EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal Deep Learning Integrating Tumor Radiomics and Mediastinal Adiposity Improves Survival Prediction in Non‐Small Cell Lung Cancer: A Prognostic Modeling Study

Ye Niu, Han-Bing Xie, Hao-Bo Jia, Lin Zhao, Le Liu, Ping-Ping Liu iD, Xue-Meng Li, Rui-Tao Wang iD, Yuan-Zhou Li

Cancer Medicine · 2025

DOI: 10.1002/cam4.71077 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancer Medicine, 2025. Verfasst von Ye Niu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, Harbin Medical University Cancer Hospital, Harbin Medical University, Harbin, Heilongjiang, China. Hauptthemen laut MEDLINE: Carcinoma, Non-Small-Cell Lung, Deep Learning, Lung Neoplasms, Adiposity. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Harbin Medical University Cancer Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Purpose Prognostic stratification in non‐small cell lung cancer (NSCLC) presents considerable challenges due to tumor heterogeneity. Emerging evidence has proposed that adipose tissue may play a prognostic role in oncological outcomes. This study investigates the integration of deep learning (DL)–derived computed tomography (CT) imaging biomarkers with mediastinal adiposity metrics to develop a multimodal prognostic model for postoperative survival prediction in NSCLC patients.

Methods

A retrospective cohort of 702 surgically resected NSCLC patients was analyzed. Tumor radiomic features were extracted using a DenseNet121 convolutional neural network architecture, while mediastinal fat area (MFA) was quantified through semiautomated segmentation using ImageJ software. A multimodal survival prediction model was developed through feature‐level fusion of DL‐extracted tumor characteristics and MFA measurements. Model performance was evaluated using Harrell's concordance index (C‐index) and receiver operating characteristic (ROC) analysis. Risk stratification was performed using an optimal threshold derived from training data, with subsequent Kaplan–Meier survival curve comparison between high‐ and low‐risk cohorts.

Results

The DL‐based tumor model achieved C‐indices of 0.787 (95% CI: 0.742–0.832) for disease‐free survival (DFS) and 0.810 (95% CI: 0.768–0.852) for overall survival (OS) in internal validation. Integration of MFA with DL‐derived tumor features yielded a multimodal model demonstrating enhanced predictive performance, with C‐indices of 0.823 (OS) and 0.803 (DFS). Kaplan–Meier analysis revealed significant survival divergence between risk‐stratified groups (log‐rank p < 0.05).

Conclusion

The multimodal fusion of DL‐extracted tumor radiomics and mediastinal adiposity metrics represents a significant advancement in postoperative survival prediction for NSCLC patients, demonstrating superior prognostic capability compared to unimodal approaches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, Non-Small-Cell LungDeep LearningLung NeoplasmsAdiposityMediastinumHumansMaleFemalePrognosisRetrospective StudiesMiddle AgedAgedTomography, X-Ray ComputedAdultRadiomics

Stichwörter der Autor:innen

computerized tomographydeep learningmediastinal fatnon‐small cell lung cancersurvival

Autor:innen und Institutionen

  • Department of Internal Medicine, Harbin Medical University Cancer Hospital, Harbin Medical University, Harbin, Heilongjiang, China.
  • The School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.
  • Department of Radiology, Harbin Medical University Cancer Hospital, Harbin Medical University, Harbin, Heilongjiang, China.

ORCID-Profile: Ping-Ping Liu, Rui-Tao Wang

Förderung

  • Harbin Medical University Cancer Hospital

Zitieren

APA

Niu, Y., Xie, H. B., Jia, H. B., Zhao, L., Liu, L., Liu, P. P., Li, X. M., Wang, R. T., & Li, Y. Z. (2025). Multimodal Deep Learning Integrating Tumor Radiomics and Mediastinal Adiposity Improves Survival Prediction in Non‐Small Cell Lung Cancer: A Prognostic Modeling Study. Cancer Medicine. https://doi.org/10.1002/cam4.71077

Vancouver

Niu Y, Xie HB, Jia HB, Zhao L, Liu L, Liu PP, et al. Multimodal Deep Learning Integrating Tumor Radiomics and Mediastinal Adiposity Improves Survival Prediction in Non‐Small Cell Lung Cancer: A Prognostic Modeling Study. Cancer Medicine. 2025. doi:10.1002/cam4.71077

BibTeX
@article{Niu2025,
  author = {Niu, Ye and Xie, Han-Bing and Jia, Hao-Bo and Zhao, Lin and Liu, Le and Liu, Ping-Ping and Li, Xue-Meng and Wang, Rui-Tao and Li, Yuan-Zhou},
  title = {Multimodal Deep Learning Integrating Tumor Radiomics and Mediastinal Adiposity Improves Survival Prediction in Non‐Small Cell Lung Cancer: A Prognostic Modeling Study},
  journal = {Cancer Medicine},
  year = {2025},
  doi = {10.1002/cam4.71077}
}
Kostenlos starten →