EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Derived Pathomic Features Predict NCIT Efficacy in Resectable Locally Advanced ESCC: Clinical Utility and Mechanistic Insights

Kunrui Zhu iD, Jie Tong, Yaqi Duan, Yiming Li iD, Yanqi Feng, Yuelin Han, Xiangtian Xiao, Zhuoyan Han, Shu Xia iD

Current Oncology · 2026

DOI: 10.3390/curroncol33030136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Current Oncology, 2026. Verfasst von Kunrui Zhu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Oncology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China. Hauptthemen laut MEDLINE: Esophageal Squamous Cell Carcinoma, Deep Learning, Neoadjuvant Therapy, Esophageal Neoplasms. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Chinese Society of Clinical Oncology, Beijing Xisike Clinical Oncology Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Esophageal squamous cell carcinoma (ESCC) is the predominant subtype of esophageal cancer, with poor outcomes following neoadjuvant chemoradiotherapy (NCRT). Neoadjuvant chemoimmunotherapy (NCIT) has emerged as a promising strategy, but reliable predictive biomarkers remain lacking. This study aimed to develop an AI-driven pathomic model for NCIT response prediction and explore its biological mechanisms.

Methods

We analyzed 269 H&E-stained whole-slide images (WSIs) from 198 ESCC patients (104 from Tongji Hospital, 94 from TCGA). Using ResNet152, we segmented WSIs into four tissue categories (tumor cells, stroma, lymphocytes, and necrosis), extracted spatially weighted pathomic features, and constructed the ECiT score via logistic regression. An integrated model combining the ECiT score with clinical variables (T stage, P53 status) was developed. Mechanistic analyses were performed using TCGA-ESCA and GSE160269 datasets.

Results

The integrated model achieved AUCs of 0.897 (training) and 0.809 (temporal validation), outperforming clinical (AUC = 0.624) and pathomic-only (AUC = 0.751) models. Mechanistically, a high ECiT score correlated with enhanced immune activation (elevated CD4+ memory T cell infiltration), while low scores were linked to endoplasmic reticulum (ER) stress-unfolded protein response (UPR) activation. EIF2S3 was identified as a key molecular mediator, correlating with three pathomic features, UPR activation, and poor prognosis.

Conclusions

This study may offer a preliminary indicator that could assist in personalized clinical decision-making. Correlative evidence suggests that the EIF2S3-mediated ER stress–UPR axis represents a potential candidate therapeutic target to overcome NCIT resistance, generating testable hypotheses to advance precision oncology for resectable locally advanced ESCC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Esophageal Squamous Cell CarcinomaDeep LearningNeoadjuvant TherapyEsophageal NeoplasmsImmunotherapyHumansMaleFemale

Stichwörter der Autor:innen

esophageal squamous cell carcinomamachine learningneoadjuvant chemoimmunotherapypathomics

Autor:innen und Institutionen

  • Institute of Oncology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China.
  • Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China.

ORCID-Profile: Kunrui Zhu, Yiming Li, Shu Xia

Förderung

  • National Natural Science Foundation of China
  • Chinese Society of Clinical Oncology
  • Beijing Xisike Clinical Oncology Research Foundation

Zitieren

APA

Zhu, K., Tong, J., Duan, Y., Li, Y., Feng, Y., Han, Y., Xiao, X., Han, Z., & Xia, S. (2026). Deep Learning-Derived Pathomic Features Predict NCIT Efficacy in Resectable Locally Advanced ESCC: Clinical Utility and Mechanistic Insights. Current Oncology. https://doi.org/10.3390/curroncol33030136

Vancouver

Zhu K, Tong J, Duan Y, Li Y, Feng Y, Han Y, et al. Deep Learning-Derived Pathomic Features Predict NCIT Efficacy in Resectable Locally Advanced ESCC: Clinical Utility and Mechanistic Insights. Current Oncology. 2026. doi:10.3390/curroncol33030136

BibTeX
@article{Zhu2026,
  author = {Zhu, Kunrui and Tong, Jie and Duan, Yaqi and Li, Yiming and Feng, Yanqi and Han, Yuelin and Xiao, Xiangtian and Han, Zhuoyan and Xia, Shu},
  title = {Deep Learning-Derived Pathomic Features Predict NCIT Efficacy in Resectable Locally Advanced ESCC: Clinical Utility and Mechanistic Insights},
  journal = {Current Oncology},
  year = {2026},
  doi = {10.3390/curroncol33030136}
}
Kostenlos starten →