On the filtering properties of classic-curvature and intensity-curvature functional images: applications in magnetic resonance imaging

Abstract

Eight subjects affected from various typologies of human brain tumour were scanned using the magnetic resonance imaging (MRI) modality known as fluid attenuated inversion recovery (FLAIR). The intensity-curvature measurement approaches called: 1) classic-curvature; 2) intensity-curvature functional; were calculated when fitting to the MRI data two mathematical models: 1) the bivariate cubic polynomial; 2) the bivariate linear function, respectively. The classic-curvature and the intensity-curvature functional show well behaved medical intensity-curvature maps of the human brain and they were used as filter masks to convolve the FLAIR data. As a result of the convolution, the filtered FLAIR images were obtained and analysed searching for evidence of feature extraction. The resulting filtered FLAIR images show: 1) well behaved presentation of the tumour; 2) well behaved delineation of the parenchyma surrounding the tumour; 3) well behaved separation between the tumour and the surrounding oedema; 4) clear and neat delineation of grey and white matter of the brain. The comparison between the filtered FLAIR and the filtered T2-weighted MRI images indicates that filtering FLAIR images yields a more effective highlight of the tumour structures than filtering the T2-weighted MRI.