SHEST: single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell-type prediction and spatial transcriptomics reconstruction
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag037 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Hoyeon Jeong und 4 weiteren Autor:innen. Beteiligte Einrichtung: Medical Research Institute, Sungkyunkwan University, 81 Irwon-Ro, 06351 Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Artificial Intelligence, Single-Cell Analysis, Eosine Yellowish-(YS), Lung Neoplasms. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National R&D Program for Cancer Control, Ministry of Health & Welfare, Republic of Korea, Samsung Medical Center.
Abstract (Originalsprache)
A comprehensive understanding of cancer progression requires integrating tissue morphology with spatial molecular profiles. We present SHEST, a multi-task profiling framework that leverages haematoxylin and eosin morphology to predict cellular composition and reconstruct spatial gene expression at single-cell resolution. SHEST employs a quadruple-tile input capturing nuclear and contextual information, combined with a neighbourhood-informed clustering algorithm to filter ambiguous cellular signals. It comprises a shared morphological encoder with two task-specific heads: a classifier for cell-type prediction and a reconstructor for gene expression. Multi-task optimization uses cross-entropy and zero-inflated negative binomial losses, specifically addressing the sparsity of spatial transcriptomic data. Evaluation on human lung adenocarcinoma datasets demonstrated high accuracy for the principal reciprocal constituents of the tumour–immune axis ($F_{1}$: 0.97 for tumour cells and 0.91 for lymphocytes). External validation confirmed its generalizability, revealing alveolar cells and their early neoplastic transitions. Reconstructed gene expression reproduced spatially resolved, cell-type-specific marker patterns—EPCAM in tumour cells, LTBP2 in fibroblasts, and CD3E in lymphocytes—recovering biologically coherent transcriptional architecture. SHEST also preserved distance-dependent spatial relationships and gene-level autocorrelation, reflecting the multicellular niche structure of the tumour microenvironment. By unifying cell-type identification, gene expression reconstruction, and spatial mapping within a single interpretable framework, SHEST provides a synergistic and cost-efficient bridge between histopathology and spatial transcriptomics. This approach facilitates comprehensive tissue characterization and forms a foundation for precision oncology through spatially informed, cell-level insights into tumour–immune ecosystems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Medical Research Institute, Sungkyunkwan University, 81 Irwon-Ro, 06351 Seoul, Republic of Korea.
- Research Institute for Future Medicine, Samsung Medical Center, 81 Irwon-Ro, 06351 Seoul, Republic of Korea.
- Department of Health Sciences and Technology, Samsung Advanced Institute for Health Sciences and Technology, 81 Irwon-Ro, 06351 Seoul, Republic of Korea.
- Department of Digital Health, Samsung Advanced Institute for Health Sciences and Technology, 81 Irwon-Ro, 06351 Seoul, Republic of Korea.
- Department of Pathology and Translational Genomics, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, 06351 Seoul, Republic of Korea.
ORCID-Profile: Hoyeon Jeong, Junghan Oh, Donggeon Lee, Jae Hwan Kang, Yoon-La Choi
Förderung
- National R&D Program for Cancer Control
- Ministry of Health & Welfare, Republic of Korea
- Samsung Medical Center
Zitieren
APA
Jeong, H., Oh, J., Lee, D., Kang, J. H., & Choi, Y. L. (2026). SHEST: single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell-type prediction and spatial transcriptomics reconstruction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag037
Vancouver
Jeong H, Oh J, Lee D, Kang JH, Choi YL. SHEST: single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell-type prediction and spatial transcriptomics reconstruction. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag037
BibTeX
@article{Jeong2026,
author = {Jeong, Hoyeon and Oh, Junghan and Lee, Donggeon and Kang, Jae Hwan and Choi, Yoon-La},
title = {SHEST: single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell-type prediction and spatial transcriptomics reconstruction},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag037}
}
EUVIMED