{"ID":2892860,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14670","arxiv_id":"2507.14670","title":"Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images","abstract":"Accurately predicting gene expression from histopathology images offers a scalable and non-invasive approach to molecular profiling, with significant implications for precision medicine and computational pathology. However, existing methods often underutilize the cross-modal representation alignment between histopathology images and gene expression profiles across multiple representational levels, thereby limiting their prediction performance. To address this, we propose Gene-DML, a unified framework that structures latent space through Dual-pathway Multi-Level discrimination to enhance correspondence between morphological and transcriptional modalities. The multi-scale instance-level discrimination pathway aligns hierarchical histopathology representations extracted at local, neighbor, and global levels with gene expression profiles, capturing scale-aware morphological-transcriptional relationships. In parallel, the cross-level instance-group discrimination pathway enforces structural consistency between individual (image/gene) instances and modality-crossed (gene/image, respectively) groups, strengthening the alignment across modalities. By jointly modeling fine-grained and structural-level discrimination, Gene-DML is able to learn robust cross-modal representations, enhancing both predictive accuracy and generalization across diverse biological contexts. Extensive experiments on public spatial transcriptomics datasets demonstrate that Gene-DML achieves state-of-the-art performance in gene expression prediction. The code and processed datasets are available at https://github.com/YXSong000/Gene-DML.","short_abstract":"Accurately predicting gene expression from histopathology images offers a scalable and non-invasive approach to molecular profiling, with significant implications for precision medicine and computational pathology. However, existing methods often underutilize the cross-modal representation alignment between histopathol...","url_abs":"https://arxiv.org/abs/2507.14670","url_pdf":"https://arxiv.org/pdf/2507.14670v3","authors":"[\"Yaxuan Song\",\"Jianan Fan\",\"Hang Chang\",\"Weidong Cai\"]","published":"2025-07-19T15:45:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":612023,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892860,"paper_url":"https://arxiv.org/abs/2507.14670","paper_title":"Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images","repo_url":"https://github.com/YXSong000/Gene-DML","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}