Prediction of extraction difficulty for impacted maxillary third molars with deep learning approach.

OBJECTIVE: The aim of this study is to determine if a deep learning (DL) model can predict the surgical difficulty for impacted maxillary third molar tooth using panoramic images before surgery. MATERIALS AND METHODS: The dataset consists of 708 panoramic radiographs of the patients who applied to the Oral and Maxillofacial Surgery Clinic for various reasons. Each maxillary third molar difficulty was scored based on dept (V), angulation (H), relation with maxillary sinus (S), and relation with ramus (R) on panoramic images. The YoloV5x architecture was used to perform automatic segmentation and classification. To prevent re-testing of images, participate in the training, the data set was subdivided as: 80 % training, 10 % validation, and 10 % test group. RESULTS: Impacted Upper Third Molar Segmentation model showed best success on sensitivity, precision and F1 score with 0,9705, 0,9428 and 0,9565, respectively. S-model had a lesser sensitivity, precision and F1 score than the other models with 0,8974, 0,6194, 0,7329, respectively. CONCLUSION: The results showed that the proposed DL model could be effective for predicting the surgical difficulty of an impacted maxillary third molar tooth using panoramic radiographs and this approach might help as a decision support mechanism for the clinicians in peri­surgical period.

Is Injectable Platelet-Rich Fibrin Really Effective in Reducing Expected Side Effects of Removing Impacted Third Molar Surgery?

BACKGROUND: Common side effects of third molar (M3) operations including pain, edema, and trismus have an adverse effect on patient quality of life. Injectable platelet-rich fibrin (i-PRF) may ameliorate some of the side effects of the operation. PURPOSE: The primary purpose of this study is to measure and compare differences in pain, swelling, trismus, and quality of life between i-PRF side and a control side of subjects undergoing M3 removal. STUDY DESIGN, SETTING AND SAMPLE: This study is a single-center, split-mouth, randomized prospective clinical trial conducted at Ordu University Faculty of Dentistry. Patients who presented between March and August 2022 for the extraction of impacted third molars due to various reasons were included in the study. The exclusion criteria were local conditions and systematic comorbidities. Additionally, patients with differences that could cause bias between the sides were excluded from the study. PREDICTOR VARIABLE: The predictor variable is treatment i-PRF or control. MAIN OUTCOME VARIABLE: The outcome variables of interest are the pain level and analgesic consumption values on the Visual Analog Scale, the distance between determined reference points, maximum mouth opening, and the Postoperative Symptom Severity scale data. A Postoperative Symptom Severity scale was created using questions commonly employed in the clinical evaluation of patients following the extraction of third molars. This scale was further divided into subscales corresponding to the 7 primary adverse effects identified in a prior study. COVARIATES: Covariate variables, sex, age, and operation times. ANALYSES: The normality of the distribution of the study data was assessed using the Kolmogorov-Smirnov test. Depending on whether the data exhibited a normal distribution or not, the data were analyzed using either the paired t-test or the Wilcoxon test. A P value < .05 was considered statistically significant. RESULTS: The study included 35 patients with a mean age of 19.97 ± 2.07 years. The i-PRF side significant success in postoperative edema measurements. There was a statistically significant difference observed between the control side and the i-PRF side on the second day (control: 9.74 ± 0.57 mm, i-PRF: 9.46 ± 0.51 mm) and seventh day (control: 9.33 ± 0.59 mm, i-PRF: 9.12 ± 0.50 mm) in lateral canthus-angulus measurements (P: .01 and P: .04, respectively). Additionally, on the second day, there was a statistically significant difference in tragus-commisura measurements (control: 11.53 ± 0.62 mm, i-PRF: 11.31 ± 0.58 mm) with a P value of .02. There was no significant difference observed between the sides in terms of postoperative pain (P > .05). However, analgesic consumption in the i-PRF side was significantly lower at the sixth hour (control: 1.8 ± 0.58 dose, i-PRF: 1.14 ± 0.35 dose), 24th hour (control: 1.77 ± 0.54 dose, i-PRF: 1.14 ± 0.35 dose), and second day (control: 1.8 ± 0.47 dose, i-PRF: 1.4 ± 0.73 dose) postoperatively (P: .000, P: .000, and P: .012). Mouth opening was significantly lower in the i-PRF side on the second day (control: 27.88 ± 6.48 mm, i-PRF: 25.51 ± 5.56 mm) (P: .025). However, i-PRF had no significant effect on postoperative quality of life (P > .05). CONCLUSIONS: According to the study results, i-PRF had a limited effect on the management of postoperative pain, but i-PRF was effective in reducing postoperative edema. Further studies with larger patient sides are now needed to yield more detailed findings on the subject.