The diagnostic value of quantitative texture analysis of conventional MRI sequences using artificial neural networks in grading gliomas.

AIM: To explore the value of quantitative texture analysis of conventional magnetic resonance imaging (MRI) sequences using artificial neural networks (ANN) for the differentiation of high-grade gliomas (HGG) and low-grade gliomas (LGG). MATERIALS AND METHODS: A total of 181 patients, 97 with HGG (53.5%) and 84 with LGG (46.5%) with brain MRI having T2-weighted (W) fluid attenuation inversion recovery (FLAIR), and contrast-enhanced T1W images were enrolled in the present study. Histogram parameters and high-order texture features were extracted using manually placed regions of interest (ROIs) on T2W-FLAIR and contrast-enhanced T1W images covering the whole volume of the tumours. The reproducibility of the features was assessed by interobserver reliability analyses. The cohort was divided into training (n=121) and test partitions (n=60). The training set was used for attribute selection and model development, and the test set was used to evaluate the diagnostic performance of the pre-trained ANNs in discriminating HGG and LGG. RESULTS: In the test cohort, the ANN models using texture data of T2W-FLAIR and contrast-enhanced T1W images achieved an area under the receiver operating characteristic curve (AUC) of 0.87 and 0.86, respectively. The combined ANN model with selected texture features achieved the highest diagnostic accuracy equating 88.3% with an AUC of 0.92. CONCLUSIONS: Quantitative texture analysis of T2W-FLAIR and contrast-enhanced T1W enhanced by ANN can accurately discriminate HGG from LGG and might be of clinical value in tailoring the management strategies in patients with gliomas.

Assessment of ventricular tachyarrhythmia in patients with hypertrophic cardiomyopathy with machine learning-based texture analysis of late gadolinium enhancement cardiac MRI.

OBJECTIVE: To assess the diagnostic value of machine learning-based texture feature analysis of late gadolinium enhancement images on cardiac magnetic resonance imaging (MRI) for assessing the presence of ventricular tachyarrhythmia (VT) in patients with hypertrophic cardiomyopathy. MATERIALS AND METHODS: This retrospective study included 64 patients with hypertrophic cardiomyopathy who underwent cardiac MRI and 24-hour Holter monitoring within 1 year before cardiac MRI. There were 42 men and 22 women with a mean age of 48.13±13.06 (SD) years (range: 20-70 years). Quantitative textural features were extracted via manually placed regions of interest in areas with high and intermediate signal intensity on late gadolinium-chelate enhanced images. Feature selection and dimension reduction were performed. The diagnostic performances of machine learning classifiers including support vector machines, Naive Bayes, k-nearest-neighbors, and random forest for predicting the presence of VT were assessed using the results of 24-hour Holter monitoring as the reference test. All machine learning models were assessed with and without the application of the synthetic minority over-sampling technique (SMOTE). RESULTS: Of the 64 patients with hypertrophic cardiomyopathy, 21/64 (32.8%) had VT. Of eight machine learning models investigated, k-nearest-neighbors with SMOTE exhibited the best diagnostic accuracy for the presence or absence of VT. k-nearest-neighbors with SMOTE correctly identified 40/42 (95.2%) VT-positive patients and 40/43 (93.0%) VT-negative patients, yielding 95.2% sensitivity (95% CI: 82.5%-99.1%), 93.0% specificity (95% CI: 79.8%-98.1%) and 94.1% accuracy (95% CI: 88.8%-98%). CONCLUSION: Machine learning-based texture analysis of late gadolinium-chelate enhancement-positive areas is a promising tool for the classification of hypertrophic cardiomyopathy patients with and without VT.

Is there any association between jugular venous reflux and nonpulsatile subjective tinnitus? A preliminary study of four-dimensional magnetic resonance angiography.

