Hasil untuk "Dentistry"

S. Sidhu, J. Nicholson

This article is an updated review of the published literature on glass-ionomer cements and covers their structure, properties and clinical uses within dentistry, with an emphasis on findings from the last five years or so. Glass-ionomers are shown to set by an acid-base reaction within 2–3 min and to form hard, reasonably strong materials with acceptable appearance. They release fluoride and are bioactive, so that they gradually develop a strong, durable interfacial ion-exchange layer at the interface with the tooth, which is responsible for their adhesion. Modified forms of glass-ionomers, namely resin-modified glass-ionomers and glass carbomer, are also described and their properties and applications covered. Physical properties of the resin-modified glass-ionomers are shown to be good, and comparable with those of conventional glass-ionomers, but biocompatibility is somewhat compromised by the presence of the resin component, 2 hydroxyethyl methacrylate. Properties of glass carbomer appear to be slightly inferior to those of the best modern conventional glass-ionomers, and there is not yet sufficient information to determine how their bioactivity compares, although they have been formulated to enhance this particular feature.

R. Bapat, T. Chaubal, Chaitanya Joshi et al.

Oral cavity is a gateway to the entire body and protection of this gateway is a major goal in dentistry. Plaque biofilm is a major cause of majority of dental diseases and although various biomaterials have been applied for their cure, limitations pertaining to the material properties prevent achievement of desired outcomes. Nanoparticle applications have become useful tools for various dental applications in endodontics, periodontics, restorative dentistry, orthodontics and oral cancers. Off these, silver nanoparticles (AgNPs) have been used in medicine and dentistry due to its antimicrobial properties. AgNPs have been incorporated into biomaterials in order to prevent or reduce biofilm formation. Due to greater surface to volume ratio and small particle size, they possess excellent antimicrobial action without affecting the mechanical properties of the material. This unique property of AgNPs makes these materials as fillers of choice in different biomaterials whereby they play a vital role in improving the properties. This review aims to discuss the influence of addition of AgNPs to various biomaterials used in different dental applications.

Zhaolin Yu, Litao Yang, Ben Babicka et al.

Orthopantomograms (OPGs) are the standard panoramic radiograph in dentistry, used for full-arch screening across multiple diagnostic tasks. While Vision Language Models (VLMs) now allow multi-task OPG analysis through natural language, they underperform task-specific models on most individual tasks. Agentic systems that orchestrate specialized tools offer a path to both versatility and accuracy, this approach remains unexplored in the field of dental imaging. To address this gap, we propose OPGAgent, a multi-tool agentic system for auditable OPG interpretation. OPGAgent coordinates specialized perception modules with a consensus mechanism through three components: (1) a Hierarchical Evidence Gathering module that decomposes OPG analysis into global, quadrant, and tooth-level phases with dynamically invoking tools, (2) a Specialized Toolbox encapsulating spatial, detection, utility, and expert zoos, and (3) a Consensus Subagent that resolves conflicts through anatomical constraints. We further propose OPG-Bench, a structured-report protocol based on (Location, Field, Value) triples derived from real clinical reports, which enables a comprehensive review of findings and hallucinations, extending beyond the limitations of VQA indicators. On our OPG-Bench and the public MMOral-OPG benchmark, OPGAgent outperforms current dental VLMs and medical agent frameworks across both structured-report and VQA evaluation. Code will be released upon acceptance.

Hongyang Ma, Tiantian Gu, Huaiyuan Sun et al.

The transition of Large Language Models (LLMs) from passive knowledge retrievers to autonomous clinical agents demands a shift in evaluation-from static accuracy to dynamic behavioral reliability. To explore this boundary in dentistry, a domain where high-quality AI advice uniquely empowers patient-participatory decision-making, we present the Standardized Clinical Management & Performance Evaluation (SCMPE) benchmark, which comprehensively assesses performance from knowledge-oriented evaluations (static objective tasks) to workflow-based simulations (multi-turn simulated patient interactions). Our analysis reveals that while models demonstrate high proficiency in static objective tasks, their performance precipitates in dynamic clinical dialogues, identifying that the primary bottleneck lies not in knowledge retention, but in the critical challenges of active information gathering and dynamic state tracking. Mapping "Guideline Adherence" versus "Decision Quality" reveals a prevalent "High Efficacy, Low Safety" risk in general models. Furthermore, we quantify the impact of Retrieval-Augmented Generation (RAG). While RAG mitigates hallucinations in static tasks, its efficacy in dynamic workflows is limited and heterogeneous, sometimes causing degradation. This underscores that external knowledge alone cannot bridge the reasoning gap without domain-adaptive pre-training. This study empirically charts the capability boundaries of dental LLMs, providing a roadmap for bridging the gap between standardized knowledge and safe, autonomous clinical practice.

