US findings in euthyroid patients with positive antithyroid autoantibody tests compared to normal and hypothyroid cases.

PURPOSE: We aimed to compare the ultrasonographic and laboratory parameters of euthyroid patients who have only positive antithyroid autoantibody test results with those of patients with a hypothyroid status of Hashimoto's thyroiditis (HT). MATERIALS AND METHODS: Thirty-five patients with newly diagnosed HT, 35 euthyroid patients who have autoantibodies against thyroid peroxidase (TPOAb) and/or thyroglobulin (TgAb), and 40 controls were enrolled in the study. Plasma free T3, free T4, thyroid stimulating hormone, TPOAb, and TgAb levels were obtained retrospectively. For gray-scale ultrasonography, each thyroid gland of all individuals graded with gray-scale grading (GSG), which was determined according to the gland size, parenchymal structure, echogenicity, micronodulation, contour irregularity, and existence of hyperechoic septa. For Doppler analysis, the peak systolic velocity (S), resistive index (RI), and pulsatility index (PI) values were obtained from the superior thyroid artery (STA) and intrathyroidal artery (ITA). The color pixel ratio (CPR), which was computationally evaluated from a power Doppler image of all individuals, was used for quantification of the intrathyroidal vascularity. RESULTS: Although the mean GSG values were higher in the HT and antibody-positive groups than they were in the control group, there was no significant difference between the HT and antibody-positive groups. The three study groups demonstrated no statistically significant difference with regard to the S, RI, or PI variables obtained from the STAs and ITAs. Although the CPR values were highest in the HT group, the difference between the HT and antibody-positive group did not reach statistical significance. CONCLUSION: The euthyroid antibody-positive group revealed gray-scale and Doppler ultrasonographic findings that were similar to those of the HT group.

Computer based classification of MR scans in first time applicant Alzheimer patients.

In this study, we aimed to classify MR images for recognizing Alzheimer Disease (AD) in a group of patients who were recently diagnosed by clinical history and neuropsychiatric exams by using non-biased machine-learning techniques. T1 weighted MRI scans of 31 patients with probable AD and 31 age- and gender-matched cognitively normal elderly were analyzed with voxel-based morphometry and classified by support vector machine (SVM), a machine learning technique. SVM could differentiate patients from controls with accuracy of 74% (sensitivity: 70% and specificity: 77%) when the whole brain was included the analyses. The classification accuracy was increased to 79% (sensitivity: 65 % and specificity: 93%) when the analyses restricted to hippocampus. Our results showed that SVM is a promising tool for diagnosis of AD, but needed to be improved.