Gaussian-Filtered High-Frequency-Feature Trained Optimized BiLSTM Network for Spoofed-Speech Classification.

Voice-controlled devices are in demand due to their hands-free controls. However, using voice-controlled devices in sensitive scenarios like smartphone applications and financial transactions requires protection against fraudulent attacks referred to as "speech spoofing". The algorithms used in spoof attacks are practically unknown; hence, further analysis and development of spoof-detection models for improving spoof classification are required. A study of the spoofed-speech spectrum suggests that high-frequency features are able to discriminate genuine speech from spoofed speech well. Typically, linear or triangular filter banks are used to obtain high-frequency features. However, a Gaussian filter can extract more global information than a triangular filter. In addition, MFCC features are preferable among other speech features because of their lower covariance. Therefore, in this study, the use of a Gaussian filter is proposed for the extraction of inverted MFCC (iMFCC) features, providing high-frequency features. Complementary features are integrated with iMFCC to strengthen the features that aid in the discrimination of spoof speech. Deep learning has been proven to be efficient in classification applications, but the selection of its hyper-parameters and architecture is crucial and directly affects performance. Therefore, a Bayesian algorithm is used to optimize the BiLSTM network. Thus, in this study, we build a high-frequency-based optimized BiLSTM network to classify the spoofed-speech signal, and we present an extensive investigation using the ASVSpoof 2017 dataset. The optimized BiLSTM model is successfully trained with the least epoch and achieved a 99.58% validation accuracy. The proposed algorithm achieved a 6.58% EER on the evaluation dataset, with a relative improvement of 78% on a baseline spoof-identification system.

Presentation, treatment, and prognosis of colorectal adenosquamous carcinoma: A contemporary analysis of the surveillance, epidemiology, and end results database.

INTRODUCTION: Colorectal adenosquamous carcinoma (ASC) represents <0.1% of colorectal cancers. Due to its rarity, there is paucity of data regarding its prognosis and treatment compared to other colorectal cancers. The aim of the study was to evaluate presentation, treatment and prognosis of colorectal ASC in comparison to adenocarcinoma (AC) and squamous cell carcinoma (SCC). METHODS: Adult patients diagnosed with colorectal AC, SCC, and ASC between 2000 and 2017 were identified using Surveillance, Epidemiology, and End Results database. RESULTS: Among the 446,132 patients diagnosed with colorectal cancer, 0.06% had ASC and were more likely to present with higher T stage and distant metastases compared to AC and SCC (p < 0.001). Major surgery was the primary treatment for colonic ASC, while for rectal ASC, chemotherapy and/or radiation were mainly utilized. Localized and distant colonic ASC had an unadjusted 5-year cause-specific survival that was worse than AC, while rectal ASC had the worst survival across all stages. CONCLUSION: Colorectal ASC usually present with advanced stage and have overall worse prognosis. Standardization of treatment strategies may improve survival in colorectal ASC.

Recent Advancements in Fuzzy C-means Based Techniques for Brain MRI Segmentation.

BACKGROUND: Variations of image segmentation techniques, particularly those used for Brain MRI segmentation, vary in complexity from basic standard Fuzzy C-means (FCM) to more complex and enhanced FCM techniques. OBJECTIVE: In this paper, a comprehensive review is presented on all thirteen variations of FCM segmentation techniques. In the review process, the concentration is on the use of FCM segmentation techniques for brain tumors. Brain tumor segmentation is a vital step in the process of automatically diagnosing brain tumors. Unlike segmentation of other types of images, brain tumor segmentation is a very challenging task due to the variations in brain anatomy. The low contrast of brain images further complicates this process. Early diagnosis of brain tumors is indeed beneficial to patients, doctors, and medical providers. RESULTS: FCM segmentation works on images obtained from magnetic resonance imaging (MRI) scanners, requiring minor modifications to hospital operations to early diagnose tumors as most, if not all, hospitals rely on MRI machines for brain imaging. CONCLUSION: In this paper, we critically review and summarize FCM based techniques for brain MRI segmentation.