Kun Tang, Xinquan Yang, Mianjie Zheng et al.

The scarcity and high cost of expert annotations in dental imaging present a significant challenge for the development of AI in dentistry. DINOv3, a state-of-the-art, self-supervised vision foundation model pre-trained on 1.7 billion images, offers a promising pathway to mitigate this issue. However, its reliability when transferred to the dental domain, with its unique imaging characteristics and clinical subtleties, remains unclear. To address this, we introduce DinoDental, a unified benchmark designed to systematically evaluate whether DINOv3 can serve as a reliable, off-the-shelf encoder for comprehensive dental image analysis without requiring domain-specific pre-training. Constructed from multiple public datasets, DinoDental covers a wide range of tasks, including classification, detection, and instance segmentation on both panoramic radiographs and intraoral photographs. We further analyze the model's transfer performance by scaling its size and input resolution, and by comparing different adaptation strategies, including frozen features, full fine-tuning, and the parameter-efficient Low-Rank Adaptation (LoRA) method. Our experiments show that DINOv3 can serve as a strong unified encoder for dental image analysis across both panoramic radiographs and intraoral photographs, remaining competitive across tasks while showing particularly clear advantages for intraoral image understanding and boundary-sensitive dense prediction. Collectively, DinoDental provides a systematic framework for comprehensively evaluating DINOv3 in dental analysis, establishing a foundational benchmark to guide efficient and effective model selection and adaptation for the dental AI community.

Huimin Xiong, Zijie Meng, Tianxiang Hu et al.

3D intraoral scans (IOS) are increasingly adopted in routine dentistry due to abundant geometric evidence, and unified multi-disease diagnosis is desirable for clinical documentation and communication. While recent works introduce dental vision-language models (VLMs) to enable unified diagnosis and report generation on 2D images or multi-view images rendered from IOS, they do not fully leverage native 3D geometry. Such work is necessary and also challenging, due to: (i) heterogeneous scan forms and the complex IOS topology, (ii) multi-disease co-occurrence with class imbalance and fine-grained morphological ambiguity, (iii) limited paired 3D IOS-text data. Thus, we present IOSVLM, an end-to-end 3D VLM that represents scans as point clouds and follows a 3D encoder-projector-LLM design for unified diagnosis and generative visual question-answering (VQA), together with IOSVQA, a large-scale multi-source IOS diagnosis VQA dataset comprising 19,002 cases and 249,055 VQA pairs over 23 oral diseases and heterogeneous scan types. To address the distribution gap between color-free IOS data and color-dependent 3D pre-training, we propose a geometry-to-chromatic proxy that stabilizes fine-grained geometric perception and cross-modal alignment. A two-stage curriculum training strategy further enhances robustness. IOSVLM consistently outperforms strong baselines, achieving gains of at least +9.58% macro accuracy and +1.46% macro F1, indicating the effectiveness of direct 3D geometry modeling for IOS-based diagnosis.

Anastasiia Sukhanova, Aiden Taylor, Julian Myers et al.

Digital dentistry has made significant advances with the advent of deep learning. However, the majority of these deep learning-based dental image analysis models focus on very specific tasks such as tooth segmentation, tooth detection, cavity detection, and gingivitis classification. There is a lack of a specialized model that has holistic knowledge of teeth and can perform dental image analysis tasks based on that knowledge. Datasets of dental images with captions can help build such a model. To the best of our knowledge, existing dental image datasets with captions are few in number and limited in scope. In many of these datasets, the captions describe the entire mouth, while the images are limited to the anterior view. As a result, posterior teeth such as molars are not clearly visible, limiting the usefulness of the captions for training vision-language models. Additionally, the captions focus only on a specific disease (gingivitis) and do not provide a holistic assessment of each tooth. Moreover, tooth disease scores are typically assigned to individual teeth, and each tooth is treated as a separate entity in orthodontic procedures. Therefore, it is important to have captions for single-tooth images. As far as we know, no such dataset of single-tooth images with dental captions exists. In this work, we aim to bridge that gap by assessing the possibility of generating captions for dental images using Vision-Language Models (VLMs) and evaluating the extent and quality of those captions. Our findings suggest that guided prompts help VLMs generate meaningful captions. We show that the prompts generated by our framework are better anchored in describing the visual aspects of dental images. We selected RGB images as they have greater potential in consumer scenarios.

