Taming dimensionality in big neuroimaging data: Efficient orthonormal projective NMF via stochastic learning and data compression
Abdalla Bani, Sung Min Ha, Thomas Earnest, Braden Yang, Pan Xiao, John Lee, Janine Bijsterbosch, Aristeidis Sotiras · 2026
Read Taming dimensionality in big neuroimaging data: Efficient orthonormal projective NMF via stochastic learning and data compression by Abdalla Bani, Sung Min Ha, Thomas Earnest, Braden Yang, Pan Xiao, John Lee, Janine Bijsterbosch, Aristeidis Sotiras (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13556794.txt.
Description
Abdalla Bani and co-authors speed up a method for finding patterns in large brain scan data sets in a 2026 paper. The method splits brain maps into clear, non-overlapping patterns, which aids interpretation better than some standard tools. It had been too slow and memory-hungry for the huge cohorts now available.
Their version learns from small batches at a time, compresses the data at random, and varies the batches to cut repetition. On scans from a thousand people it matched the old method's quality at far lower cost. Applied to ten thousand UK Biobank scans, it found twenty patterns of shared structure. Many patterns linked to belly fat levels, with mostly negative links in both sexes. The tool opens large-scale brain studies that were impractical before.
Catalog record
| CREATOR | Abdalla Bani, Sung Min Ha, Thomas Earnest, Braden Yang, Pan Xiao, John Lee, Janine Bijsterbosch, Aristeidis Sotiras |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 75 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |