Back

Harmonization of large multi-site imaging datasets: Application to 10,232 MRIs for the analysis of imaging patterns of structural brain change throughout the lifespan

Pomponio, R.; Erus, G.; Habes, M.; Doshi, J.; Srinivasan, D.; Mamourian, E.; Bashyam, V.; Fan, Y.; Launer, L. J.; Masters, C. L.; Maruff, P.; Zhuo, C.; Nasrallah, I. M.; Völzke, H.; Johnson, S. C.; Fripp, J.; Koutsouleris, N.; Satterthwaite, T. D.; Wolf, D.; Gur, R.; Gur, R.; Morris, J.; Albert, M.; Grabe, H. J.; Resnick, S. M.; Bryan, R. N.; Wolk, D. A.; Shinohara, R. T.; Shou, H.; Davatzikos, C.

2019-09-26 bioinformatics
10.1101/784363 bioRxiv
Show abstract

As medical imaging enters its information era and presents rapidly increasing needs for big data analytics, robust pooling and harmonization of imaging data across diverse cohorts with varying acquisition protocols have become critical. We describe a comprehensive effort that merges and harmonizes a large-scale dataset of 10,232 structural brain MRI scans from participants without known neuropsychiatric disorder from 18 different studies that represent geographic diversity. We use this dataset and multi-atlas-based image processing methods to obtain a hierarchical partition of the brain from larger anatomical regions to individual cortical and deep structures and derive normative age trends of brain structure through the lifespan (3 to 96 years old). Critically, we present and validate a methodology for harmonizing this pooled dataset in the presence of nonlinear age trends. We provide a web-based visualization interface to generate and present the resulting age trends, enabling future studies of brain structure to compare their data with this normative reference of brain development and aging, and to examine deviations from normative ranges, potentially related to disease.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.