed with independent samples t-test. The results were evaluated statistically at the P <0.05 significance level. RESULTS: The T-PRF group showed increased vascularity which can be interpreted to improve healing in soft tissue. However, not a difference, but a positively very high correlation was observed between the right and left tissue thicknesses (P = 0,00; r = +0902). CONCLUSIONS: Evaluation of tissue thickness and vascularization density of donor sites with US not only increases clinical success rate but also reduces the risk of complications during surgery and postoperative pain in FGG. Studies evaluating T-PRF membrane as palatal dressing after FGG are only clinical, however, the efficiency of T-PRF was evaluated radiologically in this study for the first time.

Role of NLRP3 inflammasome in COVID-19 and periodontitis: Possible protective effect of melatonin.

Daily new information emerges regarding the COVID-19, infection of SARS-CoV-2, which is considered a global pandemic. Angiotensin-converting enzyme 2 (ACE2) and transmembrane protease serine 2 (TMPRSS2) are required to complete the viral invasion pathway and are present in the oral mucosa, gingiva and periodontal pocket. Thus, increasing the likelihood of periodontitis and gingivitis caused by COVID-19. The cytokine storm during COVID-19 similarly arises during periodontal inflammation. Studies have reported that NOD-Like Receptor family pyrin domain-containing 3 (NLRP3) inflammasome is significant in the cytokine storm. Recently, the course of the COVID-19 has been related to the melatonin levels in both COVID-19 and periodontal diseases. It is known that melatonin prevents the activation of NLRP3 inflammasome. In light of these findings, we think that melatonin treatment during COVID-19 or periodontal diseases may prevent the damage seen in periodontal tissues by preventing the activation of NLRP3 inflammasome.