2024/11/22 by Wentao Huang, Meilong Xu, Huang, Wentao +20 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #AI in cancer detection #Artificial intelligence #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Consistency (knowledge bases) #Digital Imaging for Blood Diseases #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Materials science #Mathematics #Modal #Political science #Quantitative Methods (q-bio.QM) #Ranking (information retrieval) #Representation (politics) #Statistics #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2411.15076
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/11/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Spatial transcriptomics (ST) provides essential spatial context by mapping gene expression within tissue, enabling detailed study of cellular heterogeneity and tissue organization. However, aligning ST data with histology images poses challenges due to inherent spatial distortions and modality-specific variations. Existing methods largely rely on direct alignment, which often fails to capture complex cross-modal relationships. To address these limitations, we propose a novel framework that aligns gene and image features using a ranking-based alignment loss, preserving relative similarity across modalities and enabling robust multi-scale alignment. To further enhance the alignment's stability, we employ self-supervised knowledge distillation with a teacher-student network architecture, effectively mitigating disruptions from high dimensionality, sparsity, and noise in gene expression data. Extensive experiments on seven public datasets that encompass gene expression prediction, slide-level classification, and survival analysis demonstrate the efficacy of our method, showing improved alignment and predictive performance over existing methods.