Multispectral analysis of multimodal images

Abstract

The MSA software appears to be a valuable tool for image analysis with multimodal images at hand. It readily gives a segmentation of image volumes that visually seems to be sensible. However, to really learn how to use MSA, it will be necessary to gain more insight into what tissues the different segments contain, and the upcoming work will therefore be focused on examining the tissues through for example histological sections.

Automatic glioma characterization from dynamic susceptibility contrast imaging: Brain tumor segmentation using knowledge‐based fuzzy clustering

“…Hence, identification of tumor volume and growth should be assessed from 3D data (or at least a stack of 2D data), not from a single ROI in a single MR slice. Alternatively, brain lesion delineation may be improved by multispectral segmentation of both anatomical and perfusion images (13) or by diffusion tensor imaging (39). However, in our experience, the relatively low spatial resolution of current perfusion and diffusion MR sequences do not improve the proposed segmentation routine with respect to pixel-by-pixel tumor area comparisons or presurgical glioma characterization from DSC imaging.…”

“…Recently, both supervised and unsupervised segmentation methods for identification of brain tissue structures have been proposed. Automatic tissue or tumor segmentation based on multi-spectral data analysis (12,13), neural networking (14,15), support vector machines (16,17) and knowledge-based fuzzy c-means (FCM) clustering techniques (18 -20) all show great promise. The potential advantages of automatic tumor segmentation include removal of intra-and inter-observer variations, time efficiency and standardized criteria's for tumor characterization (18).…”

Brain Tissue Classification from Multispectral MRI by Wavelet based Principal Component Analysis

“…In this work, similarity checking of reproduced brain tissues with corresponding ground truth is performed using (2).…”

“…T2-weighted sequence shows details of Cerebrospinal Fluid (CSF) and abnormalities, whereas FLAIR images suppress CSF effects to give hyperintense lesions details. Simultaneous analysis of these sequences to collect the prominent pathological information is a great challenge in clinical analysis [1,2]. Methods using multispectral approaches are useful in this context to improve the accuracy and consistency of the clinical results.…”

“…Classification results are highly dependent on the accuracy of extracted features. So, feature extraction and selection [2] has an important role in multispectral analysis. In Figure 1, f 1 , f 2 ...f k, represents the best features selected for training and classification to give final outputs, Class 1 , Class 2 ... Class m .…”