Deep learning-based non-invasive prediction of PD-L1 status and immunotherapy survival stratification in esophageal cancer using [18F]FDG PET/CT
Authors:
- 14 August 2025
- journal article
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 53 (2) , 1015-1028
Abstract
This study aimed to develop and validate deep learning models using [18F]FDG PET/CT to predict PD-L1 status in esophageal cancer (EC) patients. Additionally, we assessed the potential of derived deep learning model scores (DLS) for survival stratification in immunotherapy. In this retrospective study, we included 331 EC patients from two centers, dividing them into training, internal validation, and external validation cohorts. Fifty patients who received immunotherapy were followed up. We developed four 3D ResNet10-based models-PET + CT + clinical factors (CPC), PET + CT (PC), PET (P), and CT (C)-using pre-treatment [18F]FDG PET/CT scans. For comparison, we also constructed a logistic model incorporating clinical factors (clinical model). The DLS were evaluated as radiological markers for survival stratification, and nomograms for predicting survival were constructed. The models demonstrated accurate prediction of PD-L1 status. The areas under the curve (AUCs) for predicting PD-L1 status were as follows: CPC (0.927), PC (0.904), P (0.886), C (0.934), and the clinical model (0.603) in the training cohort; CPC (0.882), PC (0.848), P (0.770), C (0.745), and the clinical model (0.524) in the internal validation cohort; and CPC (0.843), PC (0.806), P (0.759), C (0.667), and the clinical model (0.671) in the external validation cohort. The CPC and PC models exhibited superior predictive performance. Survival analysis revealed that the DLS from most models effectively stratified overall survival and progression-free survival at appropriate cut-off points (P < 0.05), outperforming stratification based on PD-L1 status (combined positive score ≥ 10). Furthermore, incorporating model scores with clinical factors in nomograms enhanced the predictive probability of survival after immunotherapy. Deep learning models based on [18F]FDG PET/CT can accurately predict PD-L1 status in esophageal cancer patients. The derived DLS can effectively stratify survival outcomes following immunotherapy, particularly when combined with clinical factors.Keywords
Funding Information
- National Natural Science Foundation of China (82402321)
- Guangdong Basic and Applied Basic Research Foundation (2024A1515010093)
- Guangdong Basic and Applied Basic Research Foundation (2023A1515111181)
- Nanfang Hospital Talent Introduction Foundation of Southern Medical University (2023G003)
- President Foundation of Nanfang Hospital, Southern Medical University (2022B029)
This publication has 29 references indexed in Scilit:
- Association of PD-L1 Expression and Other Variables With Benefit From Immune Checkpoint Inhibition in Advanced Gastroesophageal CancerJAMA Oncology, 2022
- From rough to precise: PD-L1 evaluation for predicting the efficacy of PD-1/PD-L1 blockadesFrontiers in Immunology, 2022
- Deep learning radiomics based on contrast-enhanced ultrasound images for assisted diagnosis of pancreatic ductal adenocarcinoma and chronic pancreatitisBMC Medicine, 2022
- A deep learning-based radiomic nomogram for prognosis and treatment decision in advanced nasopharyngeal carcinoma: A multicentre studyEBioMedicine, 2021
- PD-L1 as a biomarker of response to immune-checkpoint inhibitorsNature Reviews Clinical Oncology, 2021
- Pyridoxal kinase and poly(ADP-ribose) affect the immune microenvironment of locally advanced cancersOncoImmunology, 2021
- Randomized Phase III KEYNOTE-181 Study of Pembrolizumab Versus Chemotherapy in Advanced Esophageal CancerJournal of Clinical Oncology, 2020
- Pretreatment CT-Based Radiomics Signature as a Potential Imaging Biomarker for Predicting the Expression of PD-L1 and CD8+TILs in ESCCOncoTargets and Therapy, 2020
- Non-invasive decision support for NSCLC treatment using PET/CT radiomicsNature Communications, 2020
- Camrelizumab versus investigator's choice of chemotherapy as second-line therapy for advanced or metastatic oesophageal squamous cell carcinoma (ESCORT): a multicentre, randomised, open-label, phase 3 studyThe Lancet Oncology, 2020