影像组学与深度学习在非小细胞肺癌中预测PD-L1表达的应用与未来展望
Radiomics and Deep Learning in Predicting PD-L1 Expression in Non-Small Cell Lung Cancer: Applications and Future Prospects
DOI: 10.12677/acm.2026.162628, PDF,   
作者: 宋亿宁：绍兴文理学院医学院，浙江 绍兴；赵 丽*：绍兴市人民医院(绍兴文理学院附属第一医院)放射科，浙江 绍兴
关键词: 影像组学；深度学习；预测；非小细胞肺癌；程序性死亡配体1；Radiomics； Deep Learning； Forecast； Non-Small Cell Lung Cancer； Programmed Death Ligand-1
摘要: 肺癌是中国最常见的恶性肿瘤之一，其死亡率在各种恶性肿瘤中居首位，其中80%~85%为非小细胞肺癌(non-small cell lung cancer, NSCLC)。随着肿瘤免疫微环境研究的深入，免疫治疗发展迅速，程序性死亡配体1 (programmed death-ligand 1, PD-L1)作为关键的免疫检查点分子，对其表达的研究显得愈发重要。PD-L1是NSCLC患者的重要预后影响因素，因此无创且高效地预测PD-L1具有重要的临床价值。随着人工智能技术的迅速发展，人工智能联合临床及传统影像学构建综合PD-L1预测模型可为NSCLC患者精确评估风险并帮助医生制定个体化的治疗方案。本文主要从计算机断层扫描(computed tomography, CT)、正电子发射体层成像(positron emission tomography, PET)及磁共振成像(magnetic resonance imaging, MRI)三个方面对影像组学与深度学习(deep learning, DL)术前预测NSCLC PD-L1表达的研究进展予以综述，旨在为医生对NSCLC患者的准确评估、治疗决策以及预后判断提供指导。
Abstract: Lung cancer is one of the most common malignant tumors in China, with the highest mortality rate among various malignant tumors, of which 80%~85% are non-small cell lung cancer (NSCLC). With the deepening research on the tumor immune microenvironment, immunotherapy has developed rapidly. Programmed death-ligand 1 (PD-L1), as a key immune checkpoint molecule, has become increasingly important in research on its expression. PD-L1 is a significant prognostic factor for NSCLC patients, so non-invasive and efficient prediction of PD-L1 holds important clinical value. With the rapid development of artificial intelligence technology, integrating AI with clinical data and traditional imaging to build comprehensive PD-L1 prediction models can accurately assess risks for NSCLC patients and assist doctors in formulating personalized treatment plans. This paper mainly reviews the research progress of radiomics and deep learning (DL) in preoperative prediction of NSCLC PD-L1 expression from three perspectives: computed tomography (CT), positron emission tomography (PET), and magnetic resonance imaging (MRI), aiming to provide guidance for clinicians in accurate assessment, treatment decision-making, and prognostic evaluation of NSCLC patients.
文章引用：宋亿宁, 赵丽. 影像组学与深度学习在非小细胞肺癌中预测PD-L1表达的应用与未来展望[J]. 临床医学进展, 2026, 16(2): 2273-2279. https://doi.org/10.12677/acm.2026.162628

参考文献

[1] Xia, C., Dong, X., Li, H., Cao, M., Sun, D., He, S., et al. (2022) Cancer Statistics in China and United States, 2022: Profiles, Trends, and Determinants. Chinese Medical Journal, 135, 584-590. [Google Scholar] [CrossRef] [PubMed]
[2] Siegel, R.L., Miller, K.D., Wagle, N.S. and Jemal, A. (2023) Cancer Statistics, 2023. CA: A Cancer Journal for Clinicians, 73, 17-48. [Google Scholar] [CrossRef] [PubMed]
[3] American Cancer Society (2024) Key Statistics for Lung Cancer: How Common Is Lung Cancer.
