Comparison of 2D- and 3D-generated Radiomics feature maps in glioblastoma tissue subtypes segmented from DCE perfusion MRI
Suhail Parvaze P1, Tejas Shah2, Jaladhar Neelavalli 3, Anup Singh4, and Rakesh K Gupta5
1Philips Innovation Campus, Bangalore, India, 2BIU, Philips Innovation Campus, Bangalore, India, 3BIU, Philips Innovation Campus, Gurugram, India, 4Center for Biomedical Engineering, Indian Institute of Technology Delhi, Bangalore, India, 5Department of Radiology and Imaging, Fortis Memorial Research Institute, Gurugram, India
Radiomics based feature value analysis and feature maps especially for first order and texture based features are being thoroughly investigated for diagnostic usability and relevance. Radiomics based feature map generation using 2D and 3D modes on different tumor sub-regions of glioblastoma were performed. 2D-based feature maps depicted accurately the texture variation with respect to other images from the slice of interest, whereas in 3D based maps anatomy and pathology of the neighboring slices induced influence resulting in over depiction of pathology.
This abstract and the presentation materials are available to members only;
a login is required.