Non-local MRI Library-Based Super-Resolution: Application to Hippocampus Subfield Segmentation

Jose V Romero (1) , Pierrick Coupé (2) , Jose V Manjón (1)

1 ITACA
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique

Magnetic Resonance Imaging (MRI) has become one of the most used techniques in research and clinical settings. One of the limiting factors of the MRI is the relatively low resolution for some applications. Although new high resolution MR sequences have been proposed recently, usually these acquisitions require long scanning times which is not always possible neither desirable. Recently, superresolution techniques have been proposed to alleviate this problem by inferring the underlying high resolution images from low resolution acquisitions. We present a new superresolution technique that takes benefit from the self-similarity properties of the images and the use of a high resolution image library. The proposed method is compared with related state-of-the-art methods showing a significant reconstruction improvement. Finally, we show the advantage of the proposed framework compared to classic interpolation when used for segmentation of hippocampus subfields.

Domaines: Imagerie médicale

Jose V Romero, Pierrick Coupé, Jose V Manjón. Non-local MRI Library-Based Super-Resolution: Application to Hippocampus Subfield Segmentation. Patch-Based Techniques in Medical Imaging (MICCAI), Oct 2016, Athènes, Greece. pp.68 - 75, ⟨10.1007/978-3-319-47118-1_9⟩. ⟨hal-01398781⟩