Meeting Banner
Abstract #3431

Non-Negative Blind Source Separation Techniques for Describing Intratumoral Histopathological Tissue Properties Within MRSI Measurements

Anca Ramona Croitor Sava1, Sofie Van Cauter2, Diana Maria Sima1, Maria Osorio Garcia1, Uwe Himmelreich2, Sabine Van Huffel2

1Depart. Electrical Eng. ESAT/SCD, Katholieke Universiteit Leuven, Leuven, Belgium; 2Dept. Medical Diagnostic Sciences Biomedical NMR Unit, Katholieke Universiteit Leuven, Leuven, Belgium


The accuracy of Magnetic resonance spectroscopic imaging in differentiating and grading brain tumors is limited by significant variability of in vivo spectra as an effect of intra-tumoral heterogeneity. We propose a first screening between these intratumoral histopathological tissue properties, such as viable tumor cells, necrotic tissue or regions where the tumor infiltrates normal by quantifying their abundance within each MRSI voxel using a non-negative matrix factorization algorithm. Additionally, nosologic images are drawn based on the extracted abundance maps, reflecting the presence of necrosis, viable tumor cells or infiltrations in the MRSI grid.