Preoperative Radiomic Approach to Evaluate Tumor-Infiltrating CD8+ T Cells in Hepatocellular Carcinoma Patients Using Contrast-Enhanced Computed Tomography
- 51 Downloads
To help identify potential hepatocellular carcinoma (HCC) candidates for immunotherapies, we aimed to develop and validate a radiomics-based biomarker (Rad score) to predict the infiltration of tumor-infiltrating CD8+ T cells in HCC patients, and to evaluate the correlation of Rad score with tumor immune characteristics.
Overall, 142 HCC patients (n = 100 and n = 42 in the training and validation sets, respectively) were subjected to radiomic feature extraction. Imaging features and immunochemistry data of patients in the training set were subjected to elastic-net regularized regression analysis to predict the level of CD8+ T cell infiltration.
A Rad score for CD8+ T-cell infiltration, which contained seven variables, was developed and was validated in the validation set (area under the curve [AUC]: training set 0.751, 95% confidence interval [CI] 0.656–0.846; validation set 0.705, 95% CI 0.547–0.863). The decision curve indicated the clinical usefulness of the Rad score. A higher Rad score correlated with superior overall and disease-free survival outcomes (p = 0.012 and 0.0088, respectively). Using the pathological slides, we found that the Rad score positively correlated with the percentage of tumor-infiltrating lymphocytes (TILs; Spearman rho = 0.51, p < 0.0001). Moreover, the Rad score could also discriminate inflamed tumors from immune-desert and immune-excluded tumors (Kruskal–Wallis, p < 0.0001), and higher Rad scores could be found in patients with positive programmed cell death ligand 1 expression in tumor/immune cells, as well as those with positive programmed cell death protein 1 expression.
The newly developed Rad score was a powerful predictor of CD8+ T-cell infiltration, which could be useful in identifying potential HCC patients who can benefit from immunotherapies when validated in large-scale prospective cohorts.
BS and YZ designed the whole project and participated in result evaluation. HL, ML, and ZZ collected the clinical data of HCC candidates. ZZ and JC participated in ROI segmentation and image feature extractions. LX and ZW participated in performing IHC and pathological analysis. HL and ZZ performed image feature selection and radiomic model construction. HL and ZZ conducted the data analysis and wrote the manuscript. KY modified the structure of manuscript. All authors reviewed the manuscript and approved the final version.
This work was supported by Grants from the Natural Science Foundation of China (81872004, 81800564, 81770615, 81700555, 81672882 and 81502441), the Science and Technology Support Program of Sichuan Province (2017SZ0003, 2018SZ0115), and the Science and Technology Program of Tibet Autonomous Region (XZ201801-GB-02).
Haotian Liao, Zhen Zhang, Jie Chen, Mingheng Liao, Lin Xu, Zhenru Wu, Kefei Yuan, Bin Song, and Yong Zeng declare no competing interests in this work.
- 6.Rossi C, Gilhodes J, Maerevoet M, Herbaux C, Morschhauser F, Brice P, et al. Efficacy of chemotherapy or chemo-anti-PD-1 combination after failed anti-PD-1 therapy for relapsed and refractory Hodgkin lymphoma: a series from Lysa centers. Am J Hematol. 2018. https://doi.org/10.1002/ajh.25154.Google Scholar
- 13.Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278(2):563–77.Google Scholar
- 19.Zwanenburg A, Leger S, Vallières M, Löck S. Image biomarker standardisation initiative—feature definitions. 2016.Google Scholar