Artificial intelligence for radiographic imaging detection of caries lesions: a systematic review

BMC Oral Health, Journal Year: 2024, Volume and Issue: 24(1)

Published: Feb. 24, 2024

Abstract Background The aim of this systematic review is to evaluate the diagnostic performance Artificial Intelligence (AI) models designed for detection caries lesion (CL). Materials and methods An electronic literature search was conducted on PubMed, Web Science, SCOPUS, LILACS Embase databases retrospective, prospective cross-sectional studies published until January 2023, using following keywords: artificial intelligence (AI), machine learning (ML), deep (DL), neural networks (ANN), convolutional (CNN), (DCNN), radiology, detection, diagnosis dental (DC). quality assessment performed guidelines QUADAS-2. Results Twenty articles that met selection criteria were evaluated. Five periapical radiographs, nine bitewings, six orthopantomography. number imaging examinations included ranged from 15 2900. Four investigated ANN models, fifteen CNN two DCNN models. Twelve retrospective studies, prospective. achieved in detecting CL: sensitivity 0.44 0.86, specificity 0.85 0.98, precision 0.50 0.94, PPV (Positive Predictive Value) NPV (Negative 0.95, accuracy 0.73 area under curve (AUC) 0.84 intersection over union 0.3–0.4 0.78, Dice coefficient 0.66 0.88, F1-score 0.64 0.92. According QUADAS-2 evaluation, most exhibited a low risk bias. Conclusion AI-based have demonstrated good performance, potentially being an important aid CL detection. Some limitations these are related size heterogeneity datasets. Future need rely comparable, large, clinically meaningful Protocol PROSPERO identifier: CRD42023470708

Language: Английский

---

A novel artificial intelligence‐powered tool for automated root canal segmentation in single‐rooted teeth on cone‐beam computed tomography

International Endodontic Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 28, 2025

Abstract Aim To develop and validate an artificial intelligence (AI)‐powered tool based on convolutional neural network (CNN) for automatic segmentation of root canals in single‐rooted teeth using cone‐beam computed tomography (CBCT). Methodology A total 69 CBCT scans were retrospectively recruited from a hospital database acquired two devices with varying protocols. These randomly assigned to the training ( n = 31, 88 teeth), validation 8, 15 teeth) testing 30, 120 sets. For data sets, each scan was imported Virtual Patient Creator platform, where manual performed by operators, establishing ground truth. Subsequently, AI model tested 30 (120 AI‐generated three‐dimensional (3D) virtual models exported standard triangle language (STL) format. Importantly, set encompassed different types teeth. An experienced operator evaluated automated segmentation, refinements made create refined 3D (R‐AI). The R‐AI compared performance evaluation. Additionally, 30% sample manually segmented at times compare AI‐based human methods. time taken method obtain recorded seconds(s) further comparison. Results AI‐driven demonstrated highly accurate (Dice similarity coefficient [DSC] ranging 89% 93%; 95% Hausdorff distance [HD] 0.10 0.13 mm), no significant impact tooth type accuracy metrics p > .05). approach outperformed < .05), showing higher DSC lower HD values. In terms efficiency, required significantly more (2262.4 ± 679.1 s) (94 64.7 (41.8 12.2 methods representing 54‐fold decrease. Conclusions novel exhibited time‐efficient canal CBCT, surpassing performance.

Language: Английский

---

Current Progress and Challenges of Using Artificial Intelligence in Clinical Dentistry—A Narrative Review

Journal of Clinical Medicine, Journal Year: 2023, Volume and Issue: 12(23), P. 7378 - 7378

Published: Nov. 28, 2023

The concept of machines learning and acting like humans is what meant by the phrase “artificial intelligence” (AI). Several branches dentistry are increasingly relying on artificial intelligence (AI) tools. literature usually focuses AI models. These models have been used to detect diagnose a wide range conditions, including, but not limited to, dental caries, vertical root fractures, apical lesions, diseases salivary glands, maxillary sinusitis, maxillofacial cysts, cervical lymph node metastasis, osteoporosis, cancerous alveolar bone loss, need for orthodontic extractions or treatments, cephalometric analysis, age gender determination, more. primary contemporary applications in field undergraduate teaching research. Before these methods can be everyday dentistry, however, underlying technology user interfaces refined.

