Multi class disorder detection of magnetic resonance brain images using composite features and neural network.

Brain disorder recognition has becoming a promising area of study. In reality, some disorders share similar features and signs, making the task of diagnosis and treatment challenging. This paper presents a rigorous and robust computer aided diagnosis system for the detection of multiple brain abnormalities which can assist physicians in the diagnosis and treatment of brain diseases. In this system, we used energy of wavelet sub bands, textural features of gray level co-occurrence matrix and intensity feature of MR brain images. These features are ranked using Wilcoxon test. The composite features are classified using back propagation neural network. Bayesian regulation is adopted to find the optimal weights of neural network. The experimentation is carried out on datasets DS-90 and DS-310 of Harvard Medical School. To enhance the generalization capability of the network, fivefold stratified cross validation technique is used. The proposed system yields multi class disease classification accuracy of 100% in differentiating 90 MR brain images into 18 classes and 97.81% in differentiating 310 MR brain images into 6 classes. The experimental results reveal that the composite features along with BPNN classifier create a competent and reliable system for the identification of multiple brain disorders which can be used in clinical applications. The Wilcoxon test outcome demonstrates that standard deviation feature along with energies of approximate and vertical sub bands of level 7 contribute the most in achieving enhanced multi class classification performance results.

Development of computerized masticatory force measurement system.

PURPOSE: The aim of this study was to assess the Maximum Voluntary Bite Force (MVBF) in Indian population with normal occlusion and after treatment of mandibular angle fracture. MATERIALS AND METHODS: This paper discusses the development of a sensor fork with modified load cell and computer-based bite force measuring system that generates force profile on the computer. This is a powerful diagnostic tool in response to the needs of dentists seeking an accurate way to dynamically measure occlusion. RESULTS: This study was carried out to evaluate the maximum voluntary bite force generated by the patients after the treatment of mandibular angle fracture. The in vivo measurements were repeated on the following day, week and two months later. The measurements of the device were highly repeatable. CONCLUSION: This development provides the cost effective and handy equipment for bite force measurement further, if again sensor thickness reduced, we will be able to get more close results of forces that are exactly generated during the mastication process. Our study shows a significant difference in mean bite force efficiency between the all the treatment weeks and increased with time at α = 0.05 level. The gender difference was statistically significant in the male and female.

Normal limits of the electrocardiogram in Indians.

AIMS: The objective of the study was to develop normal limits of the ECG in an apparently healthy population of South Asians living in India. METHODS: Three centres contributed to recording 12 lead ECGs on identical digital electrocardiographs. Apparently healthy volunteers were recruited and ECGs were first transferred to a local database and then to Glasgow where all ECGs were analysed by the same University of Glasgow ECG Interpretation Program. RESULTS: A total of 963 individuals were recruited into the study (30.4% female) with an age range of 18-83 years. QRS duration was longer in males than females, QT interval was longer in females than males, and QRS voltages in general were higher in males than females and in younger compared to older individuals. CONCLUSION: Findings in general paralleled those in other populations and suggested that criteria for a white Caucasian population could be applied to a South Asian Indian population.

Effect of a multi-lead PCA approach on modified moving average method for T-wave alternans detection.

T-wave alternans, a beat-to-beat re-polarization pattern variation phenomenon, plays an important role in sudden cardiac death prediction. The proposed method modifies the currently available Modified Moving Average Method (MMAM) by a multi-lead principal component analysis (PCA) approach. Application of PCA will concentrate the alternans effect, which is supposed to be distributed on multiple leads in a single derived lead. MMAM is applied to the derived lead and alternans magnitude is measured. Results are compared with MMAM, implemented by the authors and by an open source tool, TWAnalyser. The TWA Physionet/CinC 2008 Challenge Database is used for testing. Performances are measured in terms of root mean square error (rmse) and correlation coefficients. The rmse is highest for TWAnalyser results and lowest for the proposed method. While the correlation coefficient is highest for the proposed method, 0.88, that for normal MMAM is 0.73 and for TWAnalyser is 0.75. The proposed multi-lead PCA approach provides improved performance of current MMAM.