| Autor: |
Jonsson BA; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.; University of Iceland, 101, Reykjavik, Iceland., Bjornsdottir G; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland., Thorgeirsson TE; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland., Ellingsen LM; University of Iceland, 101, Reykjavik, Iceland., Walters GB; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.; University of Iceland, 101, Reykjavik, Iceland., Gudbjartsson DF; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.; University of Iceland, 101, Reykjavik, Iceland., Stefansson H; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland., Stefansson K; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland. kstefans@decode.is.; University of Iceland, 101, Reykjavik, Iceland. kstefans@decode.is., Ulfarsson MO; deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland. mou@hi.is.; University of Iceland, 101, Reykjavik, Iceland. mou@hi.is. |
| Abstrakt: |
Machine learning algorithms can be trained to estimate age from brain structural MRI. The difference between an individual's predicted and chronological age, predicted age difference (PAD), is a phenotype of relevance to aging and brain disease. Here, we present a new deep learning approach to predict brain age from a T1-weighted MRI. The method was trained on a dataset of healthy Icelanders and tested on two datasets, IXI and UK Biobank, utilizing transfer learning to improve accuracy on new sites. A genome-wide association study (GWAS) of PAD in the UK Biobank data (discovery set: [Formula: see text], replication set: [Formula: see text]) yielded two sequence variants, rs1452628-T ([Formula: see text], [Formula: see text]) and rs2435204-G ([Formula: see text], [Formula: see text]). The former is near KCNK2 and correlates with reduced sulcal width, whereas the latter correlates with reduced white matter surface area and tags a well-known inversion at 17q21.31 (H2). |
