Background: Big data is reshaping many aspects of healthcare. Brain MRI studies with over 1000 participants are often considered releative big sample size. Recent Nature, Science, PNAS and other studies used 10,000 or more publicly-shared brain MRIs, or 20,000-50,000 brain MRIs if combining public and private data. Two trends are clear: (a) while many studies used private data, public data is ideal for transparency and replication; (b) lifespan coverage is important, especially to include participants in both extremeties of ages in the 0-100 years range.
Our ongoing work: we compiled >95,000 brain MRIs from >71,000 healthy participants from public domains, coveraging 0-100 years of age [Pereira2021]. Using the first patch, we have derived early-childhood brain atlases [Ou2017, Sotardi2021], and built brain age predictors [He2020, He2021]. The age distribution is unbalanced but covers 0-100 years (figure below). Comprehensive non-MRI and MRI information exists for subsets of the data:
|
 |
Neuroscientific/Clinical Opportunities: Big-data, publicly-available, typically-developing, across-the-lifespan brain MRI and non-MRI data opens up tremendous opportunities. Examples include to study lifespan brain development, to early screen abnormalities as deviation from normal, to build age predictors, to quantify genotype-phenotype associations, to understand environement, lifestyle, socioeconomic factors for brain health, to create and maintain up-to-date knowledgebase, and more. Many opportunities were previously underpowered or even less practical. Public data also increases transparency and replication.
Technical Opportunities: Tremendous opportunities call for technical advancement. Open portal cloud computing is a key direction.
References
- [Pereira2021] DN Pereira*, S He*, JD Perez, T Ge, SU Morton, R Pienaar, NM Benson, RL Gollub, PE Grant, Y Ou. "Over 71,000 Healthy Brain MRIs are Publicly-Available across the Lifespan for Big-Data Studies", under review, 2021.
- [Ou2017] Y Ou, L Zöllei, K Retzepi, V Castro, SV Bates, S Pieper, KP Andriole, SN Murphy, RL Gollub, PE Grant, "Using Clinically-Acquired MRI to Construct Age-Specific ADC Atlases: Quantifying Spatiotemporal ADC Changes from Birth to 6 Years Old", Human Brain Mapping, 38(6): 3052-3068, (2017).
- [Sotardi21] S Sotardi, RL Gollub, SV Bates, R Weiss, SN Murphy, PE Grant, Y Ou, "Voxel-wise and Regional Brain Apparent Diffusion Coefficient Changes on MRI from Birth to 6 Years of Age", Radiology, 298(2): 415-424, (2021).
- [He2020] S He, RL Gollub, SN Murphy, JD Perez, S Prabhu, R Pienaar, RL Robertson, PE Grant, Y Ou. “Brain Age Estimation Using LSTM on Children's Brain MRI", IEEE International Symposium on Biomedical Imaging (ISBI), 420-423. (2020).
- [He2021] S He, D Pereira, JD Perez, RL Gollub, SN Murphy, S Prabhu, R Pienaar, RL Robertson, PE Grant, Y Ou. "Multi-channel Attention-Fusion Neural Network for Brain Age Estimation: Accuracy, Generality, and Interpretation with 16,705 Healthy MRIs across Lifespan", Medical Image Analysis, (2021).