» Articles » PMID: 33244242

Pretreatment CT-Based Radiomics Signature As a Potential Imaging Biomarker for Predicting the Expression of PD-L1 and CD8+TILs in ESCC

Overview
Publisher Dove Medical Press
Specialty Oncology
Date 2020 Nov 27
PMID 33244242
Citations 24
Authors
Affiliations
Soon will be listed here.
Abstract

Background: The present study constructed and validated models to predict PD-L1 and CD8+TILs expression levels in esophageal squamous cell carcinoma (ESCC) patients using radiomics features and clinical factors.

Patients And Methods: This retrospective study randomly assigned 220 ESCC patients to a discovery dataset (n= 160) and validation dataset (n= 60). A total of 462 radiomics features were extracted from the segmentation of regions of interest (ROIs) based on pretreatment CT images of each patient. The LASSO algorithm was applied to reduce the dimensionality of the data and select features. A multivariable logistic regression analysis was adopted to build radiomics signatures. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the predictive accuracy of these models.

Results: There was no significant difference between the training and validation datasets for any clinical factors in patients with ESCC. The PD-L1 expression level correlated with the differentiation degree (= 0.011) and tumor stage (= 0.032). Smoking status (= 0.043) and differentiation degree (= 0.025) were associated with CD8+TILs expression levels. The radiomics signatures achieved good performance in predicting PD-L1 and CD8+TILs with AUCs= 0.784 and 0.764, respectively. The combined model showed a favorable predictive ability compared to radiomics signatures or clinical factors alone and improved the AUCs from 0.669 to 0.871 for PD-L1 and from 0.672 to 0.832 for CD8+TILs. These results were verified in the validation dataset with the AUCs of 0.817 and 0.795, respectively.

Conclusion: CT-based radiomics features have a potential value for classifying patients according to PD-L1 and CD8+TILs expression levels. The combination of clinical factors and radiomics signatures significantly improved the predictive performance in ESCC.

Citing Articles

Deep learning radiomics for the prediction of epidermal growth factor receptor mutation status based on MRI in brain metastasis from lung adenocarcinoma patients.

Cao P, Jia X, Wang X, Fan L, Chen Z, Zhao Y BMC Cancer. 2025; 25(1):443.

PMID: 40075375 PMC: 11899356. DOI: 10.1186/s12885-025-13823-8.


A CT-based interpretable deep learning signature for predicting PD-L1 expression in bladder cancer: a two-center study.

Han X, Guan J, Guo L, Jiao Q, Wang K, Hou F Cancer Imaging. 2025; 25(1):27.

PMID: 40065444 PMC: 11892212. DOI: 10.1186/s40644-025-00849-1.


Delta/pre-radiomics based on enhanced CT predicts complete response in locally advanced esophageal squamous cell carcinoma.

Zhu Y, Zhang Z, Bai G, Guo L, Xu Q, Zhang L Am J Transl Res. 2025; 17(1):162-177.

PMID: 39959224 PMC: 11826183. DOI: 10.62347/WQYO9624.


Predicting response to immunotherapy in oral squamous cell carcinoma via a CT-based radiomics model.

Ma Q, Ren J, Wang R, Yuan Y, Tao X BMC Med Imaging. 2024; 24(1):266.

PMID: 39375583 PMC: 11460018. DOI: 10.1186/s12880-024-01444-9.


CT-based deep learning radiomics biomarker for programmed cell death ligand 1 expression in non-small cell lung cancer.

Xu T, Liu X, Chen Y, Wang S, Jiang C, Gong J BMC Med Imaging. 2024; 24(1):196.

PMID: 39085788 PMC: 11292915. DOI: 10.1186/s12880-024-01380-8.


References
1.
Herbst R, Baas P, Kim D, Felip E, Perez-Gracia J, Han J . Pembrolizumab versus docetaxel for previously treated, PD-L1-positive, advanced non-small-cell lung cancer (KEYNOTE-010): a randomised controlled trial. Lancet. 2015; 387(10027):1540-1550. DOI: 10.1016/S0140-6736(15)01281-7. View

2.
Kudo T, Hamamoto Y, Kato K, Ura T, Kojima T, Tsushima T . Nivolumab treatment for oesophageal squamous-cell carcinoma: an open-label, multicentre, phase 2 trial. Lancet Oncol. 2017; 18(5):631-639. DOI: 10.1016/S1470-2045(17)30181-X. View

3.
Lin Z, Xu Y, Zhang Y, He Q, Zhang J, He J . The prevalence and clinicopathological features of programmed death-ligand 1 (PD-L1) expression: a pooled analysis of literatures. Oncotarget. 2016; 7(12):15033-46. PMC: 4924769. DOI: 10.18632/oncotarget.7590. View

4.
Yoon H, Sohn I, Cho J, Lee H, Kim J, Choi Y . Decoding Tumor Phenotypes for ALK, ROS1, and RET Fusions in Lung Adenocarcinoma Using a Radiomics Approach. Medicine (Baltimore). 2015; 94(41):e1753. PMC: 4616787. DOI: 10.1097/MD.0000000000001753. View

5.
Jiang M, Sun D, Guo Y, Guo Y, Xiao J, Wang L . Assessing PD-L1 Expression Level by Radiomic Features From PET/CT in Nonsmall Cell Lung Cancer Patients: An Initial Result. Acad Radiol. 2019; 27(2):171-179. DOI: 10.1016/j.acra.2019.04.016. View