Meeting Banner
Abstract #1862

Automatic detection of Multiple Sclerosis cortical lesions based on 3D-FLAIR and MP2RAGE sequences

Francesco La Rosa1,2, Ahmed Abdulkadir3, Mário João Fartaria1,2,4, Reza Rahmanzadeh5,6, Riccardo Galbusera5,6, Jean-Philippe Thiran1,2, Cristina Granziera5,6, and Meritxell Bach Cuadra1,2
1LTS5, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland, 2Radiology Department, Center for Biomedical Imaging, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, 3Universitäre Psychiatrische Dienste and University of Bern, Bern, Switzerland, 4Siemens Healthcare AG Switzerland, Lausanne, Switzerland, 5Neurologic Clinic and Policlinic, Departments of Medicine, Clinical Research and Biomedical Engineering, University Hospital Basel and University of Basel, Basel, Switzerland, 6Translational Imaging in Neurology (ThINk) Basel, Department of Medicine and Biomedical Engineering, University Hospital Basel and University of Basel, Basel, Switzerland

Multiple Sclerosis cortical lesions are not readily visible in conventional MRI, but they are clinically highly relevant and have been recently included in the MS diagnostic criteria. However, advanced MRI sequences such as the MP2RAGE are needed in order to identify them visually. In this work, we propose an automatic method based on a convolutional neural network to automatically detect cortical lesions. In a cohort of 84 patients with FLAIR and MP2RAGE acquisitions our framework achieves a 77% cortical lesion detection rate with a 26% lesion-wise false positive rate.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here