Follicular Thyroid Carcinoma with Unusual Mandible Metastasis.

Follicular thyroid cancer is the second-most common type of thyroid cancer after papillary thyroid cancer. Metastases to the mandible and maxillofacial region are rare. Our study presents a 55-year-old patient who underwent total thyroidectomy for follicular thyroid cancer and subsequent radioactive iodine therapy. Sixteen years after diagnosis, elevated thyroglobulin levels suggested disease recurrence. Using advanced imaging techniques - Fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography scan, bone scintigraphy, and posttreatment I-131 scan-an unexpected metastatic site was identified: the left mandibular condyle. A biopsy confirmed the presence of metastatic follicular thyroid cancer.

Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer.

Purpose: This study aims to evaluate the potential of machine learning algorithms built with radiomics features from computed tomography urography (CTU) images that classify RB1 gene mutation status in bladder cancer. Method: The study enrolled CTU images of 18 patients with and 54 without RB1 mutation from a public database. Image and data preprocessing were performed after data augmentation. Feature selection steps were consisted of filter and wrapper methods. Pearson's correlation analysis was the filter, and a wrapper-based sequential feature selection algorithm was the wrapper. Models with XGBoost, Random Forest (RF), and k-Nearest Neighbors (kNN) algorithms were developed. Performance metrics of the models were calculated. Models' performances were compared by using Friedman's test. Results: 8 features were selected from 851 total extracted features. Accuracy, sensitivity, specificity, precision, recall, F1 measure and AUC were 84%, 80%, 88%, 86%, 80%, 0.83 and 0.84, for XGBoost; 72%, 80%, 65%, 67%, 80%, 0.73 and 0.72 for RF; 66%, 53%, 76%, 67%, 53%, 0.60 and 0.65 for kNN, respectively. XGBoost model had outperformed kNN model in Friedman's test (p = 0.006). Conclusions: Machine learning algorithms with radiomics features from CTU images show promising results in classifying bladder cancer by RB1 mutation status non-invasively.

Neuroimaging findings in patients with idiopathic intracranial hypertension and cerebral venous thrombosis, and their association with clinical features.

Objective: To investigate the frequency of neuroimaging findings of intracranial hypertension in patients with idiopathic intracranial hypertension (IIH) and cerebral venous thrombosis (CVT). We also aimed to compare these findings in two patient groups and investigate the association of these findings with some clinical parameters.Methods: Patients with IIH and CVT admitted to the neurology, neuro-ophthalmology outpatient clinics, and emergency services between 2017 and 2019 were enrolled in this study. The presence of eight previously defined neuroimaging signs of intracranial hypertension were evaluated on MRIs. The values of total MRI scores were formed to use in the analyses investigating the association between neuroimaging findings and clinical parameters.Results: Twenty-three patients with proven IIH and seven patients with CVT with signs of intracranial hypertension were included in this study. Body mass index (BMI) values were higher in the IIH group than in the CVT group (31.0/25.9; p = 0.022). There were no differences in terms of gender distribution, age, ortotal MRI scores between the patient groups. The most common neuroimaging parameters found in the IIH group were the following: increased peri-optic cerebrospinal fluid (CSF) (n = 20) and optic nerve tortuosity (n = 12). There were no significant correlations between values of total MRI scores, lumbar puncture opening pressure, and BMI.Conclusion: Neuroimaging findings are useful tools with high diagnostic sensitivity in IIH. The most sensitive finding was increased peri-optic CSF. The utility of these neuroimaging correlates and their potential significance as solely diagnostic markers in IIH should be investigated in future large-scale studies.

The Effects of 23-Gauge Pars Plana Vitrectomy on Orbital Circulation Using Doppler Ultrasonography in Diabetic Macular Edema with Epiretinal Membrane and Taut Posterior Hyaloid.

PURPOSE: To evaluate using Doppler ultrasonography (DUS) how pars plana vitrectomy (PPV) affects orbital circulation in diffuse diabetic macular edema (DME) associated with either the epiretinal membrane (ERM) or taut posterior hyaloid (TPH). METHODS: The sample included 46 eyes of 42 patients with DME associated with the ERM (n = 22, Group 1) or TPH (n = 24, Group 2). All participants received panretinal laser photocoagulation and antivascular endothelial growth factor injections preoperatively and underwent 23-gauge PPV combined with ERM or TPH removal and internal limiting membrane (ILM) peeling. Pre- and postoperative peak systolic velocity (PSV), end-diastolic velocity (EDV), and the resistivity index (RI) of the ophthalmic artery (OA), central retinal artery (CRA), posterior ciliary artery (PCA), and central retinal vein were measured with DUS. RESULTS: Statistically significant decreases in the PSV and EDV of the OA, CRA, and PCA were detected in all groups. In Group 1, the PSV of the OA and CRA as well as the EDV and PSV of the PCA declined significantly. In Group 2, the EDV of the OA and both the PSV and EDV of the CRA and PCA decreased. Postoperatively, the CRA's PSV and EDV were lower in Group 2, while the preoperative and postoperative RI of the CRA and preoperative RI of the PCA were greater in Group 2 than in Group 1. Changes in the CRA's RI, PSV, and EDV were greater in Group 2 after surgery. CONCLUSIONS: 23-Gauge PPV combined with ERM or TPH removal and ILM peeling in DME reduces blood flow rates of both choroidal and retinal vessels. In eyes with TPH, the RIs of the CRA and PCA were significantly greater preoperatively and the changes in the CRA's RI, PSV, and EDV were greater postoperatively. The removal of the TPH may play a role in regulating blood flow.