https://www.cancer.org/cancer/types/lung-cancer/about/key-statistics.html
[4] John, N., Schlintl, V., Sassmann, T., Lindenmann, J., Fediuk, M., Wurm, R., et al. (2024) Longitudinal Analysis of PD-L1 Expression in Patients with Relapsed NSCLC. Journal for ImmunoTherapy of Cancer, 12, e008592. [Google Scholar] [CrossRef] [PubMed]
[5] Cui, J., Li, Y., Yang, Y., Yang, H., Dong, J., Xiao, Z., et al. (2024) Tumor Immunotherapy Resistance: Revealing the Mechanism of PD-1/PD-L1-Mediated Tumor Immune Escape. Biomedicine & Pharmacotherapy, 171, Article ID: 116203. [Google Scholar] [CrossRef] [PubMed]
[6] Lambin, P., Leijenaar, R.T.H., Deist, T.M., Peerlings, J., de Jong, E.E.C., van Timmeren, J., et al. (2017) Radiomics: The Bridge between Medical Imaging and Personalized Medicine. Nature Reviews Clinical Oncology, 14, 749-762. [Google Scholar] [CrossRef] [PubMed]
[7] Gillies, R.J., Kinahan, P.E. and Hricak, H. (2016) Radiomics: Images Are More than Pictures, They Are Data. Radiology, 278, 563-577. [Google Scholar] [CrossRef] [PubMed]
[8] Ma, J., Song, J., Han, L., Zhou, W., Meng, L., Li, J., et al. (2024) Analysis of PD-1/PD-L1 Variations in Lung Cancer and Association with Immunotherapeutic Efficacy and Prognosis: A Nonrandomized Controlled Trial. Clinics, 79, Article ID: 100395. [Google Scholar] [CrossRef] [PubMed]
[9] Zheng, X., He, B., Hu, Y., Ren, M., Chen, Z., Zhang, Z., et al. (2022) Diagnostic Accuracy of Deep Learning and Radiomics in Lung Cancer Staging: A Systematic Review and Meta-Analysis. Frontiers in Public Health, 10, Article 938113. [Google Scholar] [CrossRef] [PubMed]
[10] Qian, L., Wu, T., Kong, S., Lou, X., Jiang, Y., Tan, Z., et al. (2024) Could the Underlying Biological Basis of Prognostic Radiomics and Deep Learning Signatures Be Explored in Patients with Lung Cancer? A Systematic Review. European Journal of Radiology, 171, Article ID: 111314. [Google Scholar] [CrossRef] [PubMed]
[11] Evangelista, L., Fiz, F., Laudicella, R., Bianconi, F., Castello, A., Guglielmo, P., et al. (2023) PET Radiomics and Response to Immunotherapy in Lung Cancer: A Systematic Review of the Literature. Cancers, 15, Article 3258. [Google Scholar] [CrossRef] [PubMed]
[12] Forte, G.C., Altmayer, S., Silva, R.F., Stefani, M.T., Libermann, L.L., Cavion, C.C., et al. (2022) Deep Learning Algorithms for Diagnosis of Lung Cancer: A Systematic Review and Meta-Analysis. Cancers, 14, Article 3856. [Google Scholar] [CrossRef] [PubMed]
[13] Palani, M., Rajagopal, S. and Chintanpalli, A.K. (2024) A Systematic Review on Feature Extraction Methods and Deep Learning Models for Detection of Cancerous Lung Nodules at an Early Stage—The Recent Trends and Challenges. Biomedical Physics & Engineering Express, 11, Article ID: 012001. [Google Scholar] [CrossRef] [PubMed]
[14] Liang, H., Hu, M., Ma, Y., Yang, L., Chen, J., Lou, L., et al. (2023) Performance of Deep-Learning Solutions on Lung Nodule Malignancy Classification: A Systematic Review. Life, 13, Article 1911. [Google Scholar] [CrossRef] [PubMed]
[15] Wen, Q., Yang, Z., Dai, H., Feng, A. and Li, Q. (2021) Radiomics Study for Predicting the Expression of PD-L1 and Tumor Mutation Burden in Non-Small Cell Lung Cancer Based on CT Images and Clinicopathological Features. Frontiers in Oncology, 11, Article 620246. [Google Scholar] [CrossRef] [PubMed]
[16] Liu, Z., Yao, Y., Zhao, M., Zhao, Q., Xue, J., Huang, Y., et al. (2025) Radiomics Models Derived from Arterial-Phase-Enhanced CT Reliably Predict Both PD-L1 Expression and Immunotherapy Prognosis in Non-Small Cell Lung Cancer: A Retrospective, Multicenter Cohort Study. Academic Radiology, 32, 493-505. [Google Scholar] [CrossRef] [PubMed]
[17] Sun, X.M., Zhang, L.X., Liu, H.X., et al. (2025) Value of Contrast-Enhanced CT-Based Radiomics Model in Predicting PD-L1 Expression in Lung Adenocarcinoma. Radiologic Practice, 40, 962-968.