Daria Poul, Amanda Rodriguez Betancourt, Ankita Samal et al.

This study presents the first quantifications of ultrasound attenuation in oral soft tissues using validated standard techniques and serves as foundational step in advancing quantitative ultrasound (QUS) imaging in dentistry. Current standards of care in clinics for diagnosing periodontal diseases such as inflammation are limited by subjectivity, qualitive assessment, and late-stage indication. As a result, the application of ultrasonography is emerging as a surrogate for non-invasive and quantitative assessments and a relatively new research area with significant potential biomarkers to be explored. Many QUS analyses rely on quantifying ultrasound attenuation coefficient (UAC), as a confounding factor. Here, in a swine cohort (N=10), we characterized the high-frequency (24 MHz) UAC of healthy periodontal tissues (gingiva) in vivo. UAC were estimated using spectral difference method. Five interproximal oral sites were imaged from four oral quadrants: Premolar 3-Mesial, Premolar3-Distal, Premolar4-Distal, Molar1-Distal, and Molar2-Distal. A total of 162 oral sites were analyzed. The respective medians (1st-quartile|3rd-quartile) UACs for these oral sites were 1.66 (1.25|1.99), 1.37 (1.06|1.64), 0.99 (0.8|1.25), 1.08 (0.89|1.47), and 1.28 (0.94|1.24) dB/MHz.cm. The gingival attenuation mean at Premolar3-Mesial was significantly higher than any other oral sites while the rest of them showed non-significance difference in their means. Across all non-significant oral sites, the average UAC was 1.17 dB/MHz.cm with a standard deviation of 0.49 dB/MHz.cm. This work not only characterized an important acoustic property of oral tissues for the first time but also contributes to future development of a number of QUS biomarkers for periodontal/dental healthcare that rely on accurate attenuation knowledge.

M. Tahriri, M. Monico, A. Moghanian et al.

The emerging science of graphene-based engineered nanomaterials as either nanomedicines or dental materials in dentistry is growing. Apart from its exceptional mechanical characteristics, electrical conductivity and thermal stability, graphene and its derivatives can be functionalized with several bioactive molecules, allowing them to be incorporated into and improve different scaffolds used in regenerative dentistry. This review presents state of the art graphene-based engineered nanomaterial applications to cells in the dental field, with a particular focus on the control of stem cells of dental origin. The interactions between graphene-based nanomaterials and cells of the immune system, along with the antibacterial activity of graphene nanomaterials are discussed. In the last section, we offer our perspectives on the various applications of graphene and its derivatives in association with titanium dental implants, membranes for bone regeneration, resins, cements and adhesives, as well as tooth-whitening procedures.

K. Jandt, D. Watts

Graphical abstract

M. Blatz, G. Chiche, O. Bahat et al.

One of the main goals of dental treatment is to mimic teeth and design smiles in a most natural and aesthetic manner, based on the individual and specific needs of the patient. Possibilities to reach that goal have significantly improved over the last decade through new and specific treatment modalities, steadily enhanced and more aesthetic dental materials, and novel techniques and technologies. This article gives an overview of the evolution of aesthetic dentistry over the past 100 y from a historical point of view and highlights advances in the development of dental research and clinical interventions that have contributed the science and art of aesthetic dentistry. Among the most noteworthy advancements over the past decade are the establishment of universal aesthetic rules and guidelines based on the assessment of natural aesthetic parameters, anatomy, and physiognomy; the development of tooth whitening and advanced restorative as well as prosthetic materials and techniques, supported by the pioneering discovery of dental adhesion; the significant progress in orthodontics and periodontal as well as oral and maxillofacial surgery; and, most recently, the implementation of digital technologies in the 3-dimensional planning and realization of truly natural, individual, and aesthetic smiles. In the future, artificial intelligence and machine learning will likely lead to automation of aesthetic evaluation, smile design, and treatment-planning processes.

