Automated BI-RADS classification of lesions using pyramid triple deep feature generator technique on breast ultrasound images.

Ultrasound (US) is an important imaging modality used to assess breast lesions for malignant features. In the past decade, many machine learning models have been developed for automated discrimination of breast cancer versus normal on US images, but few have classified the images based on the Breast Imaging Reporting and Data System (BI-RADS) classes. This work aimed to develop a model for classifying US breast lesions using a BI-RADS classification framework with a new multi-class US image dataset. We proposed a deep model that combined a novel pyramid triple deep feature generator (PTDFG) with transfer learning based on three pre-trained networks for creating deep features. Bilinear interpolation was applied to decompose the input image into four images of successively smaller dimensions, constituting a four-level pyramid for downstream feature generation with the pre-trained networks. Neighborhood component analysis was applied to the generated features to select each network's 1,000 most informative features, which were fed to support vector machine classifier for automated classification using a ten-fold cross-validation strategy. Our proposed model was validated using a new US image dataset containing 1,038 images divided into eight BI-RADS classes and histopathological results. We defined three classification schemes: Case 1 involved the classification of all images into eight categories; Case 2, classification of breast US images into five BI-RADS classes; and Case 3, classification of BI-RADS 4 lesions into benign versus malignant classes. Our PTDFG-based transfer learning model attained accuracy rates of 79.29%, 80.42%, and 88.67% for Case 1, Case 2, and Case 3, respectively.

Role of hepatosteatosis in the prognosis of COVID 19 disease.

PURPOSE: To measure the degree of fatty liver using non-contrast enhanced chest computed tomography (CT) and investigate its relationship with the severity and prognosis of coronavirus disease 2019 (COVID-19) in adult patients. METHODS: This retrospective study included consecutive patients who had been diagnosed with COVID-19 using real-time reverse-transcription polymerase chain reaction (RT-PCR) and subsequently underwent non-contrast enhanced chest CT between October 10 and December 10, 2020. Hepatic attenuation values were measured from Couinaud segments 2, 4, and 8 based on the CT images and the relationships between these values and the Pneumonia Severity Score (PSS), requirement of hospitalization, and the length of hospital and intensive care unit (ICU) stay were analyzed. RESULTS: The study included 414 patients (182 were female, 43.96%), among whom 106 (25.6%) were diagnosed with hepatosteatosis (HS). In the patients with HS, the PSS scores were higher (10.8 ± 4.96 vs. 8.07 ± 5.12; p < 0.001), and 69 (65%) received inpatient care. Moreover, the number of HS patients who received inpatient care was 1.99 (95% confidence interval (CI) 1.26-3.15, p < 0.003) times higher than that of the non-HS patients. No significant difference was found between the HS and non-HS patients with regard to the length of hospital or ICU stay. CONCLUSION: HS can be easily evaluated using non-contrast enhanced chest CT in COVID-19 patients and can be used as a prognostic marker to determine the requirement of hospitalization.

Merkel cell carcinoma of the gluteal region: A rare case report and literature review.

Merkel cell carcinoma (MCC) is a rare cutaneous neuroendocrine cancer that shows aggressive biological behaviour. Although it usually occurs on sun-exposed areas, it can sometimes be seen on non-sun-exposed sites. Here, we present the case of a 66-year-old woman with MCC arising from the right gluteal region that was treated with excision and adjuvant chemoradiotherapy. On follow-up after the 24 months, the patient was disease- and recurrence-free, representing the longest survival among patients with gluteal MCC. Early diagnosis and treatment are important to improve survival rates in patients with non-sun-exposed MCC.

Evaluation of diffusion tensor imaging changes and neurocognitive effects of asymptomatic vitamin B12 deficiency.

Vitamin B12 plays an important role in the mechanisms which are responsible for myelinization in the central nervous system. It can particularly lead to hematological and neuropsychiatric symptoms when serum levels fall due to insufficient intake with diet or absorption problems. The purpose of this study was to show the cognitive effects in vitamin B12 deficiency cases that have not reached clinical symptom level using neuropsychological tests, and to show possible cerebral neuronal damage using diffusion tensor imaging (DTI) method. A total of 62 asymptomatic vitamin B12 deficiency patients and 40 healthy subjects were included in the study and both groups were subjected to Standardized Mini-Mental State Examination, Montreal Cognitive Assessment Test, Rey Auditory Verbal Learning Test, forward and backward digit span (WMS-R forward and backward), Visual Reproduction Subtest (WMS-III), Category Fluency Test, Trail Making (Trail A-B) (21) and Similarities (BENZ) tests. DTI examinations were performed on both groups. Patient group was determined to get lower scores in all neuropsychological tests compared to control group. In DTI examination, a significant decrease in FA values of bilateral hippocampus and a prominent increase in apparent diffusion coefficient (ADC) values were determined in the patient group compared to control group. In this study, it was determined that there was microstructural damage in the brain in the presence of vitamin B12 deficiency even in the asymptomatic period, and the patients revealed cognitive decline. In accordance with this result, early treatment of the easily diagnosed and treated vitamin B12 deficiency may prevent possible irreversible damage in the future.

