EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access

Integrating Lymph Node Metastasis and Programmed Death-Ligand 1 Prediction in Non–Small Cell Lung Cancer From a Single PET/CT Scan: Multicenter Radiomics Study

Wen Chen iD, Qiufang Liu iD, Huiling Peng iD, Jianping Zhang iD, Zhihao Chen iD, Silong Hu iD, Shaoli Song iD

JMIR Medical Informatics · 09.09.2026 · 14 · e86835-e86835

DOI: 10.2196/86835 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift JMIR Medical Informatics, online erschienen am 09.09.2026. Verfasst von Wen Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine, Fudan University Shanghai Cancer Center, Fudan University, Rd. Dongan 270, Shanghai, Shanghai, 2000027, China, 86 683…. Hauptthemen laut MEDLINE: Positron Emission Tomography Computed Tomography, Carcinoma, Non-Small-Cell Lung, Lymphatic Metastasis, B7-H1 Antigen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Preoperative stratification for non–small cell lung cancer (NSCLC) necessitates separate evaluations of lymph node metastasis (LNM) to guide surgical decisions and of programmed death-ligand 1 (PD-L1) expression to inform immunotherapy.

Objective

This study aimed to develop and validate an integrated diagnostic solution that could simultaneously predict both LNM status and PD-L1 expression status from a single, standard-of-care 18 F-fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography ( 18 F-FDG PET/CT) scan.

Methods

In this multicenter study, we segmented primary tumors and peritumoral 15-mm expansion regions from preoperative PET/CT scans of 273 patients (for LNM prediction) and 242 patients (for PD-L1 prediction). A total of 7868 radiomic features from intratumoral and peritumoral regions were extracted. Following rigorous feature selection, 2 independent models were developed using machine learning and tested on a temporal validation cohort (n=45). Model performance was benchmarked against clinicopathological models and nuclear medicine physicians.

Results

The integrated model for LNM prediction (PT-IPT-LR) achieved an area under the curve of 0.845 (95% CI 0.716‐0.973) in the temporal validation cohort, with a sensitivity of 0.765 (95% CI 0.518‐1.000) and a specificity of 0.786 (95% CI 0.602‐0.970). The model for PD-L1 expression (PT-IPT-SVM) achieved an area under the curve of 0.776 (95% CI 0.641‐0.911) in the temporal validation cohort, with a sensitivity of 0.800 (95% CI 0.609‐0.991) and a specificity of 0.650 (95% CI 0.401‐0.899). Decision curve analysis confirmed the clinical utility of both models. Critically, we found no significant correlation between the radiomic signatures of LNM and PD-L1, which validates our 2-model approach.

Conclusions

We present a radiomics framework that noninvasively integrates prediction of LNM and PD-L1 from a single preoperative PET/CT scan. This tool may enable preoperative stratification, potentially optimizing both surgical and systemic treatment planning for patients with NSCLC in a single step.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Positron Emission Tomography Computed TomographyCarcinoma, Non-Small-Cell LungLymphatic MetastasisB7-H1 AntigenLung NeoplasmsHumansRadiomicsFemaleMaleMiddle AgedAgedFluorodeoxyglucose F18ROC Curve

Stichwörter der Autor:innen

CTNSCLCPD-L1 expressionPETPET/CTcomputed tomographymachine learningnon–small cell lung cancerperitumoral regionpositron emission tomographyprogrammed death-ligand 1radiomics

Substanzen

B7-H1 AntigenCD274 protein, humanFluorodeoxyglucose F18

Autor:innen und Institutionen

  • Department of Nuclear Medicine, Fudan University Shanghai Cancer Center, Fudan University, Rd. Dongan 270, Shanghai, Shanghai, 2000027, China, 86 68388096, 86 68388096.
  • College of Biomedical Engineering, Yiwu Research Institute, Fudan University, Shanghai, Shanghai, China.
  • Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, Shanghai, China.
  • Center for Biomedical Imaging, Fudan University, Shanghai, Shanghai, China.
  • Key Laboratory of Nuclear Physics and Ion-beam Application (MOE), Fudan University, Shanghai, Shanghai, China.
  • Department of Nuclear Medicine, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital, Shanghai, Shanghai, China.

ORCID-Profile: Wen Chen, Qiufang Liu, Huiling Peng, Jianping Zhang, Zhihao Chen, Silong Hu, Shaoli Song

Zitieren

APA

Chen, W., Liu, Q., Peng, H., Zhang, J., Chen, Z., Hu, S., & Song, S. (2026). Integrating Lymph Node Metastasis and Programmed Death-Ligand 1 Prediction in Non–Small Cell Lung Cancer From a Single PET/CT Scan: Multicenter Radiomics Study. JMIR Medical Informatics, 14, e86835-e86835. https://doi.org/10.2196/86835

Vancouver

Chen W, Liu Q, Peng H, Zhang J, Chen Z, Hu S, et al. Integrating Lymph Node Metastasis and Programmed Death-Ligand 1 Prediction in Non–Small Cell Lung Cancer From a Single PET/CT Scan: Multicenter Radiomics Study. JMIR Medical Informatics. 2026;14:e86835-e86835. doi:10.2196/86835

BibTeX
@article{Chen2026,
  author = {Chen, Wen and Liu, Qiufang and Peng, Huiling and Zhang, Jianping and Chen, Zhihao and Hu, Silong and Song, Shaoli},
  title = {Integrating Lymph Node Metastasis and Programmed Death-Ligand 1 Prediction in Non–Small Cell Lung Cancer From a Single PET/CT Scan: Multicenter Radiomics Study},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e86835--e86835},
  doi = {10.2196/86835}
}
Kostenlos starten →