L. Bathala, V. Majeti, N. Rachuri et al.

This study is aimed to review the applications of Polyether Ether Ketone (PEEK) in dentistry. The increased demand for aesthetics, legislation in some developed countries, few drawbacks with existing materials and clinicians shifting their paradigms towards metal free restorations led space for the metal-free restorations in today’s dental practice. An electronic literature search was conducted through Medline via PubMed, Wiley Online library, EBSCOhost, Science Direct, as well as the Google Scholar between January 2010 and March 2018 using the keywords: PEEK, modified PEEK, PEEK and Dental, advantages of PEEK, applications of PEEK in dentistry and PEEK Implants. A total of 103 articles were found in the literature search and out of these, 18 were not related to our study and hence were excluded. Finally, 85 articles were found to be relevant. PEEK has been explained for a number of applications in dental practice. The literature showed that the PEEK material has superior mechanical properties with different uses in various specialties of dentistry.

Anbang Wang, Marawan Elbatel, Keyuan Liu et al.

Accurate detection of anatomic landmarks is essential for assessing alveolar bone and root conditions, thereby optimizing clinical outcomes in orthodontics, periodontics, and implant dentistry. Manual annotation of landmarks on cone-beam computed tomography (CBCT) by dentists is time-consuming, labor-intensive, and subject to inter-observer variability. Deep learning-based automated methods present a promising approach to streamline this process efficiently. However, the scarcity of training data and the high cost of expert annotations hinder the adoption of conventional deep learning techniques. To overcome these challenges, we introduce GeoSapiens, a novel few-shot learning framework designed for robust dental landmark detection using limited annotated CBCT of anterior teeth. Our GeoSapiens framework comprises two key components: (1) a robust baseline adapted from Sapiens, a foundational model that has achieved state-of-the-art performance in human-centric vision tasks, and (2) a novel geometric loss function that improves the model's capacity to capture critical geometric relationships among anatomical structures. Experiments conducted on our collected dataset of anterior teeth landmarks revealed that GeoSapiens surpassed existing landmark detection methods, outperforming the leading approach by an 8.18% higher success detection rate at a strict 0.5 mm threshold-a standard widely recognized in dental diagnostics. Code is available at: https://github.com/xmed-lab/GeoSapiens.

Hexian Zhang, Xinyu Yan, Yanqi Yang et al.

Large language models (LLMs) hold transformative potential in healthcare, yet their capacity to interpret longitudinal patient narratives remains inadequately explored. Dentistry, with its rich repository of structured clinical data, presents a unique opportunity to rigorously assess LLMs' reasoning abilities. While several commercial LLMs already exist, DeepSeek, a model that gained significant attention earlier this year, has also joined the competition. This study evaluated four state-of-the-art LLMs (GPT-4o, Gemini 2.0 Flash, Copilot, and DeepSeek V3) on their ability to analyze longitudinal dental case vignettes through open-ended clinical tasks. Using 34 standardized longitudinal periodontal cases (comprising 258 question-answer pairs), we assessed model performance via automated metrics and blinded evaluations by licensed dentists. DeepSeek emerged as the top performer, demonstrating superior faithfulness (median score = 0.528 vs. 0.367-0.457) and higher expert ratings (median = 4.5/5 vs. 4.0/5), without significantly compromising readability. Our study positions DeepSeek as the leading LLM for case analysis, endorses its integration as an adjunct tool in both medical education and research, and highlights its potential as a domain-specific agent.

Zhi Qin Tan, Xiatian Zhu, Owen Addison et al.

Cone-Beam Computed Tomography (CBCT) is a widely used 3D imaging technique in dentistry, providing volumetric information about the anatomical structures of jaws and teeth. Accurate segmentation of these anatomies is critical for clinical applications such as diagnosis and surgical planning, but remains time-consuming and challenging. In this paper, we present U-Mamba2, a new neural network architecture designed for multi-anatomy CBCT segmentation in the context of the ToothFairy3 challenge. U-Mamba2 integrates the Mamba2 state space models into the U-Net architecture, enforcing stronger structural constraints for higher efficiency without compromising performance. In addition, we integrate interactive click prompts with cross-attention blocks, pre-train U-Mamba2 using self-supervised learning, and incorporate dental domain knowledge into the model design to address key challenges of dental anatomy segmentation in CBCT. Extensive experiments, including independent tests, demonstrate that U-Mamba2 is both effective and efficient, securing first place in both tasks of the Toothfairy3 challenge. In Task 1, U-Mamba2 achieved a mean Dice of 0.84, HD95 of 38.17 with the held-out test data, with an average inference time of 40.58s. In Task 2, U-Mamba2 achieved the mean Dice of 0.87 and HD95 of 2.15 with the held-out test data. The code is publicly available at https://github.com/zhiqin1998/UMamba2.

