Abstract
Neuroimaging and genetic testing are two clinical references for nervous system diseases, offering complementary diagnostic information. However, integrating genomic and neuroimaging data for disease diagnosis is challenging due to cross-modality heterogeneity. Existing imaging–genetics approaches mainly encode genetic information as hard-coded labels, which lose the local sequence context around disease-associated variants. To address this limitation, we propose GeneFuse, a multimodal learning framework that aligns genetic representations from pretrained Genomic Language Models (GLMs) with neuroimaging features. GeneFuse integrates two components: (1) Genotype-Conditioned Feature Modulation (GCFM) to use genomic embeddings to modulate image feature maps; and (2) Uncertainty-aware Genomic Residual Fusion (U-GRF) for combining imaging and genotypic features with soft gating. We evaluate GeneFuse on early cognitive decline identification (NC vs. MCI) and dementia screening (NC vs. AD). In the APOE-centered setting, GeneFuse achieves AUROCs of 0.77 and 0.83, outperforming existing imaging–genetics fusion methods. These results indicate that GLM-derived genomic embeddings provide additional information to imaging.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MLMI_020.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=M5Asc6jdmW
BibTex
@InProceedings{TaoTia_Decoding_MICCAISAT2026,
author = { Tao, Tianli AND Wang, Ziyang AND Robinson, Emma AND Sparks, Rachel AND Zhang, Le},
title = { { Decoding Phenotypes: A Framework for Fusing Genomic Language Models and Neuroimaging } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17272},
month = {pending},
page = {pending}
}