RESUMEN
BACKGROUND: Accurate age estimation is vital for clinical and forensic purposes. With the rapid advancement of artificial intelligence(AI) technologies, traditional methods relying on tooth development, while reliable, can be enhanced by leveraging deep learning, particularly neural networks. This study evaluated the efficiency of an AI model by applying the entire panoramic image for age estimation. The outcome performances were analyzed through supervised learning (SL) models. METHODS: Total of 27,877 dental panorama images from 5 to 90 years of age were classified by 2 types of grouping. In type 1 they were classified by each age and in type 2, applying heuristic grouping, the age over 20 years were classified by every 5 years. Wide ResNet (WRN) and DenseNet (DN) were used for supervised learning. In addition, the analysis with ± 3 years of deviation in both types were performed. RESULTS: For the DN model, while the type 1 grouping achieved an accuracy of 0.1016 and F1 score of 0.058, the type 2 achieved an accuracy of 0.3146 and F1 score of 0.2027. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.281, 0.7323 respectively; and the F1 score were 0.1768, 0.6583 respectively. For the WRN model, while the type 1 grouping achieved an accuracy of 0.1041 and F1 score of 0.0599, the type 2 achieved an accuracy of 0.3182 and F1 score of 0.2071. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.2716, 0.7323 respectively; and the F1 score were 0.1709, 0.6437 respectively. CONCLUSIONS: The application of entire panorama image data for supervised with classification by heuristics grouping with ± 3years of deviation for supervised learning models and demonstrated satisfactory outcome for the age estimation.
Asunto(s)
Inteligencia Artificial , Odontogénesis , Humanos , Adulto Joven , Adulto , TecnologíaRESUMEN
OBJECTIVES: The aim of the study was to evaluate the efficacy of traditional supervised learning (SL) and semi-supervised learning (SSL) in the classification of mandibular third molars (Mn3s) on panoramic images. The simplicity of preprocessing step and the outcome of the performance of SL and SSL were analyzed. METHODS: Total 1625 Mn3s cropped images from 1000 panoramic images were labeled for classifications of the depth of impaction (D class), spatial relation with adjacent second molar (S class), and relationship with inferior alveolar nerve canal (N class). For the SL model, WideResNet (WRN) was applicated and for the SSL model, LaplaceNet (LN) was utilized. RESULTS: In the WRN model, 300 labeled images for D and S classes, and 360 labeled images for N class were used for training and validation. In the LN model, only 40 labeled images for D, S, and N classes were used for learning. The F1 score were 0.87, 0.87, and 0.83 in WRN model, 0.84, 0.94, and 0.80 for D class, S class, and N class in the LN model, respectively. CONCLUSIONS: These results confirmed that the LN model applied as SSL, even utilizing a small number of labeled images, demonstrated the satisfactory of the prediction accuracy similar to that of the WRN model as SL.
Asunto(s)
Tercer Molar , Diente Impactado , Humanos , Tercer Molar/diagnóstico por imagen , Radiografía Panorámica/métodos , Inteligencia Artificial , Mandíbula , Tomografía Computarizada de Haz Cónico , Aprendizaje Automático SupervisadoRESUMEN
This study investigated the retreatability of EndoSeal MTA (Maruch, Wonju, Korea) according to the presence or absence of a canal isthmus and the additional use of passive ultrasonic irrigation (PUI) through microcomputed tomography (micro-CT) imaging. An epoxy resin sealer (AH Plus (Dentsply DeTrey, Konstanz, Germany)) was used as a reference for comparison. Forty-five artificial mandibular molars (TRUETOOTH #19, DELABS, Santa Barbara, CA) with a mesial canal with an isthmus and a distal canal without an isthmus were obturated using gutta-percha and one of the following sealers (n = 15 each): AH Plus, EndoSeal MTA, and EndoSeal MTA + PUI. Micro-CT scanning was performed to assess the void volume (as a percentage) at three root levels. After the root fillings were removed, second micro-CT scanning was conducted to evaluate the amount of remaining root filling material. The Kruskal-Wallis H test and post hoc analysis were used for between-group comparisons. The Mann-Whitney U test was used for comparisons between canals with and without an isthmus (p < 0.05). In the EndoSeal MTA group, the void volume and remaining filling materials were higher irrespective of the presence or absence of an isthmus. In apical lesions in the EndoSeal MTA group, the void ratio was significantly lower, and there was a significantly higher amount of remaining filling material. Regardless of the presence of an isthmus, the amount of remaining filling material of the EndoSeal + PUI group was reduced to a similar degree as the AH plus group. When performing retreatment for root canals filled with EndoSeal MTA, removal of the filling material can be more difficult in the apical region. The additional use of PUI can improve the efficacy of removal.
