%0 Conference Proceedings %T Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training %+ E-Patient : Images, données & mOdèles pour la médeciNe numériquE (EPIONE) %+ Algorithms, models and methods for images and signals of the human brain (ARAMIS) %+ Institut du Cerveau = Paris Brain Institute (ICM) %A Wei, Wen %A Poirion, Emilie %A Bodini, Benedetta %A Durrleman, Stanley %A Ayache, Nicholas %A Stankoff, Bruno %A Colliot, Olivier %< avec comité de lecture %B MICCAI 2018 – 21st International Conference On Medical Image Computing & Computer Assisted Intervention %C Granada, Spain %V 11072 %8 2018-09-16 %D 2018 %R 10.1007/978-3-030-00931-1_59 %Z Computer Science [cs]/Artificial Intelligence [cs.AI] %Z Computer Science [cs]/Medical ImagingConference papers %X Multiple sclerosis (MS) is a demyelinating disease of the central nervous system (CNS). A reliable measure of the tissue myelin content is therefore essential to understand the physiopathology of MS, track progression and assess treatment efficacy. Positron emission tomography (PET) with [ 11 C]PIB has been proposed as a promising biomarker for measuring myelin content changes in-vivo in MS. However, PET imaging is expensive and invasive due to the injection of a radioactive tracer. On the contrary, magnetic resonance imaging (MRI) is a non-invasive, widely available technique, but existing MRI sequences do not provide, to date, a reliable, specific, or direct marker of either demyelination or remyelination. In this work, we therefore propose Sketcher-Refiner Gen-erative Adversarial Networks (GANs) with specifically designed adver-sarial loss functions to predict the PET-derived myelin content map from a combination of MRI modalities. The prediction problem is solved by a sketch-refinement process in which the sketcher generates the preliminary anatomical and physiological information and the refiner refines and generates images reflecting the tissue myelin content in the human brain. We evaluated the ability of our method to predict myelin content at both global and voxel-wise levels. The evaluation results show that the demyelination in lesion regions and myelin content in normal-appearing white matter (NAWM) can be well predicted by our method. The method has the potential to become a useful tool for clinical management of patients with MS. %G English %2 https://inria.hal.science/hal-01810822/document %2 https://inria.hal.science/hal-01810822/file/paper.pdf %L hal-01810822 %U https://inria.hal.science/hal-01810822 %~ CNRS %~ INRIA %~ INRIA-SOPHIA %~ INRIA-ROCQ %~ APHP %~ INRIASO %~ INRIA_TEST %~ TESTALAIN1 %~ ICM %~ INRIA2 %~ ARAMISLAB %~ UNIV-COTEDAZUR %~ SORBONNE-UNIVERSITE %~ SORBONNE-UNIV %~ SU-MEDECINE %~ SU-MED %~ OPAL %~ SU-TI %~ ALLIANCE-SU