Quantifying mass effect deformation with structural radiomics in brain tumor patients

An apparatus comprising:

• a processor;
• a memory that stores a template image of a healthy brain;
• a set of circuits;
• and
• an interface that connects the processor, the memory, and the set of circuits, where the set of circuits comprises:
• an image acquisition circuit that acquires a radiological image of a region of tissue demonstrating glioblastoma multiforme (GBM);
• a delineation circuit that generates a segmented image by segmenting a tumor region from the background of the image;
• a pre-processing circuit that generates a pre-processed image by pre-processing the segmented image;
• a registration circuit that generates a registered image by registering the pre-processed image with the template image;
• and
• a deformation quantification circuit computes a set of differences between a position of a brain sub-structure represented in the registered image relative to the position of the brain sub-structure represented in the template image.

A method for quantifying mass effect deformation heterogeneity (MEDH) in region of tissue demonstrating Glioblastoma Multiforme, the method comprising:

• accessing a radiological image of the region of tissue, where the radiological image includes a plurality of voxels;
• computing a deformation field by registering the radiological image with an atlas of images of healthy regions of tissue, where the deformation field includes a voxel-wise deformation field vector in three planar dimensions;
• computing a magnitude of deformation for a member of the plurality of voxels using a Euclidean norm of scalar values of deformation orientations associated with the voxel-wise deformation field vector;
• and
• computing an MEDH value for the region of tissue based, at least in part, on the magnitude of deformation.