Language: Английский

---

Artificial Intelligence and Its Application in Endodontics: A Review

The Journal of Contemporary Dental Practice, Journal Year: 2024, Volume and Issue: 24(11), P. 912 - 917

Published: Jan. 11, 2024

Aim and background: Artificial intelligence (AI) since it was introduced into dentistry, has become an important valuable tool in many fields.It applied different specialties with uses, for example, diagnosis of oral cancer, periodontal disease dental caries, the treatment planning predicting outcome orthognathic surgeries.The aim this comprehensive review is to report on application performance AI models designed field endodontics.Materials methods: PubMed, Web Science, Google Scholar were searched collect most relevant articles using terms, such as AI, endodontics, dentistry.This included 56 papers related its endodontics.Result: The applications detecting diagnosing periapical lesions, assessing root fractures, working length determination, prediction postoperative pain, studying canal anatomy decision-making endodontics retreatment.The accuracy performing these tasks can reach up 90%.Conclusion: modern promising results.Larger multicenter data sets give external validity models.Clinical significance: In are specifically crafted contribute diseases, ranging from common issues caries more complex conditions like diseases cancer.AI help diagnosis, planning, patient management endodontics.Along tools cone-beam computed tomography (CBCT), be a aid clinician.

Language: Английский

---

The Use of Artificial Intelligence in Endodontics

Journal of Dental Research, Journal Year: 2024, Volume and Issue: 103(9), P. 853 - 862

Published: May 31, 2024

Endodontics is the dental specialty foremost concerned with diseases of pulp and periradicular tissues. Clinicians often face patients varying symptoms, must critically assess radiographic images in 2 3 dimensions, derive complex diagnoses decision making, deliver sophisticated treatment. Paired low intra- interobserver agreement for interpretation variations treatment outcome resulting from nonstandardized clinical techniques, there exists an unmet need support form artificial intelligence (AI), providing automated biomedical image analysis, support, assistance during In past decade, has been a steady increase AI studies endodontics but limited application. This review focuses on assessing recent advancements endodontic research applications, including detection diagnosis pathologies such as periapical lesions, fractures resorptions, well predictions. It discusses benefits AI-assisted diagnosis, planning execution, future directions augmented reality robotics. reviews limitations challenges imposed by nature data sets, transparency generalization, potential ethical dilemmas. near future, will significantly affect everyday workflow, education, continuous learning.

Language: Английский

---

Artificial intelligence-powered dentistry: Probing the potential, challenges, and ethicality of artificial intelligence in dentistry

Digital Health, Journal Year: 2024, Volume and Issue: 10

Published: Jan. 1, 2024

Introduction Healthcare amelioration is exponential to technological advancement. In the recent era of automation, consolidation artificial intelligence (AI) in dentistry has rendered transformation oral healthcare from a hardware-centric approach software-centric approach, leading enhanced efficiency and improved educational clinical outcomes. Objectives The aim this narrative overview extend succinct major events innovations that led creation modern-day AI applicability former dentistry. This article also prompts workers endeavor liable optimal for effective incorporation technology into their practice promote health by exploring potentials, constraints, ethical considerations Methods A comprehensive searching white grey literature was carried out collect assess data on AI, its use dentistry, associated challenges concerns. Results still evolving phase with paramount applicabilities relevant risk prediction, diagnosis, decision-making, prognosis, tailored treatment plans, patient management, academia as well concerns implementation. Conclusion upsurging advancements have resulted transformations promising outcomes across all domains futurity, may be capable executing multitude tasks domain healthcare, at level or surpassing ability mankind. However, could significant benefit only if it utilized under responsibility, ethicality universality.

Language: Английский

---

Artificial Intelligence in Endodontics: A Scoping Review.

