Riemannian Manifold Learning for Cross-Modal Feature Alignment in Bioinformatics-Oriented Multimodal Medical Imaging
International Journal of Drug Delivery Technology · 22.04.2026 · 16 (16s)
DOI: 10.25258/ijddt.16.16s.20 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 22.04.2026. Verfasst von Dr Janarthanam Selvarasu und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Integrating medical images from diverse modalities—such as MRI, PET, and whole-slide histopathology—remains challenging because each technique generates data in fundamentally incompatible scales, resolutions, and physical principles. This study introduces a novel Riemannian manifold framework that models each modality as residing on its own curved geometric manifold. By computing geodesic alignments, the approach maps all modalities into a unified latent space while rigorously preserving local neighborhoods and global topology. A distinctive geometry-aware attention mechanism dynamically weighs each modality’s contribution based on its geodesic consistency with the others, enabling adaptive fusion. Features are then seamlessly transferred to a common tangent space via parallel transport, guaranteeing distortion-free integration. Evaluated on BraTS 2021, ADNI, and TCGA-GBM benchmarks, the method surpassed leading baselines, delivering a 4.7% Dice score gain over Cross-Modal Transformer (BraTS), 6.2% higher accuracy than Multimodal GCN (ADNI), and a 5.8% improved concordance index versus Hypergraph NN (TCGA-GBM). Ablation studies verified that geodesic alignment and learned attention closely mirror established clinical importance of individual sequences. These findings demonstrate that Riemannian geometry offers a mathematically principled foundation for robust multimodal fusion, paving the way for more reliable and interpretable AI-driven diagnostics.
Zitieren
APA
Selvarasu, D. J., Periyasamy, M. S., Gangadharappa, M. S. B., Boddu, P. R. S. K., & Manavalan, D. B. (2026). Riemannian Manifold Learning for Cross-Modal Feature Alignment in Bioinformatics-Oriented Multimodal Medical Imaging. International Journal of Drug Delivery Technology, 16(16s). https://doi.org/10.25258/ijddt.16.16s.20
Vancouver
Selvarasu DJ, Periyasamy MS, Gangadharappa MSB, Boddu PRSK, Manavalan DB. Riemannian Manifold Learning for Cross-Modal Feature Alignment in Bioinformatics-Oriented Multimodal Medical Imaging. International Journal of Drug Delivery Technology. 2026;16(16s). doi:10.25258/ijddt.16.16s.20
BibTeX
@article{Selvarasu2026,
author = {Selvarasu, Dr Janarthanam and Periyasamy, Ms. Sangeetha and Gangadharappa, Ms Sandhya Billahalli and Boddu, Prof. Raja Sarath Kumar and Manavalan, Dr Balachandramohan},
title = {Riemannian Manifold Learning for Cross-Modal Feature Alignment in Bioinformatics-Oriented Multimodal Medical Imaging},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {16s},
doi = {10.25258/ijddt.16.16s.20}
}
EUVIMED