Yaqi Wang, Zhi Li, Chengyu Wu et al.

Cone-Beam Computed Tomography (CBCT) and Intraoral Scanning (IOS) are essential for digital dentistry, but annotated data scarcity limits automated solutions for pulp canal segmentation and cross-modal registration. To benchmark semi-supervised learning (SSL) in this domain, we organized the STSR 2025 Challenge at MICCAI 2025, featuring two tasks: (1) semi-supervised segmentation of teeth and pulp canals in CBCT, and (2) semi-supervised rigid registration of CBCT and IOS. We provided 60 labeled and 640 unlabeled IOS samples, plus 30 labeled and 250 unlabeled CBCT scans with varying resolutions and fields of view. The challenge attracted strong community participation, with top teams submitting open-source deep learning-based SSL solutions. For segmentation, leading methods used nnU-Net and Mamba-like State Space Models with pseudo-labeling and consistency regularization, achieving a Dice score of 0.967 and Instance Affinity of 0.738 on the hidden test set. For registration, effective approaches combined PointNetLK with differentiable SVD and geometric augmentation to handle modality gaps; hybrid neural-classical refinement enabled accurate alignment despite limited labels. All data and code are publicly available at https://github.com/ricoleehduu/STS-Challenge-2025 to ensure reproducibility.

Sidhu Leah M., Jensen Sven W.C., Jensen Emilija D.

The increase in popularity and demand for clear aligner therapy (CAT) has resulted in the recent use of this modality to treat more complex orthodontic cases.

Kamil Pajor, L. Pajchel, J. Kolmas

Calcium phosphate, due to its similarity to the inorganic fraction of mineralized tissues, has played a key role in many areas of medicine, in particular, regenerative medicine and orthopedics. It has also found application in conservative dentistry and dental surgery, in particular, as components of toothpaste and mouth rinse, coatings of dental implants, cements, and bone substitute materials for the restoration of cavities in maxillofacial surgery. In dental applications, the most important role is played by hydroxyapatite and fluorapatite, i.e., calcium phosphates characterized by the highest chemical stability and very low solubility. This paper presents the role of both apatites in dentistry and a review of recent achievements in the field of the application of these materials.

Jian Xu, L. Gou, Peng Zhang et al.

Abstract Regenerative dentistry is an emerging field of medicine involving stem cell technology, tissue engineering and dental science. It exploits biological mechanisms to regenerate damaged oral tissues and restore their functions. Platelet‐rich plasma (PRP) is a biological product that is defined as the portion of plasma fraction of autologous blood with a platelet concentration above that of the original whole blood. A super‐mixture of key cytokines and growth factors is present in platelet granules. Thus, the application of PRP has gained unprecedented attention in regenerative medicine. The rationale underlies the utilization of PRP is that it acts as a biomaterial to deliver critical growth factors and cytokines from platelet granules to the targeted area, thus promoting regeneration in a variety of tissues. Based on enhanced understanding of cell signalling and growth factor biology, researchers have begun to use PRP treatment as a novel method to regenerate damaged tissues, including liver, bone, cartilage, tendon and dental pulp. To enable better understanding of the regenerative effects of PRP in dentistry, this review describes different methods of preparation and application of this biological product, and provides detailed explanations of the controversies and future prospects related to the use of PRP in dental regenerative medicine.

Muhammad Sohail Zafar, Faiza Amin, M. A. Fareed et al.

Biomimetic has emerged as a multi-disciplinary science in several biomedical subjects in recent decades, including biomaterials and dentistry. In restorative dentistry, biomimetic approaches have been applied for a range of applications, such as restoring tooth defects using bioinspired peptides to achieve remineralization, bioactive and biomimetic biomaterials, and tissue engineering for regeneration. Advancements in the modern adhesive restorative materials, understanding of biomaterial–tissue interaction at the nano and microscale further enhanced the restorative materials’ properties (such as color, morphology, and strength) to mimic natural teeth. In addition, the tissue-engineering approaches resulted in regeneration of lost or damaged dental tissues mimicking their natural counterpart. The aim of the present article is to review various biomimetic approaches used to replace lost or damaged dental tissues using restorative biomaterials and tissue-engineering techniques. In addition, tooth structure, and various biomimetic properties of dental restorative materials and tissue-engineering scaffold materials, are discussed.