Thrombus Detection Using Image Processing

Abstract

The powerful tool for increasing the reliability and reproducibility of disease diagnostics is image processing. In the hands of pathologists, image processing provides quantitative data to specialists from histological images which supplement the qualitative data. This project proposes the method for analyzing digitized images of MRI and detects the diseases which can cause the Heart Attack. The proposed work presents the method for detecting the disease like thrombus related to heart. Methods presented in this proposed work for detection of thrombus include steps like preprocessing, segmentation, feature extraction. At first the noise is been removed using Median Filter. Image is segmented using Region Growing method to detect the affected region. From this segmented region, the features are extracted using Histogram of Oriented Gradients (HOG) and Speeded up Robust Features (SURF).