Differentiation of glioblastomas and solitary brain metastases is clinically crucial for the prescription of patient management and assessment of prognosis. However, indistinguishable signs between two tumors on routine MRI leads to a high misdiagnosis rate. Neurite orientation dispersion and density imaging (NODDI) can not only estimate the intricacy of neurites in vivo but also provide data to illuminate pathology. We developed a series of radiomics models of NODDI parameter maps, routine MRI, combined routine MRI, and combined NODDI parameter maps to compare their performance in the identification of two tumors. Finally, the combined NODDI radiomics model obtained the best performance.
This abstract and the presentation materials are available to members only; a login is required.