Meeting Banner
Abstract #2409

AUTOMATED DETECTION OF WHITE-MATTER AND CORTICAL LESIONS IN MP2RAGE AT ULTRA-HIGH FIELD USING A SINGLE SCAN

Mário João Fartaria 1,2,3, Alexis Roche1,2,3, Alexandra Şorega4, Kieran O'Brien5,6, Gunnar Krueger7, Bénédicte Maréchal1,2,3, Pascal Sati8, Daniel S. Reich8, Tobias Kober1,2,3, Meritxell Bach Cuadra2,3,9, and Cristina Granziera10,11

1Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland, 2Department of Radiology, Centre Hospitalier Universitaire Vaudois (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland, 3Signal Processing Laboratory (LTS 5), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland, 4Department of Radiology, Valais Hospital, Sion, Switzerland, 5Centre for Advanced Imaging, University of Queensland, Brisbane, Queensland, QC, Australia, 66. Siemens Healthcare Pty Ltd., Brisbane, Queensland, Australia, 7Siemens Medical Solutions USA, Boston, MA, United States, 8Translational Neuroradiology Section, Institute of Neurological Disorders and Stroke, National Institutes of Health (NIH), Bethesda, MD, United States, 9Medical Image Analysis Laboratory (MIAL), Centre d'Imagerie BioMédicale (CIBM), Lausanne, Switzerland, 10Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States, 11Department of Clinical Neurosciences, Centre Hospitalier Universitaire Vaudois (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland

Ultra-high-field Magnetic Resonance Imaging (7T MRI) has been shown to be a valuable tool to assess focal and diffuse pathology in multiple sclerosis (MS) patients, both in grey- and in white-matter. In this work, we developed and evaluated a method to automatically assess MS lesion load using magnetization-prepared two inversion-contrast rapid gradient-echo (MP2RAGE) MRI at 7T. The validation was conducted in a cohort of twenty MS patients from two research centers through a ground truth based on manual segmentations performed by a radiologist. Our single-sequence segmentation accurately detects visible white-matter and cortical lesions.

This abstract and the presentation materials are available to members only; a login is required.

Join Here

Abstract