Abstract #0167

SUper-REsolution TRACTography (SURE-TRACT) pipeline using self-similarity between diffusional and anatomical images

Hong Hsi Lee^1,2, Ying Chia Lin^1,2, Gregory Lemberskiy^1,2, Benjamin Ades-aron^1,2, Steven Baete^1,2, Fernando E Boada^1,2, Els Fieremans^1,2, and Dmitry S Novikov^1,2

¹Center for Biomedical Imaging, New York University School of Medicine, New York, NY, United States, ²Center for Advanced Imaging Innovation and Research (CAI2R), New York University School of Medicine, New York, NY, United States

Here, we propose a model-free, self-similarity based SUper-REsolution TRACTography (SURE-TRACT) pipeline to increase the resolution of diffusion weighted images (DWIs) by translating the high spatial frequency details from the co-registered high-resolution anatomical image of the same subject. The generated high-resolution DWIs enable to identify fiber tracks and estimate biophysical parameters with greater anatomical detail. Validating our pipeline using Human Connectome Project data, we showed that the SURE-TRACT pipeline resolves partial volume effects, and is more flexible to different acquisition protocols than other recent machine-learning based algorithms.

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

Join Here