TY  - JOUR
AU  - Wulan, Naren
AU  - An, Lijun
AU  - Zhang, Chen
AU  - Kong, Ru
AU  - Chen, Pansheng
AU  - Bzdok, Danilo
AU  - Eickhoff, Simon B.
AU  - Holmes, Avram J.
AU  - Yeo, B. T. Thomas
TI  - Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching
JO  - Imaging neuroscience
VL  - 2
SN  - 2837-6056
CY  - Cambridge, MA
PB  - MIT Press
M1  - FZJ-2024-05517
SP  - 1 - 21
PY  - 2024
AB  - Individualized phenotypic prediction based on structural magnetic resonance imaging (MRI) is an important goal in neuroscience. Prediction performance increases with larger samples, but small-scale datasets with fewer than 200 participants are often unavoidable. We have previously proposed a “meta-matching” framework to translate models trained from large datasets to improve the prediction of new unseen phenotypes in small collection efforts. Meta-matching exploits correlations between phenotypes, yielding large improvement over classical machine learning when applied to prediction models using resting-state functional connectivity as input features. Here, we adapt the two best performing meta-matching variants (“meta-matching finetune” and “meta-matching stacking”) from our previous study to work with T1-weighted MRI data by changing the base neural network architecture to a 3D convolution neural network. We compare the two meta-matching variants with elastic net and classical transfer learning using the UK Biobank (N = 36,461), the Human Connectome Project Young Adults (HCP-YA) dataset (N = 1,017), and the HCP-Aging dataset (N = 656). We find that meta-matching outperforms elastic net and classical transfer learning by a large margin, both when translating models within the same dataset and when translating models across datasets with different MRI scanners, acquisition protocols, and demographics. For example, when translating a UK Biobank model to 100 HCP-YA participants, meta-matching finetune yielded a 136% improvement in variance explained over transfer learning, with an average absolute gain of 2.6% (minimum = –0.9%, maximum = 17.6%) across 35 phenotypes. Overall, our results highlight the versatility of the meta-matching framework.
LB  - PUB:(DE-HGF)16
C6  - 40800257
UR  - <Go to ISI:>//WOS:001531565300003
DO  - DOI:10.1162/imag_a_00251
UR  - https://juser.fz-juelich.de/record/1030924
ER  -