EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Intratumoural and Peritumoural Radiomics-Based Machine Learning Models for the Postoperative Survival Prediction in Oesophageal Squamous Cell Carcinoma

Zhi-Qiang Deng, Chen Yang, Zhong-Feng Yan, Yue Li, Hong-Tao Tang, Hou-Dong Zuo, Jun-Jie Zhang, Wen-Long Hu, Yu-Yang Mao, Dai-Yuan Ma, Kai-Yuan Jiang, Hao-Ji Yan und 1 weitere

Interdisciplinary CardioVascular and Thoracic Surgery · 12.03.2026 · 41 (3)

DOI: 10.1093/icvts/ivaf293 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Interdisciplinary CardioVascular and Thoracic Surgery, online erschienen am 10.03.2026. Verfasst von Zhi-Qiang Deng und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thoracic Surgery, West China Hospital, Sichuan University, Chengdu, 610041, China. Hauptthemen laut MEDLINE: Radiomics, Esophageal Neoplasms, Esophageal Squamous Cell Carcinoma, Esophagectomy. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Clinical Research Incubation Project of West China Hospital, Sichuan University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

This study aimed to develop and validate machine learning (ML) models to predict survival following oesophagectomy in oesophageal squamous cell carcinoma (ESCC) patients using intratumoural and peritumoural radiomic features.

Methods

A retrospective analysis was conducted on ESCC patients with preoperative contrast-enhanced computed tomography who underwent oesophagectomy from June 2016 to January 2020. Patients were randomly assigned to training and test sets (8:2 ratio). Radiomic features were independently extracted from intratumoural and peritumoural regions. Cox regression, random survival forests (RSF), and gradient boosting decision tree (GBDT) were used for modelling. The performance of models was evaluated by discrimination and calibration.

Results

The study included 443 patients, 354 in the training set and 89 in the test set. Peritumoural radiomic features predominated in the final selection, with 14 of 17 selected features originating from peritumoural region. The optimal GBDT model (the integrated area under the curve [iAUC]: 0.854; the integrated Brier score [iBS]: 0.160) using dual-region radiomic and clinical features outperformed other models, with a 1-year time-dependent area under the curve (tAUC) of 0.712 (95% CI, 0.655-0.738) and 3-year tAUC of 0.733 (95% CI, 0.655-0.805). It effectively stratified patients into high- and low-risk groups (P < .001).

Conclusions

ML models using intratumoural and peritumoural radiomic features showed potential for predicting postoperative survival in ESCC patients, with the optimal GBDT model demonstrating effective risk stratification.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadiomicsEsophageal NeoplasmsEsophageal Squamous Cell CarcinomaEsophagectomyMachine LearningTomography, X-Ray ComputedHumansRetrospective StudiesPredictive Learning ModelsFemaleMaleMiddle AgedAgedPredictive Value of TestsRisk AssessmentRisk FactorsBoosting Machine Learning AlgorithmsTreatment Outcome

Stichwörter der Autor:innen

machine learningoesophageal squamous cell carcinomaradiomicssurvival

Autor:innen und Institutionen

  • Department of Thoracic Surgery, West China Hospital, Sichuan University, Chengdu, 610041, China.
  • College of Medical Imaging, North Sichuan Medical College, Nanchong, 637000, China.
  • College of Clinical Medicine, North Sichuan Medical College, Nanchong, 637000, China.
  • Department of Cardiovascular Surgery, West China Hospital, Sichuan University, Chengdu, 610041, China.
  • Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, 637000, China.
  • Department of Oncology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, 637000, China.

ORCID-Profile: Dong Tian

Förderung

  • Clinical Research Incubation Project of West China Hospital, Sichuan University

Zitieren

APA

Deng, Z. Q., Yang, C., Yan, Z. F., Li, Y., Tang, H. T., Zuo, H. D., Zhang, J. J., Hu, W. L., Mao, Y. Y., Ma, D. Y., Jiang, K. Y., Yan, H. J., & Tian, D. (2026). Intratumoural and Peritumoural Radiomics-Based Machine Learning Models for the Postoperative Survival Prediction in Oesophageal Squamous Cell Carcinoma. Interdisciplinary CardioVascular and Thoracic Surgery, 41(3). https://doi.org/10.1093/icvts/ivaf293

Vancouver

Deng ZQ, Yang C, Yan ZF, Li Y, Tang HT, Zuo HD, et al. Intratumoural and Peritumoural Radiomics-Based Machine Learning Models for the Postoperative Survival Prediction in Oesophageal Squamous Cell Carcinoma. Interdisciplinary CardioVascular and Thoracic Surgery. 2026;41(3). doi:10.1093/icvts/ivaf293

BibTeX
@article{Deng2026,
  author = {Deng, Zhi-Qiang and Yang, Chen and Yan, Zhong-Feng and Li, Yue and Tang, Hong-Tao and Zuo, Hou-Dong and Zhang, Jun-Jie and Hu, Wen-Long and Mao, Yu-Yang and Ma, Dai-Yuan and Jiang, Kai-Yuan and Yan, Hao-Ji and Tian, Dong},
  title = {Intratumoural and Peritumoural Radiomics-Based Machine Learning Models for the Postoperative Survival Prediction in Oesophageal Squamous Cell Carcinoma},
  journal = {Interdisciplinary CardioVascular and Thoracic Surgery},
  year = {2026},
  volume = {41},
  number = {3},
  doi = {10.1093/icvts/ivaf293}
}
Kostenlos starten →