Fine-grain atlases of functional modes for fMRI analysis

• DOI: 10.1016/j.neuroimage.2020.117126
• Publication Date: 2020-07-13T16:06:02Z
• Authors: Kamalaker Dadi; Gaël Varoquaux; Antonia Machlouza...; Krzysztof J. Gorg...; Demian Wassermann; Bertrand Thirion; Arthur Mensch
• Keywords: Adult; Signal Processing (eess.SP); FOS: Computer and information sciences; [INFO.INFO-IM] Computer Science [cs]/Medical Imaging; Neurosciences. Biological psychiatry. Neuropsychiatry; Machine Learning (stat.ML); [STAT.OT]Statistics [stat]/Other Statistics [stat.ML]; [INFO] Computer Science [cs]; 03 medical and health sciences; Atlases as Topic; 0302 clinical medicine; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing; Statistics - Machine Learning; [INFO.INFO-IM]Computer Science [cs]/Medical Imaging; Brain imaging atlases; Connectome; FOS: Electrical engineering, electronic engineering, information engineering; Humans; [INFO]Computer Science [cs]; Electrical Engineering and Systems Science - Signal Processing; Brain Mapping; [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences; Brain; [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG]; Magnetic Resonance Imaging; Functional networks; Functional parcellations; Quantitative Biology - Neurons and Cognition; FOS: Biological sciences; Multi-resolution; Neurons and Cognition (q-bio.NC); Nerve Net; RC321-571

Population imaging markedly increased the size of functional-imaging datasets, shedding new light on the neural basis of inter-individual differences. Analyzing these large data entails new scalability challenges, computational and statistical. For this reason, brain images are typically summarized in a few signals, for instance reducing voxel-level measures with brain atlases or functional modes. A good choice of the corresponding brain networks is important, as most data analyses start from these reduced signals. We contribute finely-resolved atlases of functional modes, comprising from 64 to 1024 networks. These dictionaries of functional modes (DiFuMo) are trained on millions of fMRI functional brain volumes of total size 2.4TB, spanned over 27 studies and many research groups. We demonstrate the benefits of extracting reduced signals on our fine-grain atlases for many classic functional data analysis pipelines: stimuli decoding from 12,334 brain responses, standard GLM analysis of fMRI across sessions and individuals, extraction of resting-state functional-connectomes biomarkers for 2,500 individuals, data compression and meta-analysis over more than 15,000 statistical maps. In each of these analysis scenarii, we compare the performance of our functional atlases with that of other popular references, and to a simple voxel-level analysis. Results highlight the importance of using high-dimensional "soft" functional atlases, to represent and analyse brain activity while capturing its functional gradients. Analyses on high-dimensional modes achieve similar statistical performance as at the voxel level, but with much reduced computational cost and higher interpretability. In addition to making them available, we provide meaningful names for these modes, based on their anatomical location. It will facilitate reporting of results.