OBJECTIVE: To demonstrate whether there is an association between jugular venous reflux and nonpulsatile subjective tinnitus (NST) using real-time four-dimensional magnetic resonance imaging (MRI) angiography. MATERIALS AND METHODS: Patients with unilateral NST who underwent contrast-enhanced MRI with a special protocol were included in the study. Thick slab dynamic maximum intensity projection images were obtained including interleaved stochastic trajectories (TWIST)-MRI examination. All patients were requested to perform Valsalva maneuver during the sequence. Jugular venous reflux grading was performed as follows: absence of reflux or if reflux does not reach the base of the skull: grade 0; if reflux reaches the jugular bulb, but no intracranial contrast is observed: grade 1; and if reflux extends into the intracranial cortical veins and/or the cavernous sinus above the jugular bulb: Grade 2. RESULTS: A total number of 30 patients, 23 male and 7 female, were included in the study. Jugular venous reflux was not identified (Grade 0) in 20 patients. Grade 1 reflux was determined in 7 cases and Grade 2 reflux was observed in 3 cases. Notably, only patients with Grade 2 reflux described worsening of their tinnitus symptoms during the examination and their daily activities as well. CONCLUSIONS: NST might also be associated with hemodynamic problems of the venous system and the MRI protocol starting with TWIST accompanied with Valsalva maneuver is not well-known, yet seems to be a feasible and beneficial method to detect potential jugular venous reflux in NST patients.

Evaluation of carotid intima-media thickness with vascular endothelial growth factor and malondialdehyde levels in patients with sarcoidosis.

PURPOSE: To assess the impact of sarcoidosis on endothelial function by measuring carotid intima-media thickness (CIMT) and serum levels of malondialdehyde and vascular endothelial growth factor (VEGF). MATERIALS AND METHODS: We prospectively analyzed 41 patients with sarcoidosis (9 men, 32 women) with a mean age of 44.9±10.2 (SD) years and 34 healthy subjects (9 men, 24 women) with a mean age of 37.26±8.9 (SD) years who served as a control group. Sarcoidosis patients receiving steroids were included in Group 1 while those not under steroid treatment were included in Group 2. CIMT measurements were performed using B-mode ultrasound. Malondialdehyde and VEGF serum levels were obtained in all sarcoidosis patients and control subjects. RESULTS: Both right and left CIMT was significantly higher in Group 1 and Group 2 than in control subjects. Serum levels of malondialdehyde and VEGF in Group 1 and Group 2 were significantly higher than in healthy subjects. No differences in CIMT, malondialdehyde and VEGF were found between Group 1 and Group 2. CONCLUSION: Sarcoidosis results in increased CIMT, VEGF and malondialdehyde serum levels. However, there was no difference in terms of CIMT, VEGF and malondialdehyde levels between sarcoidosis patients with or without steroid treatment, suggesting that new treatment strategies for sarcoidosis vascular involvement should consider this result.

Apparent diffusion coefficient measurement of ovarian stroma: A potential tool for the diagnosis of polycystic ovary syndrome.

PURPOSE: The purpose of this study was to assess the diagnostic value of measuring the apparent diffusion coefficient (ADC) of ovarian stroma in polycystic ovary syndrome (PCOS). MATERIALS AND METHODS: This study was approved by the institutional review board and informed consent was obtained from each women. A total of 17 women (mean age, 22.2 years±5.1 [SD]; range, 16-33 years) with a diagnosis of PCOS according to the Androgen Excess and PCOS Society criteria and 18 healthy women (mean age, 22.8 years±5.2 [SD]; range, 16-31 years) who served as a control group were included in this prospective study. ADC values of the ovarian stroma during the early follicular phase were calculated by two observers in the two groups. Comparisons were performed using the Student t-test. RESULTS: The mean ADC value in woman with PCOS (1.29±0.27×10-3 mm2/s; range: 0.59×10-3 - 1.88×10-3 mm2/s) was significantly lower than that in the control group (1.48±0.17×10-3 mm2/s; range: 1.12×10-3 - 1.86×10-3 mm2/s) (P<0.001). The ADC cutoff value for the determination of PCOS with maximum accuracy was 1.38×10-3 mm2/s (AUC: 0.720; 95% CI: 0.597, 0.843), yielding 78% sensitivity and 62.9% specificity. CONCLUSION: ADC values of ovarian stroma are lower in patients with PCOS than in control subjects. ADC measurement of ovarian stroma in women with PCOS might help improve the diagnosis of PCOS.