Neuroimage signature from salient keypoints is highly specific to individuals and shared by close relatives

• Published in: NeuroImage (Orlando, Fla.) Vol. 204; p. 116208
• Main Authors: Chauvin, Laurent, Kumar, Kuldeep, Wachinger, Christian, Vangel, Marc, de Guise, Jacques, Desrosiers, Christian, Wells, William, Toews, Matthew
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.01.2020; Elsevier Limited; Elsevier
• Subjects: Adolescent; Adult; Aged; Aged, 80 and over; Aging; Aging - pathology; Anatomy; Brain - anatomy & histology; Brain - diagnostic imaging; Cortex; Datasets; Datasets as Topic; Female; Humans; Identification; Individual variability; Investigations; Magnetic Resonance Imaging; Male; Medical imaging; Middle Aged; MRI; Neurodegenerative diseases; Neurodegenerative Diseases - diagnostic imaging; Neurodegenerative Diseases - pathology; Neuroimage analysis; Neuroimaging; Neuroimaging - methods; NMR; Nuclear magnetic resonance; Pattern Recognition, Automated - methods; Pharmaceutical industry; R&D; Research & development; Salient image keypoints; Siblings; Young Adult; Canada; Individual variability; Neuroimage analysis; Salient image keypoints; MRI
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2019.116208

Neuroimaging studies typically adopt a common feature space for all data, which may obscure aspects of neuroanatomy only observable in subsets of a population, e.g. cortical folding patterns unique to individuals or shared by close relatives. Here, we propose to model individual variability using a distinctive keypoint signature: a set of unique, localized patterns, detected automatically in each image by a generic saliency operator. The similarity of an image pair is then quantified by the proportion of keypoints they share using a novel Jaccard-like measure of set overlap. Experiments demonstrate the keypoint method to be highly efficient and accurate, using a set of 7536 T1-weighted MRIs pooled from four public neuroimaging repositories, including twins, non-twin siblings, and 3334 unique subjects. All same-subject image pairs are identified by a similarity threshold despite confounds including aging and neurodegenerative disease progression. Outliers reveal previously unknown data labeling inconsistencies, demonstrating the usefulness of the keypoint signature as a computational tool for curating large neuroimage datasets. •Efficient large scale analysis of whole brain images.•Introduction of a new pairwise brain similarity measure.•Correlation between brain similarity and genetic proximity across family members.•Automatic identification of mislabeled data in large public neuroimaging datasets.•Automatic identification of duplicate subjects across datasets.