The relationship between white matter abnormalities and cognitive functions in new-onset juvenile myoclonic epilepsy.

Diffusion tensor imaging (DTI) has revealed evidence of subcortical white matter abnormalities in the frontal area in juvenile myoclonic epilepsy (JME). Decreased fractional anisotropy (FA) and increased mean diffusivity (MD) in the corticothalamic pathway have been detected in adult patients with JME. It has been demonstrated that, in adult patients with JME, frontal dysfunction is related to subcortical white matter damage and decreased volume in frontal cortical gray matter and the thalamus. Many studies have focused on adult patients. Twenty-four patients and 28 controls were evaluated. The group with JME had significantly worse results for the word fluency, trail-B, and Stroop tests that assessed executive functions. A significant decrease in FA values in the dorsolateral prefrontal cortex (DLPFC), the supplementary motor area (SMA), the right thalamus, the posterior cingulate, the corpus callosum anterior, the corona radiata, and the middle frontal white matter (MFWM) and an increase in ADC values in patients with JME were detected. The correlation between FA values in DLPFC and the letter fluency test results was positive, and the correlation with the Stroop and trail-B test results was negative. We found a negative correlation between SMA, anterior thalamus, and MFWM FA values and the trail-B test results and a positive correlation between the SMA, anterior thalamus, and MFWM FA values and the letter fluency test results. We detected white matter and gray matter abnormalities in patients with new-onset JME using DTI. In addition, we determined the relationship between cognitive deficit and microstructural abnormalities by evaluating the correlation between the neuropsychological test battery results and DTI parameters. We evaluated newly diagnosed patients with JME in our study. That leads us to believe that microstructural abnormalities exist from the very beginning of the disease and that they result from the genetic basis of the disease.

The relationship between mean platelet volume and other platelet indices with testicular artery blood flow and fertility: a preliminary study.

OBJECTIVES: To examine the relationship between platelets (PLT) and platelets indices such as mean platelet volume (MPV), platelet distribution width (PDW), and plateletcrit (PCT) as noninvasive biomarkers with testicular artery blood flow and fertility. METHODS: Fifty-seven healthy and fertile men with normal semen values and 52 patients with abnormal semen values were included in the study. The participants' PLT, MPV, PDW and PCT values were analyzed. Four different levels of the testicular artery, peak systolic velocity (PSV), end-diastolic velocity (EDV), and resistive index (RI) were measured using color Doppler ultrasound. RESULTS: There was no significant difference in terms of platelet and platelet indices (MPV, PDW and PCT) between the fertile and infertile group. There were no between group differences in the RI values of the testicular- and intra-testicular artery. When all fertile and infertile participants were considered together, there was no statistically significant correlation between the parameters of the testicular artery blood flow (PSV, EDV and RI) and platelet and platelet indices (MPV, PDW and PCT) (P > 0.05). CONCLUSIONS: There is not statistically significant correlation between any of the following parameters: platelets and platelet indices such as MPV, PDW and PCT, RI of the testicular artery, and fertility.

False-negative diffusion-weighted imaging in acute stroke and its frequency in anterior and posterior circulation ischemia.

OBJECTIVE: We aimed to investigate the location and size of ischemic stroke lesions that were frequently overlooked by diffusion-weighted imaging (DWI). MATERIALS AND METHODS: We retrospectively reviewed the medical records of 162 patients who had symptoms suggesting ischemic stroke. National Institutes of Health Stroke Scale and Modified Rankin Scale scores, lesion size, magnetic resonance imaging (MRI) findings, delay between onset of symptoms and initial MRI (MRI latency), and vascular distribution of the stroke lesions were analyzed in patients with false-negative DWI findings. RESULTS: Of the 116 patients with a final diagnosis of acute ischemic stroke, 11 patients (9.48%) had false-negative DWI findings in the initial period. The mean (SD) MRI latency was 4.3 (1.2) hours. There was no statistically significant difference in point of lesion size, the National Institutes of Health Stroke Scale, and the Modified Rankin Scales scores. CONCLUSIONS: False-negative DWI findings in acute stroke can be observed both in association with the posterior circulation/small lesions and the anterior circulation/large lesions.

