relation: http://eprints.imtlucca.it/2767/
title: Dictionary-based Support Vector Machines for Unsupervised Ischemia Detection at Rest with CP-BOLD Cardiac MRI
creator: Bevilacqua, Marco
creator: Mukhopadhyay, Anirban
creator: Oksuz, Ilkay
creator: Rusu, Cristian
creator: Dharmakumar, Rohan
creator: Tsaftaris, Sotirios A.
subject: QA75 Electronic computers. Computer science
subject: RC Internal medicine
description: Cardiac Phase-resolved Blood-Oxygen-Level-Dependent (CP-BOLD) MRI has been recently demonstrated to detect an ongoing myocardial ischemia at rest, taking advantage of spatio-temporal patterns in myocardial signal intensities, which are modulated by the presence of disease. However, this approach does require significant post-processing to detect the disease and to this day only a few images of the acquisition are used coupled with fixed thresholds to establish biomarkers. We propose a threshold-free unsupervised approach, based on dictionary learning and one-class support vector machines, which can generate a probabilistic ischemia likelihood map.
type: Conference or Workshop Item
type: NonPeerReviewed
identifier:   Bevilacqua, Marco and Mukhopadhyay, Anirban and Oksuz, Ilkay and Rusu, Cristian and Dharmakumar, Rohan and Tsaftaris, Sotirios A.  Dictionary-based Support Vector Machines for Unsupervised Ischemia Detection at Rest with CP-BOLD Cardiac MRI.  In: ISMRM 23st Annual Meeting, 30 May - 5 Jun 2015, Toronto, Ontario, Canada       (Unpublished)