Asunto(s)
Materiales de Obturación del Conducto Radicular , Compuestos de Calcio , Cavidad Pulpar , Resinas Epoxi , Gutapercha , Retratamiento , Obturación del Conducto Radicular , Preparación del Conducto Radicular , Silicatos , Ultrasonido , Microtomografía por Rayos XRESUMEN
BACKGROUND: During the ongoing coronavirus disease (COVID-19) pandemic, hospitals have strengthened their guidelines on infection prevention and control (IPC), and a rigorous adherence to these guidelines is crucial. An infection control surveillance-working group (ICS-WG) and infection control coordinators (ICCs) team were created to monitor the IPC practices of the healthcare workers (HCWs) in a regional hospital in Korea. This study analyzed the surveillance results and aimed to identify what IPC practices needed improvement. METHODS: During phase 1 (March to April 2020), the ICS-WG performed random audits, recorded incidences of improper IPC practices, and provided advice to the violators. During phase 2 (April to July), the ICCs inspected the hospital units and proposed practical ideas about IPC. The surveillance and proposals targeted the following practices: patient screening, usage of personal protective equipment (PPE), hand and respiratory hygiene, equipment reprocessing, environmental cleaning, management of medical waste, and social distancing. RESULTS: In phase 1, of the 127 violations observed, most (32.3%) corresponded to hand and respiratory hygiene. In phase 2, the highest proportion of violation per category was observed in the management of medical waste (37.8%); among these, a higher proportion of violation (71.4%) was observed in the collection of medical waste. Of the 106 proposals made by the ICCs, the most addressed practice was patient screening (28.3%). No case of nosocomial infection was reported during the study period. CONCLUSION: Adherence to proper hand and respiratory hygiene was inadequate at the early stage of the COVID-19 pandemic. The results indicate that more attention and further training are needed for the management of medical waste, particularly medical waste collection, and that continuous upgrading of the strategies for patient screening is essential. These results will be useful in helping other healthcare facilities to establish their IPC strategies.
Asunto(s)
COVID-19/prevención & control , Adhesión a Directriz/estadística & datos numéricos , Personal de Salud , Control de Infecciones , Auditoría Clínica , Higiene de las Manos , Humanos , Pandemias , República de CoreaRESUMEN
PURPOSE: The purpose of this study was to compare the translucency and color changes of ceramic laminate veneers of different composition following glazing process. MATERIALS AND METHODS: 10 mm × 10 mm square specimens of 0.6 mm and 1.0 mm thicknesses were fabricated with IPS e.max Press (EM) and IPS e.max ZirPress (ZP) (n=10 per group). The color coordinates (CIE L* a* b*) of the specimens were recorded with a colorimeter before and after glazing. The color changes and translucency parameter (TP) were calculated. For the comparisons with the composition and thicknesses between the 'not glazed' and 'glazed' groups, statistical analyses were done through paired T-test, independent two-sample T-test, and multiple regression analysis using SPSS 18.0 (P<.05). RESULTS: The TP of 0.6 mm EM was higher than that of 0.6 mm ZP. Total color difference (ΔE*) between bare and glazed specimens of 1.0 mm EM was greater than that of 1.0 mm ZP with statistical significance. Following glazing, specimens from all groups showed statistically significant amount of decrease in L* and a*, and statistically significant increase in b*. The result of multiple regression analysis of EM and ZP showed that ΔL* improved ΔE*. CONCLUSION: Within the limitations of present study, we conclude that translucency and color of ceramic laminate veneers change significantly after glazing process, and the nature and amount of changes vary with different compositions.