Detecting Brain Tumor using Machines Learning Techniques Based on Different Features Extracting Strategies.

BACKGROUND: Brain tumor is the leading cause of death worldwide. It is obvious that the chances of survival can be increased if the tumor is identified and properly classified at an initial stage. MRI (Magnetic Resonance Imaging) is one source of brain tumors detection tool and is extensively used in the diagnosis of brain to detect blood clots. In the past, many researchers developed Computer-Aided Diagnosis (CAD) systems that help the radiologist to detect the abnormalities in an efficient manner. OBJECTIVE: The aim of this research is to improve the brain tumor detection performance by proposing a multimodal feature extracting strategy and employing machine learning techniques. METHODS: In this study, we extracted multimodal features such as texture, morphological, entropybased, Scale Invariant Feature Transform (SIFT), and Elliptic Fourier Descriptors (EFDs) from brain tumor imaging database. The tumor was detected using robust machine learning techniques such as Support Vector Machine (SVM) with kernels: polynomial, Radial Base Function (RBF), Gaussian; Decision Tree (DT), and Naïve Bayes. Most commonly used Jack-knife 10-fold Cross- Validation (CV) was used for testing and validation of dataset. RESULTS: The performance was evaluated in terms of specificity, sensitivity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), False Positive Rate (FPR), Total Accuracy (TA), Area under the receiver operating Curve (AUC), and P-value. The highest performance of 100% in terms of Specificity, Sensitivity, PPV, NPV, TA, AUC using Naïve Bayes classifiers based on entropy, morphological, SIFT and texture features followed by Decision Tree classifier with texture features (TA=97.81%, AUC=1.0) and SVM polynomial kernel with texture features (TA=94.63%). The highest significant p-value was obtained using SVM polynomial with texture features (P-value 2.65e-104) followed by SVM RB with texture features (P-value 1.96e-98). CONCLUSION: The results reveal that Naïve Bayes followed by Decision Tree gives highest detection accuracy based on entropy, morphological, SIFT and texture features.

Knowledge, Attitude And Practice Of Common Cold And Its Management Among Doctors Of Pakistan.

BACKGROUND: Antibiotic misuse for upper respiratory tract infections such as the common cold is widespread in clinical practice. Excessive prescription of antibiotics by doctors has resulted in increased antimicrobial resistance. This led to our objective of determining the percentage of doctors in Pakistan prescribing antibiotics for the treatment of common cold and to know about their knowledge in preventing the spread of this disease. METHODS: It was a cross-sectional descriptive study, conducted in 9 cities of Pakistan including Rawalpindi, Islamabad, Peshawar, Lahore, Karachi, Faisalabad, Sargodha, Multan and D.G. Khan over a period of 03 months -from October to December, 2013. Questionnaire regarding the disease spread and its treatment was distributed among 300 randomly selected doctors in nine cities of Pakistan from both public and private sector. RESULTS: Eighteen percent of the doctors prescribe antibiotics for common cold. Only 113 (37.7%) doctors correctly responded that mean incubation period for common cold was 1-2 days. Two hundred and nine (69.7%) answered correctly that cold weather increases susceptibility to common cold. Only 84 (28%) responded correctly by choosing that regular and frequent hand-washing with good quality soaps was the most effective way to prevent spread of this disease in day-to-day life. CONCLUSIONS: Antibiotics are being prescribed for treatment of common cold by a large proportion of doctors. There is insufficient knowledge among our doctors regarding the factors which aggravate or alleviate common cold symptoms as well as the methods by which these infections can be prevented.

Endoscopic therapy for significant gastric outlet obstruction caused by a small pancreatic pseudocyst with a unique shape and location.

Large perigastric or periduodenal pseudocysts are a potential cause of gastric outlet obstruction, usually requiring interventional drainage of the pseudocysts. In contrary most of the small pseudocysts are asymptomatic and require no therapy. However, certain small pseudocysts can produce clinically significant problem depending on their location. Here we report a case of small pseudocyst (12.0 mm in width) with a unique shape and location causing significant Gastric outlet obstruction treated successfully with endoscopy.