Automatic brain tumor tissue detection based on hierarchical centroid shape descriptor in t1-weighted MRI images. - 2016 PROJECT TITLE : Automatic brain tumor tissue detection based on hierarchical centroid shape descriptor in t1-weighted MRI images. - 2016 ABSTRACT: The brain tumor tissue detection permits to localize a mass of abnormal cells during a slice of Magnetic Resonance (MR). The automatization of this method is helpful for post processing of the extracted region of interest just like the tumor segmentation. So as to detect this abnormal growth of tissue in an image, this paper presents a completely unique theme that uses a two-step procedure; the k-means methodology and also the Hierarchical Centroid Form Descriptor (HCSD). The clustering stage is applied to discriminate structures based mostly on pixel intensity while the HCSD enable to pick out solely those having a specific shape. A bounding box is then automatically placed to delineate the region in which the tumor was found. Compared to the tumor delineation performed by an knowledgeable, a similarity measure of ninety onep.c was reached by using the Dice coefficient. The tests were meted out on 254 T1-weighted MRI pictures of fourteen patients with brain tumors. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Pattern Clustering Biomedical Mri Image Segmentation Medical Image Processing Object Detection Association between tumor heterogeneity and overall survival in patients with non-small cell lung cancer - 2016 Automatic hookworm detection in wireless capsule endoscopy images - 2016