The diagnostic and grading value of diffusion tensor imaging in patients with carpal tunnel syndrome.

RATIONALE AND OBJECTIVES: In this study, we investigated the diagnostic and grading value of diffusion tensor imaging (DTI) in patients with carpal tunnel syndrome (CTS). MATERIALS AND METHODS: Of the 120 subjects included in the present study, 72 were in the CTS group and 48 were in the healthy control group. In addition, the patients with CTS were further divided into three subgroups based on severity (mild, moderate, and severe) according to electrophysiological studies (EPS). DTI-derived parameters (fractional anisotropy [FA] and apparent diffusion coefficient [ADC]) were evaluated at four median nerve levels. The mean FA and ADC values of the CTS groups and healthy controls were compared separately. Correlations and possible relationships between DTI parameters and EPS results were analyzed. Receiver operating characteristics analysis was used to calculate the FA and ADC cutoff values for CTS diagnosis and grading. RESULTS: Statistically significant differences were observed in mean FA and ADC between the normal and mild, mild and moderate, and moderate and severe subgroups. Significant correlations were found between DTI parameters and EPS measurements based on severity. FA and ADC threshold values, as well as the sensitivity and specificity levels, for diagnosing and grading CTS were determined. CONCLUSIONS: DTI parameters can provide helpful information for CTS. The correlations of FA and ADC measurements versus EPS measurements based on severity were significant. Moreover, FA and ADC threshold values were sufficient for the diagnosis and grading of CTS.

Use of diffusion tensor imaging for nonsurgical treatments of carpal tunnel syndrome.

INTRODUCTION: This study evaluated the applicability of diffusion tensor imaging (DTI) of therapeutic ultrasound (US) and wrist splints in addition to clinical and electrophysiological assessments of patients with carpal tunnel syndrome (CTS). METHODS: This prospective study analyzed 41 patients (30 women, 11 men; 56 wrists) with CTS. Therapeutic US and wrist splints were performed for 3 and 4 weeks, respectively. Fractional anisotropy and the apparent diffusion coefficient (ADC) were evaluated in addition to a visual analog scale (VAS), symptom severity scale (SSS), functional status scale (FSS), and electrodiagnostic studies (EDX) before and after treatment. RESULTS: There were significant decreases in the mean ADC, VAS, SSS, FSS, and EDX after treatment. CONCLUSIONS: This study suggests that DTI parameters provide helpful information that complements clinical and electrophysiological assessments for evaluating the efficacy of nonsurgical treatment of patients with CTS.

The value of susceptibility weighted magnetic resonance imaging in evaluation of patients with familial cerebral cavernous angioma.

OBJECTIVES: We investigated the imaging features of Cavernous angioma (CA) lesions and the value of Susceptibility-weighted imaging (SWI) by comparing with T2*-weighted gradient echo (GRE) sequences in patients with familial CA disease. MATERIAL AND METHODS: We retrospectively evaluated 19 familial CA patients (8 men, 11 women; mean age, 36 years). T1-weighted, T2-weighted, T2*-weighted GRE, and SWI sequences were performed to all patients. The numbers of CA lesions seen on T2*-weighted GRE and SWI sequences were analyzed. The correlations between the numbers of lesions on both sequences with age were evaluated. CA lesions were classified according to the classification of Zabramski et al. RESULTS: The number of CA lesions was higher on SWI than T2*-weighted GRE significantly (P<.001). There was a significant strong correlation between the age of the patients and number of lesions in the cohort on T2*-weighted GRE (r = 0.81, P<0.001) and SWI (r = 0.85, P<0.001) sequences. Approximately 44% of the CA lesions which were detected only by SWI could not be categorized according to the classification of Zabramski et al. CONCLUSION: SWI can provide helpful additional information by determining the CA lesions more accurately than T2*-weighted GRE. Thus, routine clinical neuroimaging protocols should contain SWI to assess the true prevalence of lesions for optimal diagnosis and treatment. Moreover, this study show that the Zabramski classification is insufficient to identify all CA lesions, and a new type (type V) should be added to represent lesions that are seen on SWI but not on T2*-weighted GRE.