RESUMEN

BACKGROUND: Artificial intelligence has been proven to improve the identification of various maxillofacial lesions. The aim of the current study is two-fold: to assess the performance of four deep learning models (DLM) in external root resorption (ERR) identification and to assess the effect of combining feature selection technique (FST) with DLM on their ability in ERR identification. METHODS: External root resorption was simulated on 88 extracted premolar teeth using tungsten bur in different depths (0.5 mm, 1 mm, and 2 mm). All teeth were scanned using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training (70%), validation (10%), and test (20%) dataset were established. The performance of four DLMs including Random Forest (RF) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector Machine (SVM) + VGG, and SVM + EFNET) and four hybrid models (DLM + FST: (i) FS + RF + VGG, (ii) FS + RF + EFNET, (iii) FS + SVM + VGG and (iv) FS + SVM + EFNET) was compared. Five performance parameters were assessed: classification accuracy, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their performance. RESULTS: RF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed other models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the curve (AUC) of 96%. Kruskal Wallis test revealed a significant difference (p = 0.008) in the prediction accuracy among the eight DLMs. CONCLUSION: In general, all DLMs have similar performance on ERR identification. However, the performance can be improved by combining FST with DLMs.

Asunto(s)

RESUMEN

OBJECTIVES: To describe the radiographic features of odontogenic keratocysts (OKCs) and ameloblastomas and to compare the radiographic findings between these 2 lesions. METHODS: Radiographs of OKCs and ameloblastomas were retrospectively reviewed. Location, border, shape, association with impacted tooth, tooth displacement, root resorption, and bone expansion were evaluated. Chi-squared or Fisher's exact tests were used for statistical analysis. A p value < 0.05 was considered to indicate statistical significance. RESULTS: One hundred OKCs and 101 ameloblastomas were reviewed. The ratios of maxilla to mandible were 1:1.4 and 1:9.1 in OKCs and ameloblastomas, respectively. All evaluated features significantly differed between OKCs and ameloblastomas (p ≤ 0.001). Most OKCs showed smooth border (60%) and unilocular shape (82%), while most ameloblastomas showed scalloped border (77.2%) and multilocular shape (68.3%). Association with impacted tooth was found in 47% of OKCs and 18.8% of ameloblastomas. Adjacent tooth displacement was found in 33.7% of OKCs and 55.8% of ameloblastomas. Root resorption was more common in ameloblastomas (66.7%) than in OKCs (7%). Bone expansion was also more common in ameloblastomas (96.3%) than in OKCs (63.6%). CONCLUSION: A unilocular radiolucent lesion with smooth border, no adjacent tooth displacement, no root resorption and causing mild or no bone expansion is suggestive of an OKC rather than an ameloblastoma.

Asunto(s)

RESUMEN

OBJECTIVES: The aim of this study was to evaluate the accuracy of cone beam computed tomography (CBCT), periapical radiograph, and intrasurgical linear measurements in the assessment of molars with furcation defects. MATERIALS AND METHODS: This parallel, single-blinded, randomised controlled trial (RCT) consisted of 22 periodontitis patients who had molar with advanced furcation involvement (FI). All patients followed the same inclusion criteria and were treated following the same protocol, except for radiographic evaluation (CBCT vs. periapical). This study proposed and evaluated five parameters that represent the extent and severity of furcation defects in molars teeth, including CEJ-BD (clinical attachment loss), BL-H (depth), BL-V (height), RT (root trunk), and FW (width). RESULTS: There were no statistically significant differences between CBCT and intrasurgical linear measurements for any clinical parameter (p > 0.05). However, there were statistically significant differences in BL-V measurements (p < 0.05) between periapical and intrasurgical measurements in maxillary molars. Meanwhile, the sensitivity were 62.8% and 56.9% for CBCT and periapical, respectively. CONCLUSIONS: Overall, when compared to the intrasurgical measurements, CBCT provided better diagnostic, sensitivity, and quantitative information on CAL, height, depth, and width of the furcation defects than periapical radiograph. CLINICAL RELEVANCE: An accurate presurgical furcation diagnostic can guide the clinicians from the stage of diagnosis to definitive management so that unnecessary periodontal surgical interventions can be prevented.

