5318 research outputs found
Sort by
Snake Segmentation and Cluster Analysis for identification of Multiple Sclerosis Lesions
Magnetic Resonance Imaging (MRI), allowing in-vivo detection of lesions, is today a crucial tool for diagnosis of Multiple Sclerosis (MS). Although the lesions alone are not sufficient for a diagnosis of MS, because they are similar to patterns detected in other neurological diseases, taking into account different radiological informations, MRI findings can often yield a high degree of confidence. We used a snake based procedure for segmentation of lesion then proposing a method based on Cluster Analysis to support clinicians in the diagnosis of MS. By identifying a minimum set of significant descriptors, our algorithm can help radiologist to distinguish MS plaques from other kinds of lesions
Wavelet algorithm for Magnetic Resonance Imaging
Compressing an image, namely reducing the amount of information needed to display the image itself, is a major issue in the development of applications, such as multimedia. Therefore the study of image compression approaches is of fundamental importance. In the present study, we developed a novel algorithm which is able to compress and to reconstruct an image by applying a wavelet transformation without compromising the diagnostic quality of the image itself. We showed that, according to the employed wavelet (Daubachies, Coiflet e Biorthogonal), the wavelet providing the best compression belongs to the third order of the db2 family, as indicated by the Compression Ratio (CR) is the 95%