Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks.

Fast diagnostic methods can control and prevent the spread of pandemic diseases like coronavirus disease 2019 (COVID-19) and assist physicians to better manage patients in high workload conditions. Although a laboratory test is the current routine diagnostic tool, it is time-consuming, imposing a high cost and requiring a well-equipped laboratory for analysis. Computed tomography (CT) has thus far become a fast method to diagnose patients with COVID-19. However, the performance of radiologists in diagnosis of COVID-19 was moderate. Accordingly, additional investigations are needed to improve the performance in diagnosing COVID-19. In this study is suggested a rapid and valid method for COVID-19 diagnosis using an artificial intelligence technique based. 1020 CT slices from 108 patients with laboratory proven COVID-19 (the COVID-19 group) and 86 patients with other atypical and viral pneumonia diseases (the non-COVID-19 group) were included. Ten well-known convolutional neural networks were used to distinguish infection of COVID-19 from non-COVID-19 groups: AlexNet, VGG-16, VGG-19, SqueezeNet, GoogleNet, MobileNet-V2, ResNet-18, ResNet-50, ResNet-101, and Xception. Among all networks, the best performance was achieved by ResNet-101 and Xception. ResNet-101 could distinguish COVID-19 from non-COVID-19 cases with an AUC of 0.994 (sensitivity, 100%; specificity, 99.02%; accuracy, 99.51%). Xception achieved an AUC of 0.994 (sensitivity, 98.04%; specificity, 100%; accuracy, 99.02%). However, the performance of the radiologist was moderate with an AUC of 0.873 (sensitivity, 89.21%; specificity, 83.33%; accuracy, 86.27%). ResNet-101 can be considered as a high sensitivity model to characterize and diagnose COVID-19 infections, and can be used as an adjuvant tool in radiology departments.

Evaluation of hemodynamic properties of cerebral venous drainage in patients with multiple sclerosis: a case-control study.

BACKGROUND: The purpose of this study was to compare patients with multiple sclerosis and healthy control subjects as regards hemodynamics of cerebral venous drainage. MATERIAL/METHODS: Between December 2012 and May 2013, 44 consecutive patients with multiple sclerosis and 44 age- and sex-matched healthy subjects underwent the B-mode, color Doppler, and duplex Doppler evaluations of the internal jugular vein (IJV) and vertebral vein. The following four parameters were investigated: IJV stenosis, reversal of postural control of the cerebral venous outflow pathways, absence of detectable blood flow in the IJVs and/or vertebral veins, and reflux in the IJVs and/or vertebral veins in the sitting or supine position. RESULTS: In the study group, IJV stenosis, postural control reversal of the cerebral venous outflow pathways, and absence of flow in the IJVs and/or vertebral veins were found in 3 (6.8%), 2 (4.5%), and 3 (6.8%) patients, respectively. In the control group, IJV stenosis (P=0.12), postural control reversal of the cerebral venous outflow pathways (P=0.50), and absence of flow (P=0.12) were not detected. Abnormal reflux was found neither in multiple sclerosis patients nor in healthy subjects. CONCLUSIONS: No significant difference in the cerebral venous drainage through the IJV or vertebral vein was found between patients with multiple sclerosis and healthy subjects within any of the investigated ultrasonographic parameters.

Assessment of ureterovesical jet dynamics in obstructed ureter by urinary stone with color Doppler and duplex Doppler examinations.

This study was designed to evaluate ureterovesical jet dynamics in obstructed ureter and to compare it with those of contralateral unobstructed side. Forty-six patients with diagnosis of ureteral stone, based on imaging findings in computed tomography were enrolled in this study. The gray-scale ultrasound exam from both kidneys and urinary bladder was performed. Then, ureterovesical jet characteristics including ureteral jet frequency, duration and peak velocity were assessed by color Doppler and duplex Doppler studies in both obstructed and unobstructed ureters by a radiologist, 15-30 min after oral hydration with 750-1,000 mL of water. When compared with contralateral normal side, the ureterovesical jet in obstructed ureter showed less frequency (0.59 vs. 3.04 jets/min; P < 0.05), shorter duration (1.24 vs. 5.26 s; P < 0.05) and lower peak velocity (5.41 vs. 32.09 cm/s; P < 0.05). The cut-off points of 1.5 jets/min, 2.5 s and 19.5 cm/s for difference of ureteral jet frequency, duration and peak velocity between obstructed and contralateral normal ureters yielded sensitivities of 97.8, 95.6 and 100 % and specificities of 87, 87.9 and 97.8 %, respectively for diagnosis of ureteral obstruction. Given the safety of Doppler study and significant differences in flow dynamics of obstructed versus unobstructed ureters, our findings demonstrated the utility of Doppler ultrasound examination as a useful adjunct to gray-scale ultrasound by improving the accuracy of ultrasound exam in diagnosis of ureteral obstruction.

Isolated humeral metastasis in uterine cervical cancer: a rare entity.

Bone metastasis in cancer of uterine cervix, especially in the form of isolated bone involvement is a rare manifestation. Herein, we report the first case of isolated humeral metastasis in a known case of locally advanced cervical cancer. A fifty-six-year old female presented with International Federation of Gynecology and Obstetrics (FIGO) Stage IV A squamous cell carcinoma of uterine cervix. She was treated with a combination of radiation and chemotherapy and then total abdominal hysterectomy with bilateral salpingo-oophorectomy. Seven months later, she developed an isolated lytic lesion in the left humerus, which turned out to be a bone metastatic lesion.