EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LIMPACAT: Multi-omics attention transformer for immune prediction in liver cancer using whole-slide imaging

Yen-Jung Chiu iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0339667 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Yen-Jung Chiu. Beteiligte Einrichtung: Department of Biomedical Engineering, Chang Gung University, Taoyuan, Taiwan. Hauptthemen laut MEDLINE: Liver Neoplasms, Tumor Microenvironment, Carcinoma, Hepatocellular. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Characterizing the tumor immune microenvironment from histopathological images offers opportunities for ex vivo immune profiling and prognostic assessment. However, the TCGA-LIHC dataset lacks direct immune cell composition data. Therefore, this study aims to introduce Liver Immune Microenvironment Prediction and Classification Attention Transformer (LIMPACAT), a deep learning framework that leverages whole-slide images (WSIs) to predict immune cell levels relevant to hepatocellular carcinoma (HCC) prognosis. Immune cell compositions were inferred using a deconvolution approach, with bulk RNA-seq profiles simulated from liver-specific single-cell RNA sequencing data and processed with multiple normalization methods. These inferred compositions served as supervision signals to train a multiple instance learning model with an attention transformer. LIMPACAT exhibited ~80% accuracy in classifying immune cell levels from HCC WSIs, showing strong concordance between model prediction and deconvolution-derived estimates. These findings suggest that WSIs can serve as a proxy for immune profiling, facilitating pathology-based tumor microenvironment assessment and supporting personalized therapeutic strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Liver NeoplasmsTumor MicroenvironmentCarcinoma, HepatocellularHumansDeep LearningMultiple-Instance Learning AlgorithmsMultiomicsPrognosis

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Chang Gung University, Taoyuan, Taiwan.

ORCID-Profile: Yen-Jung Chiu

Förderung

  • National Science and Technology Council

Zitieren

APA

Chiu, Y. J. (2026). LIMPACAT: Multi-omics attention transformer for immune prediction in liver cancer using whole-slide imaging. PLOS One. https://doi.org/10.1371/journal.pone.0339667

Vancouver

Chiu YJ. LIMPACAT: Multi-omics attention transformer for immune prediction in liver cancer using whole-slide imaging. PLOS One. 2026. doi:10.1371/journal.pone.0339667

BibTeX
@article{Chiu2026,
  author = {Chiu, Yen-Jung},
  title = {LIMPACAT: Multi-omics attention transformer for immune prediction in liver cancer using whole-slide imaging},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0339667}
}
Kostenlos starten →