Objective Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. Materials and Methods A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. Results The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Conclusion Radiomic models using MRI were able to differentiate JME from HCs.

No abstract

BackgroundNasal bone fracture is one of the most common facial bone fracture types, and the surgical results exert a strong influence on the facial contour and patient satisfaction. Preventing secondary deformity and restoring the original bone state are the major goals of surgeons managing nasal bone fracture patients. In this study, a treatment algorithm was established by applying the modified open reduction technique and postoperative care for several years.MethodsThis article is a retrospective chart review of 417 patients who had been received surgical treatment from 2014 to 2015. Using prepared questionnaires and visual analogue scale, several components (postoperative nasal contour; degree of pain; minor complications like dry mouth, sleep disturbance, swallowing difficulty, conversation difficulty, and headache; and degree of patient satisfaction) were evaluated.ResultsThe average scores for the postoperative nasal contour given by three experts, and the degree of patient satisfaction, were within the “satisfied” (4) to “very satisfied” (5) range (4.5, 4.6, 4.5, and 4.2, respectively). The postoperative degree of pain was sufficiently low that the patients needed only the minimum dose of painkiller. The scores for the minor complications (dry mouth, sleep disturbance, swallowing difficulty, conversation difficulty, headache) were relatively low (36.4, 40.8, 65.2, 32.3, and 34 out of the maximum score of 100, respectively).ConclusionSatisfactory results were obtained through the algorithm-oriented management of nasal bone fracture. The degree of postoperative pain and minor complications were considerably low, and the degree of satisfaction with the nasal contour was high.