Does Sleeve Shape Make a Difference in Outcomes?

INTRODUCTION: Sleeve gastrectomy (SG) is one of the most common procedures performed for weight loss. Many seek the "perfect sleeve" with the notion that the type of calibrating device affects sleeve shape, and this in turn will affect outcomes and complications. Two major concerns after SG are amount of weight loss and acid reflux. Our aim was to determine if the various calibration methods could impact sleeve shape and thereby allow for better outcomes of weight loss and reflux. METHODS: A retrospective chart review was performed of 210 patients who underwent SG and had postoperative upper gastrointestinal (UGI) study from 2011 to 2015 in a single center by a single (fellowship-trained) bariatric surgeon. Data regarding demographics, calibrating devices and clinical outcomes at 1 year (weight loss and de novo acid reflux) were collected. UGIs were reviewed by two radiologists blinded to the clinical outcomes. Sleeve shape was classified according to a previously described classification as tubular, dumbbell, upper pouch, or lower pouch. The types of calibrating devices used to guide the sleeve size intraoperatively were endoscopy, large-bore orogastric tube, and fenestrated suction tube. RESULTS: One hundred ninety-nine patients met inclusion criteria (11 had no esophagram). Demographics revealed age 45.76 ± 10.6 years, BMI 47 ± 8.6 kg/m2, and 82% female. Calibration devices used were endoscopic guidance (7.6%), large bore orogastric tube (41.4%), and fenestrated suction tube (50.5%). Sleeve shape was reported as 32.6% tubular, 20.6% dumbbell, 39.2% lower pouch, and 7.5% upper pouch (100% interrater reliability). No correlation was seen with type of calibration used. Of patients, 62.0% had > 50% excess weight loss at 1 year. Twenty-three percent of patients remained on PPI at 1 year (of which 43.3% did not have reflux preoperatively). The lower pouch shape showed a trend toward less reflux and more weight loss. CONCLUSION: This study showed no clear association between uniformity of sleeve shape and the type of calibration device used. The study showed a trend toward decreased reflux and improved weight loss with the lower pouch shape, regardless of calibration device.

Ginger facilitates cholinergic activity possibly due to blockade of muscarinic autoreceptors in rat stomach fundus.

Ginger (Zingiber officinale) is a universally known food plant reputed for its medicinal use in gastrointestinal disorders as a prokinetic and laxative. We recently showed that 70% aqueous-methanolic extract of ginger (Zo.Cr) exhibits prokinetic activity in rats via activation of post-synaptic muscarinic M3 receptor in rat stomach fundus. In view of the physiological significance of pre-synaptic muscarinic M1 and M2 autoreceptors, this study was undertaken to further look into the possible mode of action of the prokinetic effect of ginger through inhibition of pre-synaptic muscarinic receptors. Isolated tissue bath experiments were performed with Sprague-Dawley rat stomach fundus strip preparations immersed in Kreb's solution at 37 degrees C. Carbachol (CCh) maximum responses (1 microM) were obtained in rat stomach fundus. Zo.Cr, given in multiple increasing bolus concentrations (0.01-0.1 mg/ml) 10 min prior to administration of CCh, potentiated the CCh peak responses showing that it is possibly inhibiting the pre-synaptic muscarinic receptors. Like wise, increasing bolus concentrations of pirenzepine (0.03-0.3 microM) and himbacine (0.01-0.03 microM), standard muscarinic M1 and M2 antagonists respectively, also potentiated the CCh responses. These results show that ginger, in addition to having a direct cholinergic agonistic effect on the post-synaptic M3 receptors, also has a possible inhibitory effect on pre-synaptic muscarinic autoreceptors, similar to standard muscarinic antagonists, thus reiterating the gastric stimulant effect of this age-old plant.