Perfusion analysis is a powerful tool to quantitatively characterize lesions. This can further be extended to differentiate lesions through comparison perfusion parameters. Typically there is overlap in perfusion parameters which makes it difficult to distinguish lesions. We demonstrate perfusion analysis combined with feature projection and classification enhances lesion detection by increasing separability and extracting features of the lesions simultaneously which can be used in automation of lesion detection.
This abstract and the presentation materials are available to members only; a login is required.