Generally, a discriminating a strategy based on a unique imaging modality is unable to appropriately differentiate normal from cancerous tissue, thus suggesting the use of a multi-modal view of the tissue for clinical assessment. Moreover, since many tumors, such as human glioma, are characterized by heterogeneous histopathology or have locally evolved to different stages of tumor progression, it is important to obtain a complete coverage of the lesion and its composing subregions. Recent work has proved that the combined multi-modal information yields improved discrimination of diseased tissue. However, its exploitation is still in its infancy since the fusion of dissimilar imaging data for classification and segmentation purposes is not a trivial task, as there is an inherent difference in information domains, dimensionality and scales .
File in questo prodotto:
Non ci sono file associati a questo prodotto.