METHODS: 35 maxillary incisors were endodontically prepared. A dimensionally stable silicone material was injected into the root canal space and scanned with CBCT. The root canal volume was measured using Romexis 3.0.1 R software. Replicas were carefully removed from the teeth and scanned using an extraoral laser scanner. These images were exported to the Rhinoceros software for volume measurement. The volume of each replica was also assessed using the gravimetric method. To determine the accuracy, the volume obtained from both devices was compared with the gravimetric method. Statistical analysis was done using a paired t-test. The reliability was assessed using the intraclass correlation coefficient.

RESULTS: There was no statistically significant difference between the mean volume of CBCT 27.04 ± 7.25 mm³ and the mean volume of the gravimetric method 27.87 ± 7.17 mm³ (P< 0.05). A statistically significant difference was seen with the laser scanner at 25.31 ± 6.89 mm³ and the gravimetric method at 27.87 ± 7.17 mm³ (P< 0.05). CBCT showed a good degree of agreement (ICC 0.899), while the laser scanner showed a moderate degree of agreement (ICC 0.644) with the gravimetric method. CBCT proved accurate and reliable in measuring minor volumes like the root canal space, ideally in the range of 20-25 mm³. The laser scanner presented acceptable reliability.

INTRODUCTION: Artificial intelligence (AI) is a relatively new technology that has widespread use in dentistry. The AI technologies have primarily been used in dentistry to diagnose dental diseases, plan treatment, make clinical decisions, and predict the prognosis. AI models like convolutional neural networks (CNN) and artificial neural networks (ANN) have been used in endodontics to study root canal system anatomy, determine working length measurements, detect periapical lesions and root fractures, predict the success of retreatment procedures, and predict the viability of dental pulp stem cells. Methodology. The literature was searched in electronic databases such as Google Scholar, Medline, PubMed, Embase, Web of Science, and Scopus, published over the last four decades (January 1980 to September 15, 2021) by using keywords such as artificial intelligence, machine learning, deep learning, application, endodontics, and dentistry.

RESULTS: The preliminary search yielded 2560 articles relevant enough to the paper's purpose. A total of 88 articles met the eligibility criteria. The majority of research on AI application in endodontics has concentrated on tracing apical foramen, verifying the working length, projection of periapical pathologies, root morphologies, and retreatment predictions and discovering the vertical root fractures.

METHODS: This narrative review was undertaken to address two main questions - why remove vital pulp tissue in teeth with complex canal anatomy when it can be preserved? And why replace the necrotic pulp in teeth with mature roots with a synthetic material when we can revitalize? This review also aims to discuss anatomical challenges with pulpotomy and revitalization procedures.

RESULTS: Maintaining the vitality of the pulp via partial or full pulpotomy procedures avoids the multiple potential challenges faced by clinicians during root canal treatment. However, carrying out pulpotomy procedures requires a meticulous understanding of the pulp chamber anatomy, which varies from tooth to tooth. Literature shows an increased interest in the application of RPs in teeth with mature roots; however, to date, the relation between the complexity of the root canal system and outcomes of RPs in necrotic multi-rooted teeth with mature roots is unclear and requires further robust comparative research and long-term follow-up.

METHODS: This study enrolled patients (N = 36) who required root canal retreatment (RCR) on mandibular molar teeth, presented with periapical lesions with periapical index scores of 2 or 3, and had a pain visual analog scale (VAS) <50 and a percussion pain VAS <50. The participants were divided into 2 groups: (1) patients scheduled for RCR followed by LLLT (n = 18) and (2) patients scheduled for RCR followed by a mock LLLT (placebo) (n = 18). Postoperative pain was assessed using the VAS. Data were collected and statistically analyzed with the chi-square test, the independent sample t test, and the Mann-Whitney U test (P = .05).

METHODS: The review protocol was registered in the PROSPERO database (CRD42017071899). A literature search was performed in the MEDLINE and EBSCOhost databases until June 2017 with no language restriction. Randomized controlled trials evaluating the efficacy of oral premedications, whether given alone or in combination, compared with other agents, placebo, or no treatment in adult patients before NSRCT for postoperative pain were included. Nonintervention studies, nonendodontic studies, animal studies, and reviews were excluded. The quality of the studies was assessed using the revised Cochrane risk of bias tool. Pair-wise meta-analysis, network meta-analysis, and quality of evidence assessment using the Grading of Recommendations Assessment, Development and Evaluation criteria was performed.

RESULTS: Eleven studies comparing pharmacologic groups of medications were included in the primary analysis. Compared with placebo, corticosteroids (prednisolone 30-40 mg) was ranked best for reducing postoperative pain (median difference [MD] = -18.14 [95% confidence interval (CI), -32.90 to -3.37] for the pain score at 6 hours; MD = -22.17 [95% CI, -36.03 to -8.32] for the pain score at 12 hours; and MD = -21.50 [95% CI, -37.95 to -5.06] for the pain score at 24 hours). However, the evidence was very low (6 and 24 hours) to moderate quality (12 hours). Nonsteroidal anti-inflammatory drugs were ranked least among the medications, and the quality of this evidence was very low. Additional analysis based on the chemical name showed that sulindac, ketorolac, and ibuprofen significantly reduced pain at 6 hours, whereas piroxicam and prednisolone significantly reduced the pain at 12 and 24 hours. Etodolac was found to be least effective in reducing pain. Overall, the evidence was of moderate to very low quality.