Computer vision on magnetic resonance images

Abstract

Abstract:We present an approach for the automated interpretation of transaxial cranial magnetic resonance images. After a brief outline of our notation and basic assumptions, the overall design consisting of a neurological inference engine, a set of image processing operators and a configurating component for these operators is presented.

Segmentation of Multispectral Magnetic Resonance Image Using Penalized Fuzzy Competitive Learning Network

“…[2] where d i,j is the Euclidean distance between the training sample x i and the class centroid w j .…”

“…For instance, it can be used to differentiate various tumor types in the uterus (1). Several studies on the automatic recognition of normal tissues in the brain and its surrounding tissues have been proposed (2,3). In general, a quantitative strategy for the analysis of brain morphometry requires a process to segment the image into different anatomic tissue components as a main step for the determination of volume shape, and location (4).…”

Unsupervised Brain Tumor Segmentation Using Knowledge-Based Fuzzy Techniques

“…Computer-based brain tumor segmentation has remained largely experimental work, with approaches including multi-spectral analysis 50,51,55,54,29,19 , edge detection 21, 1 2 , 45, 22, 6 0 , 5 9 , 2 , neural networks 35, 3 0 , 4 4 , and knowledge-based techniques 25,42,37,13,28 . Our e orts in 34,7,6 showed that a combination of knowledge-based techniques and multi-spectral analysis could e ectively detect pathology and label normal transaxial slices.…”