Asunto(s)

RESUMEN

OBJECTIVE: Knowledge and evaluation of the blood supply within the maxillary sinus before sinus augmentation are vital to avoid surgical complications. The lateral maxilla is supplied by branches of the posterior superior alveolar artery and infraorbital artery forming intraosseous anastomoses (IA) within the bony lateral antral wall. This study was undertaken to (i) measure mean diameter of IA and its distance from the alveolar ridge within dentate and posteriorly edentulous subjects and, (ii) qualitatively display the relationship of IA throughout its course within the lateral maxillary sinus in cone beam computed tomography (CBCT). METHOD: Maxillary CBCT images of two-hundred-and-fifty-seven consecutive patients (163 men, 94 women, mean age 42 years) were analyzed. Samples were later divided into dentate (n = 142) and posteriorly edentulous (n = 115) jaws. Using both alveolar ridge and tooth location as reference points, the distance and diameter of IA were assessed. RESULT: The IA was seen in 63.7% of all sinuses with 68.2% in dentate and 62.4% in edentulous. Mean distance and diameter of IA across the posterior tooth locations were 17.9 ± 3.0 mm and 1.4 ± 0.5 mm (dentate) and 15.1 ± 3.0 mm and 1.0 ± 0.5 mm (posteriorly edentulous), respectively. In each sample, there were no significant differences in distance-alveolar ridge and no significant correlations in diameter-tooth location. A statistically significant Pearson coefficient correlation between diameter and distance in dentate state was observed (r = -0.6). CONCLUSION: This study reveals that dentate maxillary jaws present larger diameters as compared to posteriorly edentulous jaws, although the IA course remains the same. As these canal structures contain neurovascular bundles with diameters that may be large enough to cause clinically substantial complications, a thorough pre-surgical planning is therefore highly advisable.

RESUMEN

OBJECTIVE: This study was conducted to compare the anesthetic and analgesic efficacy of bupivacaine with other local anesthetic agents routinely used for mandibular third molar surgery. METHOD AND MATERIALS: Four electronic databases (PubMed, Scopus, Cochrane, and Web of Science) were explored to isolate randomized controlled trials up to 10 February 2019. The anesthetic and analgesic efficacies were assessed using six evaluation outcomes: onset of anesthesia, success of anesthesia, duration of anesthesia, duration of analgesia, pain score on the fourth postoperative hour, and number of analgesics consumed. Stata software (version 13, StataCorp) was used to analyze the data. RESULTS: Fourteen studies met the specified criteria. The sample consisted of 1,078 mandibular third molar surgeries performed in 858 patients. Bupivacaine, lidocaine/lignocaine, articaine, etidocaine, levobupivacaine, and carbonated bupivacaine were the local anesthetics used. Compared with other anesthetic agents, bupivacaine showed longer duration of anesthesia (weighted mean difference [WMD] 123.431 minutes; 95% confidence interval [CI] 34.01 to 212.851; P = .007), lower pain score at the fourth and eighth postoperative hours (4 hr-WMD 2.757; 95% CI 0.893 to 4.62; P = .004; 8 hr-WMD 1.697; 95% CI 1.178 to 2.216; P < .001), and lower number of analgesics requirement (WMD 0.663; 95% CI 0.258 to 1.067; P = .001). The onset of anesthesia was slower for bupivacaine (WMD 0.865 minutes; 95% CI 0.799 to 0.931; P < .001). However, for success of anesthesia (risk ratio 1.003; 95% CI 0.972 to 1.035; P = .831) and duration of analgesia (WMD 45.285 minutes; 95% CI -48.021 to 138.537; P = .342), the local anesthetic agents showed no significant differences. CONCLUSIONS: Except for the onset of anesthesia, bupivacaine showed better anesthetic and analgesic properties than other local anesthetic agents for mandibular third molar surgery.

Asunto(s)