HiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning
Advanced Science · 2026
DOI: 10.1002/advs.202514351 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, 2026. Verfasst von Wei Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Tenth People's Hospital, Shanghai Key Laboratory of Signaling and Disease Research, School of Life Sciences and Technology, Tongji Universit…. Hauptthemen laut MEDLINE: Deep Learning, Transcriptome, Neoplasms, Gene Expression Profiling. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National key research and development program, Shanghai Jiao Tong University 2030 Initiative.
Abstract (Originalsprache)
Spatial transcriptomics (ST) provides valuable insights into the tumor microenvironment by integrating molecular features with spatial context; however, its clinical utility is limited by high costs. To address this, we develop a multi‐scale convolutional deep learning framework, HiST, which utilizes ST to learn the relationship between spatially resolved gene expression profiles (GEPs) and histological morphology. HiST accurately predicts tumor regions across multiple cancer types (e.g., breast cancer; area under the curve: 0.96), demonstrating high concordance with pathologist annotations. Moreover, HiST reconstructs spatially resolved GEPs from histological images with an average Pearson correlation coefficient of 0.74 across five cancer types, outperforming existing models by about two‐fold. These high‐fidelity spatial GEPs enable tumor heterogeneity assessment from histological images, including identification of tumor subtypes with distinct DNA copy number variations. We demonstrate the clinical utility of the predicted GEPs, which robustly stratify patient prognosis across five cancer types from The Cancer Genome Atlas (e.g., breast cancer; concordance index: 0.78). The predicted profiles further facilitate immunotherapy response prediction and enrichment analyses of relevant biological pathways and markers. Collectively, HiST achieves state‐of‐the‐art performance in spatial GEP reconstruction, providing a reliable molecular representation that enhances downstream tasks such as tumor profiling and clinical analyses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Shanghai Tenth People's Hospital, Shanghai Key Laboratory of Signaling and Disease Research, School of Life Sciences and Technology, Tongji University, Shanghai, China.
- Shanghai Institute of Immunology, Department of Immunology and Microbiology, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- UNSW BioMedical Machine Learning Lab (BML) School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, Australia.
- Department of Hepatobiliary Surgery, State Key Laboratory of Immune Response and Immunotherapy, Centre For Leading Medicine and Advanced Technologies of IHM, The First Affiliated Hospital of USTC, Division of Life Scien…
- Institute for Translational Medicine On Cell Fate and Disease, Shanghai Ninth People's Hospital, Key Laboratory of Cell Differentiation and Apoptosis of National Ministry of Education, Department of Pathophysiology, Sha…
ORCID-Profile: Youqiong Ye
Förderung
- National Natural Science Foundation of China
- National key research and development program
- Shanghai Jiao Tong University 2030 Initiative
- Research Funds of Centre for Leading Medicine and Advanced Technologies of IHM
- major project in the basic research field of Shanghai Science and Technology Innovation Action Plan
- China Postdoctoral Science Foundation
- National Basic Research Program of China
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
Zitieren
APA
Li, W., Zhang, D., Peng, E., Shen, S., Alinejad-Rokny, H., Liu, Y., Zheng, J., Jiang, C., & Ye, Y. (2026). HiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning. Advanced Science. https://doi.org/10.1002/advs.202514351
Vancouver
Li W, Zhang D, Peng E, Shen S, Alinejad-Rokny H, Liu Y, et al. HiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning. Advanced Science. 2026. doi:10.1002/advs.202514351
BibTeX
@article{Li2026,
author = {Li, Wei and Zhang, Dong and Peng, Eryu and Shen, Shijun and Alinejad-Rokny, Hamid and Liu, Yao and Zheng, Junke and Jiang, Cizhong and Ye, Youqiong},
title = {HiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.202514351}
}
EUVIMED