DESIGN: Single-centre prospective two-arm parallel randomised controlled trial.
SETTING: Orthodontic Clinic, Faculty of Dentistry, Universiti Teknologi MARA, Selangor, Malaysia.
PARTICIPANTS: Adult orthodontic patients aged 18-35 years, indicated for DPT and LC, who were fit and healthy with a body mass index of 18.5-25.0, not contraindicated to radiographic examination, not pregnant, and did not have a history of facial or skeletal abnormalities or bone diseases were included.
METHODS: Thirty-eight adult orthodontic patients were randomised into control and intervention groups. DPT and LC radiographs in the control group were obtained using standard scanning parameters as prescribed by the manufacturer using Orthopantomograph® OP300 by Instrumentarium. Scanning parameters in the intervention group were reduced by 60% for DPT (60 kV, 3.2 mA) and 30% for LC (85 kV, 8 mA). A five-point rating scale was used for the assessment of image quality. Images were evaluated for diagnostic performance by detection of anatomical landmarks. Mann-Whitney test was performed to compare the quality and diagnostic performance of the images and the observer agreement was assessed using the intraclass correlation coefficient (ICC).
RESULTS: For image quality, the control group produced slightly lower median scores (DPT 2.0, LC 2.0) compared to the intervention group (DPT 2.0, LC 3.0). For diagnostic performance, both groups showed similar median scores (DPT 21.0, LC 32.0). The differences between control and intervention groups for both modalities were not statistically significant. The average scores for intra-observer agreement were excellent (ICC 0.917) and inter-observer agreement was good (ICC 0.822).
CONCLUSION: Minimising radiation exposure by reducing scanning parameters on digital DPT by 60% and LC by 30% on Intsrumentarium 300 OP did not affect the quality and diagnostic performance of the images. Thus, scanning parameters on digital DPT and LC should be reduced when taking radiographs.
Materials and Methods: Using the MeSH keywords: artificial intelligence (AI), dentistry, AI in dentistry, neural networks and dentistry, machine learning, AI dental imaging, and AI treatment recommendations and dentistry. Two investigators performed an electronic search in 5 databases: PubMed/MEDLINE (National Library of Medicine), Scopus (Elsevier), ScienceDirect databases (Elsevier), Web of Science (Clarivate Analytics), and the Cochrane Collaboration (Wiley). The English language articles reporting on AI in different dental specialties were screened for eligibility. Thirty-two full-text articles were selected and systematically analyzed according to a predefined inclusion criterion. These articles were analyzed as per a specific research question, and the relevant data based on article general characteristics, study and control groups, assessment methods, outcomes, and quality assessment were extracted.
Results: The initial search identified 175 articles related to AI in dentistry based on the title and abstracts. The full text of 38 articles was assessed for eligibility to exclude studies not fulfilling the inclusion criteria. Six articles not related to AI in dentistry were excluded. Thirty-two articles were included in the systematic review. It was revealed that AI provides accurate patient management, dental diagnosis, prediction, and decision making. Artificial intelligence appeared as a reliable modality to enhance future implications in the various fields of dentistry, i.e., diagnostic dentistry, patient management, head and neck cancer, restorative dentistry, prosthetic dental sciences, orthodontics, radiology, and periodontics.
Conclusion: The included studies describe that AI is a reliable tool to make dental care smooth, better, time-saving, and economical for practitioners. AI benefits them in fulfilling patient demand and expectations. The dentists can use AI to ensure quality treatment, better oral health care outcome, and achieve precision. AI can help to predict failures in clinical scenarios and depict reliable solutions. However, AI is increasing the scope of state-of-the-art models in dentistry but is still under development. Further studies are required to assess the clinical performance of AI techniques in dentistry.
Materials and Methods: Forty carious primary molars indicated for pulpotomy within the age group of 4-9 years were selected and divided into two groups of 20 each using simple randomization, Group 1: Diode laser MTA and Group 2: Diode laser ZOE pulpotomy. The teeth were evaluated clinically for 1 year at 3, 6, and 12 months interval and radiologically for 6 and 12 months.
Results: Clinically and radiographically, 100% teeth treated with diode laser MTA and 94% treated with diode laser ZOE were considered successful after 12-month follow-up interval. No significant difference was seen between two groups.
Conclusion: Despite the success rate, the cost factor of diode laser and MTA could be the limiting factor in its judicious use in pulpotomy procedure.
METHODS: A sample of 111 plaster study models of Down syndrome (DS) patients were digitized using a blue light three-dimensional (3D) scanner. Digital and manual measurements of defined parameters were performed using Geomagic analysis software (Geomagic Studio 2014 software, 3D Systems, Rock Hill, SC, USA) on digital models and with a digital calliper (Tuten, Germany) on plaster study models. Both measurements were repeated twice to validate the intraexaminer reliability based on intraclass correlation coefficients (ICCs) using the independent t test and Pearson's correlation, respectively. The Bland-Altman method of analysis was used to evaluate the agreement of the measurement between the digital and plaster models.
