ITSS vasculature volume and Radiomics Features from MR SWI: Performance in Glioma Grading
Rupsa Bhattacharjee1,2, Rakesh Kumar Gupta3, Rana Patir4, Sandeep Vaishya4, Suneeta Ahlawat5, and Anup Singh1,6
1Center for Biomedical Engineering, Indian Institute of Technology (IIT), Delhi, New Delhi, India, 2Department of Radiology & Biomedical Engineering, University of California, San Francisco (UCSF), San Francisco, CA, United States, 3Department of Radiology and Imaging, Fortis Memorial Research Institute, Gururam, India, 4Department of Neurosurgery, Fortis Memorial Research Institute, Gurugram, India, 5SRL Diagnostics, Fortis Memorial Research Institute, Gurugram, India, 6Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India
Majority of the glioma studies rely on using radiomic-features extracted only from conventional MRI and noticeably limited in SWI. Main objective of the current study is to evaluate the role of SWI in glioma grading aided by machine-learning (ML) methods, in terms of ITSS-vasculature-volume(IVV), radiomic features and by combining both. We conclude SWI to be the one of the useful sequences in the glioma-analysis as it contributes to calculate the IVV, which can singlehandedly improve the glioma grading. When IVV is combined with radiomic-analysis used in combination with PCA feature reduction and RF ML classifier, the performance is marginally improved.
This abstract and the presentation materials are available to members only;
a login is required.