PubMed, Journal Year: 2024, Volume and Issue: 19(2), P. 85 - 98

Published: Jan. 1, 2024

Artificial intelligence (AI) is transforming the diagnostic methods and treatment approaches in constantly evolving field of endodontics. The current review discusses recent advancements AI; with a specific focus on convolutional artificial neural networks. Apparently, AI models have proved to be highly beneficial analysis root canal anatomy, detecting periapical lesions early stages as well providing accurate working-length determination. Moreover, they seem effective predicting success next identifying various conditions e.g., dental caries, pulpal inflammation, vertical fractures, expression second opinions for non-surgical treatments. Furthermore, has demonstrated an exceptional ability recognize landmarks cone-beam computed tomography scans consistently high precision rates. While significantly promoted accuracy efficiency endodontic procedures, it importance continue validating reliability practicality possible widespread integration into daily clinical practice. Additionally, ethical considerations related patient privacy, data security, potential bias should carefully examined ensure responsible implementation

Language: Английский

---

Accuracy and Consistency of Gemini Responses Regarding the Management of Traumatized Permanent Teeth

Dental Traumatology, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 26, 2024

The aim of this cross-sectional observational analytical study was to assess the accuracy and consistency responses provided by Google Gemini (GG), a free-access high-performance multimodal large language model, questions related European Society Endodontology position statement on management traumatized permanent teeth (MTPT).

Language: Английский

---

Deep Learning in Diagnosis of Dental Anomalies and Diseases: A Systematic Review

Diagnostics, Journal Year: 2023, Volume and Issue: 13(15), P. 2512 - 2512

Published: July 27, 2023

Deep learning and diagnostic applications in oral dental health have received significant attention recently. In this review, studies applying deep to diagnose anomalies diseases image material were systematically compiled, their datasets, methodologies, test processes, explainable artificial intelligence methods, findings analyzed. Tests results involving human-artificial comparisons are discussed detail draw the clinical importance of learning. addition, review critically evaluates literature guide further develop future field. An extensive search was conducted for 2019–May 2023 range using Medline (PubMed) Google Scholar databases identify eligible articles, 101 shortlisted, including diagnosing (n = 22) 79) classification, object detection, segmentation tasks. According results, most commonly used task type classification 51), panoramic radiographs 55), frequently performance metric sensitivity/recall/true positive rate 87) accuracy 69). Dataset sizes ranged from 60 12,179 images. Although algorithms as individual or at least individualized architectures, standardized architectures such pre-trained CNNs, Faster R-CNN, YOLO, U-Net been studies. Few AI method applied tests comparing human 21). is promising better diagnosis treatment planning dentistry based on high-performance reported by For all that, safety should be demonstrated a more reproducible comparable methodology, with information about applicability, defining standard set metrics.

Language: Английский

---

Endodontic Treatment Outcomes in Cone Beam Computed Tomography Images—Assessment of the Diagnostic Accuracy of AI

Journal of Clinical Medicine, Journal Year: 2024, Volume and Issue: 13(14), P. 4116 - 4116

Published: July 14, 2024

Background/Objectives: The aim of this study was to assess the diagnostic accuracy AI-driven platform Diagnocat for evaluating endodontic treatment outcomes using cone beam computed tomography (CBCT) images. Methods: A total 55 consecutive patients (15 males and 40 females, aged 12–70 years) referred CBCT imaging were included. images analyzed Diagnocat’s AI platform, which assessed parameters such as probability filling, adequate obturation, density, overfilling, voids in short root canal number. also evaluated by two experienced human readers. Diagnostic metrics (accuracy, precision, recall, F1 score) compared readers’ consensus, served reference standard. Results: demonstrated high most parameters, with perfect scores filling = 100%). Adequate obturation showed moderate performance (accuracy 84.1%, precision 66.7%, recall 92.3%, 77.4%). density 95.5%, 97.2%), overfilling 86.7%, 100%, 92.9%), fillings 92.9%) exhibited strong performance. detection 88.6%, 88.9%, 76.2%) highlighted areas improvement. Conclusions: images, indicating its potential a valuable tool dental radiology.

Language: Английский

---