RESULTS: No statistically significant differences (p > 0.05) were found between the manual and digital methods when measuring the arch width, arch length, and space analysis. In addition, all parameters showed a significant correlation coefficient (r ≥ 0.972; p
METHODOLOGY: Jaw sections containing 67 teeth (86 roots) were collected from nine fresh, unclaimed bodies that were due for cremation. Imaging was carried out to detect AP lesions using film and digital PR with a centred view (FP and DP groups); film and digital PR combining central with 10˚ mesially and distally angled (parallax) views (FPS and DPS groups). All specimens underwent histopathological examination to confirm the diagnosis of AP. Sensitivity, specificity and predictive values of PR were analysed using rater mean (n = 5). Receiver operating characteristics (ROC) analysis was carried out.
RESULTS: Sensitivity was 0.16, 0.37, 0.27 and 0.38 for FP, FPS, DP and DPS, respectively. Both FP and FPS had specificity and positive predictive values of 1.0, whilst DP and DPS had specificity and positive predictive values of 0.99. Negative predictive value was 0.36, 0.43, 0.39 and 0.44 for FP, FPS, DP and DPS, respectively. Area under the curve (AUC) for the various imaging methods was 0.562 (FP), 0.629 (DP), 0.685 (FPS), 0.6880 (DPS).
CONCLUSIONS: The diagnostic accuracy of single digital periapical radiography was significantly better than single film periapical radiography. The inclusion of two additional horizontal (parallax) angulated periapical radiograph images (mesial and distal horizontal angulations) significantly improved detection of apical periodontitis.
METHODOLOGY: Jaw sections containing 67 teeth (86 roots) were collected from unclaimed bodies due for cremation. Imaging was carried out to detect AP by digital PR with a central view (DP group), digital PR combining central with 10˚ mesially and distally angled (parallax) views (DPS group) and CBCT scans. All specimens underwent histopathological examination to confirm the diagnosis of AP. Sensitivity, specificity and predictive values of PR and CBCT were analysed using rater mean (n = 5). Receiver-operating characteristic (ROC) analysis was carried out.
RESULTS: Sensitivity was 0.27, 0.38 and 0.89 for DP, DPS and CBCT scans, respectively. CBCT had specificity and positive predictive value of 1.0 whilst DP and DPS had specificity and positive predictive value of 0.99. The negative predictive value was 0.39, 0.44 and 0.81 for DP, DPS and CBCT scans, respectively. Area under the curve (AUC) for the various imaging methods was 0.629 (DP), 0.688 (DPS), and 0.943 (CBCT).
CONCLUSIONS: All imaging techniques had similar specificity and positive predictive values. Additional parallax views increased the diagnostic accuracy of PR. CBCT had significantly higher diagnostic accuracy in detecting AP compared to PR, using human histopathological findings as a reference standard.
METHODS: In this study a novel system named Ceph-X is developed to computerize the manual tasks of orthodontics during cephalometric measurements. Ceph-X is developed by using image processing techniques with three main models: enhancements X-ray image model, locating landmark model, and computation model. Ceph-X was then evaluated by using X-ray images of 30 subjects (male and female) obtained from University of Malaya hospital. Three orthodontics specialists were involved in the evaluation of accuracy to avoid intra examiner error, and performance for Ceph-X, and 20 orthodontics specialists were involved in the evaluation of the usability, and user satisfaction for Ceph-X by using the SUS approach.
RESULTS: Statistical analysis for the comparison between the manual and automatic cephalometric approaches showed that Ceph-X achieved a great accuracy approximately 96.6%, with an acceptable errors variation approximately less than 0.5 mm, and 1°. Results showed that Ceph-X increased the specialist performance, and minimized the processing time to obtain cephalometric measurements of human skull. Furthermore, SUS analysis approach showed that Ceph-X has an excellent usability user's feedback.
CONCLUSIONS: The Ceph-X has proved its reliability, performance, and usability to be used by orthodontists for the analysis, diagnosis, and treatment of cephalometric.
MATERIALS AND METHODS: A total of 2306 subjects were selected from the patient archives of a large dental hospital and the chronological age for each subject was recorded. This age was assigned to each specific stage of dental development for each tooth to create a RDS. To validate this RDS, a further 484 subjects were randomly chosen from the patient archives and their dental age was assessed based on the scores from the RDS. Dental age was estimated using meta-analysis command corresponding to random effects statistical model. Chronological age (CA) and Dental Age (DA) were compared using the paired t-test.
RESULTS: The overall difference between the chronological and dental age (CA-DA) was 0.05 years (2.6 weeks) for males and 0.03 years (1.6 weeks) for females. The paired t-test indicated that there was no statistically significant difference between the chronological and dental age (p > 0.05).
CONCLUSION: The validated southern Chinese reference dataset based on dental maturation accurately estimated the chronological age.
METHODS: A total of 426 dental panoramic radiographs of 5-15-year-old Malaysian children were included in the study. The mean age error and absolute age error for all the methods were calculated and their usability analyzed.
RESULTS: The Nolla, Willems. and Demirjian methods overestimated the dental age with a mean of 0.97, 0.54, and 0.54 years, respectively, while the Cameriere and Haavikko methods underestimated by 0.41 and 1.31 years, respectively. The Cameriere method was highly precise and accurate in the population of Malaysian children, whereas the Haavikko and Demirjian methods were the least precise and accurate.
CONCLUSIONS: The Cameriere method of dental-age estimation is highly valid and reliable for Malaysian population, followed by the Willems and Nolla methods.