Multi-domain and Uni-domain Fusion for domain-generalizable fMRI-based phenotypic prediction
Motivation: Resting-state functional connectivity (RSFC) is widely used to predict phenotypes in individuals. However, predictive models may fail to generalize to new datasets due to differences in population, data collection, and processing across datasets. Goal(s): To resolve the dataset difference issue, we aimed to generalize knowledge from multiple diverse source datasets and translate the model to new target data. Approach: Here we proposed Multi-domain and Uni-domain Fusion (MUF) method that combines cross-domain learning and intra-domain learning, to capture both domain-general information and domain-specific information. Results: The results show that our MUF outperformed 4 strong baseline methods on 6 target datasets. Impact: Our MUF method is adept at addressing the challenges introduced by different population profiles, fMRI processing pipelines, and prediction tasks. We offer a robust and universal learning strategy for domain-generalization in fMRI-based phenotypic prediction.
Authors
- Lijun An (ORCID: https://orcid.org/0000-0003-1030-4625)
- Simon Bodo Eickhoff (ORCID: https://orcid.org/0000-0001-6363-2759)
- B.T. Thomas Yeo (ORCID: https://orcid.org/0000-0002-0119-3276)
- Shaoshi Zhang (ORCID: https://orcid.org/0000-0002-6352-9150)
- Pansheng Chen (ORCID: https://orcid.org/0009-0009-8881-8643)
- Leon Qi Rong Ooi (ORCID: https://orcid.org/0000-0002-3546-4580)
- Danilo Bzdok (ORCID: https://orcid.org/0000-0003-3466-6620)
- Ru Kong (ORCID: https://orcid.org/0000-0001-7842-0329)
- Jianxiao Wu (ORCID: https://orcid.org/0000-0002-4866-272X)
- Sidhant Chopra (ORCID: https://orcid.org/0000-0003-0866-3477)
- Naren Wulan (ORCID: https://orcid.org/0009-0005-3974-7528)
- Chen Zhang (ORCID: https://orcid.org/0000-0002-1579-0047)
- Avram J. Holmes (ORCID: https://orcid.org/0000-0001-6583-803X)
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2024-11-26
- DOI
- https://doi.org/10.58530/2024/2219
- Primary Topic
- Gene expression and cancer classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00