Search

Nailfold capillaroscopy is a simple, non-invasive clinical aid used for the diagnosis of vascular dysfunction. The method proposed emphasizes on the USB Digital Microscope which is a cheaper and useful alternative to commercially available expensive videocapillaroscopes which produces high quality images. As the process of identifying anomalies in nailfold capillaries is a tedious and time-consuming process this article proposes a completely automated system to diagnose anomalies. The nailfold capillary images are pre-processed to highlight the important features and remove noise in the images. The processed images are then used to train machine learning models. This article then assays and compares the performance of Logistic Regression classifier, fully connected neural network, Convolutional Neural Network (CNN) and Random Forest classifiers by evaluating their classification accuracy, sensitivity and specificity. The results prove Logistic Regression to be most accurate with a low classification error rate of 10.64%. while, a substantial classification accuracy of 72% was obtained with a small dataset by using bottleneck features of a deep CNN.

Reduction in the capillary density in the nailfold region is frequently observed in patients suffering from Hypertension (Feng J, 2010). Loss of capillaries results in avascular regions which have been well characterized in many diseases (Mariusz, 2009). Nailfold capillary images need to be pre-processed so that noise can be removed, background can be separated and the useful parameters may be computed using image processing algorithms. Smoothing filters such as Gaussian, Median and Adaptive Median filters are compared using Mean Squared Error and Peak Signal-to-Noise Ratio. Otsu's thresholding is employed for segmentation. Connected Component Labeling algorithm is applied to calculate the number of capillaries per mm. This capillary density is used to identify rarefaction of capillaries and also the severity of rarefaction. Avascular region is detected by determining the distance between the peaks of the capillaries using Euclidian distance. Detection of rarefaction of capillaries and avascular regions can be used as a diagnostic tool for Hypertension and various other diseases.

Designing a real-time BCI device requires an Electroencephalogram (EEG) acquisition system and a signal processing system to process that acquired data. EEG acquisition boards available in market are expensive and they are required to be connected to computer for any processing work. Various low cost Digital Signal Processor (DSP) boards available in market come with internal Analog to Digital converters and peripheral interfaces. The idea is to design a low cost EEG amplifier board that can be used with these commercially available DSP boards. The analog data from EEG amplifier can be converted to digital data by DSP board and sent to computer via an interface for algorithm development and further control operations. EEG amplifiers are highly affected by noise from environment. Proper noise reduction techniques are implemented and simulated in circuit design. Each filter stage and noise reduction circuit is evaluated for a low noise design.