Automatic hookworm detection in wireless capsule endoscopy images - 2016 PROJECT TITLE : Automatic hookworm detection in wireless capsule endoscopy images - 2016 ABSTRACT: Wireless capsule endoscopy (WCE) has become a widely used diagnostic technique to look at inflammatory bowel diseases and disorders. As one amongst the most common human helminths, hookworm may be a kind of tiny tubular structure with grayish white or pinkish semi-transparent body, that is with a number of 600 million individuals infection around the world. Automatic hookworm detection could be a difficult task because of poor quality of pictures, presence of extraneous matters, advanced structure of gastrointestinal, and various appearances in terms of color and texture. This can be the primary few works to comprehensively explore the automatic hookworm detection for WCE pictures. To capture the properties of hookworms, the multi scale twin matched filter is 1st applied to detect the situation of tubular structure. Piecewise parallel region detection technique is then proposed to identify the potential regions having hookworm bodies. To discriminate the distinctive visual features for various parts of gastrointestinal, the histogram of average intensity is proposed to represent their properties. In order to accommodate the problem of imbalance knowledge, Rusboost is deployed to classify WCE images. Experiments on a various and massive scale dataset with 440 K WCE pictures demonstrate that the proposed approach achieves a promising performance and outperforms the state-of-the-art strategies. Moreover, the high sensitivity in detecting hookworms indicates the potential of our approach for future clinical application. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Diseases Medical Image Processing Biomedical Optical Imaging Object Detection Image Classification Medical Disorders Endoscopes Matched Filters Automatic brain tumor tissue detection based on hierarchical centroid shape descriptor in t1-weighted MRI images. - 2016 Locality sensitive deep learning for detection and Classification of nuclei in routine colon cancer Histology images - 2016