[18] Yamagata, K., Yanagawa, M., Hata, A., Ogawa, R., Kikuchi, N., Doi, S., et al. (2024) Three-Dimensional Iodine Mapping Quantified by Dual-Energy CT for Predicting Programmed Death-Ligand 1 Expression in Invasive Pulmonary Adenocarcinoma. Scientific Reports, 14, Article No. 18310. [Google Scholar] [CrossRef] [PubMed]
[19] Wu, L., Lou, X., Kong, N., Xu, M. and Gao, C. (2022) Can Quantitative Peritumoral CT Radiomics Features Predict the Prognosis of Patients with Non-Small Cell Lung Cancer? A Systematic Review. European Radiology, 33, 2105-2117. [Google Scholar] [CrossRef] [PubMed]
[20] Bao, X., Peng, Q., Bian, D., Ni, J., Zhou, S., Zhang, P., et al. (2025) Short-Term Intra-and Peri-Tumoral Spatiotemporal CT Radiomics for Predicting Major Pathological Response to Neoadjuvant Chemoimmunotherapy in Non-Small Cell Lung Cancer. European Radiology, 35, 6052-6064. [Google Scholar] [CrossRef] [PubMed]
[21] Liu, P.M., Feng, B., Shi, J.F., Feng, H.J., Hu, Z.J., Chen, Y.H., et al. (2023) A Deep-Learning Model Using Enhanced Chest CT Images to Predict PD-L1 Expression in Non-Small-Cell Lung Cancer Patients. Clinical Radiology, 78, e689-e697. [Google Scholar] [CrossRef] [PubMed]
[22] Tian, P., He, B., Mu, W., Liu, K., Liu, L., Zeng, H., et al. (2021) Assessing PD-L1 Expression in Non-Small Cell Lung Cancer and Predicting Responses to Immune Checkpoint Inhibitors Using Deep Learning on Computed Tomography Images. Theranostics, 11, 2098-2107. [Google Scholar] [CrossRef] [PubMed]
[23] Huang, X., Huang, X., Xie, Y., Wang, K., Bai, H., Ning, R., et al. (2025) Integrative Habitat Analysis and Multi-Instance Deep Learning for Predictive Model of PD-1/PD-L1 Immunotherapy Efficacy in NSCLC Patients: A Dual-Center Retrospective Study. BMC Medical Imaging, 25, Article No. 288. [Google Scholar] [CrossRef] [PubMed]
[24] Shao, J., Ma, J., Zhang, S., Li, J., Dai, H., Liang, S., et al. (2022) Radiogenomic System for Non-Invasive Identification of Multiple Actionable Mutations and PD-L1 Expression in Non-Small Cell Lung Cancer Based on CT Images. Cancers, 14, Article 4823. [Google Scholar] [CrossRef] [PubMed]
[25] Zhao, X., Zhao, Y., Zhang, J., Zhang, Z., Liu, L. and Zhao, X. (2023) Predicting PD-L1 Expression Status in Patients with Non-Small Cell Lung Cancer Using [18F]FDG PET/CT Radiomics. EJNMMI Research, 13, Article No. 4. [Google Scholar] [CrossRef] [PubMed]
[26] Ji, Y., Cui, K., Zhang, J., Wang, J., Dai, Z., Cui, Y., et al. (2025) Noninvasive Prediction of Programmed Cell Death Protein-Ligand 1 Expression in Locally Advanced Non-Small Cell Lung Cancer by 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography-Based Metabolic Habitats: A Multicenter Radiomic and Biological Study. Annals of Surgical Oncology, 32, 10094-10107. [Google Scholar] [CrossRef] 
[27] Liang, C., Zheng, M., Zou, H., Han, Y., Zhan, Y., Xing, Y., et al. (2024) Deep Learning-Based Image Analysis Predicts PD-L1 Status from 18F-FDG PET/CT Images in Non-Small-Cell Lung Cancer. Frontiers in Oncology, 14, Article 1402994. [Google Scholar] [CrossRef] [PubMed]
[28] Mu, W., Jiang, L., Shi, Y., Tunali, I., Gray, J.E., Katsoulakis, E., et al. (2021) Non-Invasive Measurement of PD-L1 Status and Prediction of Immunotherapy Response Using Deep Learning of PET/CT Images. Journal for ImmunoTherapy of Cancer, 9, e002118. [Google Scholar] [CrossRef] [PubMed]
[29] Bortolotto, C., Stella, G.M., Messana, G., Lo Tito, A., Podrecca, C., Nicora, G., et al. (2022) Correlation between PD-L1 Expression of Non-Small Cell Lung Cancer and Data from IVIM-DWI Acquired during Magnetic Resonance of the Thorax: Preliminary Results. Cancers, 14, Article 5634. [Google Scholar] [CrossRef] [PubMed]
[30] Bortolotto, C., Messana, G., Lo Tito, A., Stella, G.M., Pinto, A., Podrecca, C., et al. (2023) The Role of Native T1 and T2 Mapping Times in Identifying PD-L1 Expression and the Histological Subtype of NSCLCS. Cancers, 15, Article 3252. [Google Scholar] [CrossRef] [PubMed]
[31] Yang, C., Zhu, F., Li, Q., Sun, C., Jin, H. and Zhao, Z. (2025) Evaluation of PD‐L1 Expression in Patients with Non-Small Cell Lung Cancer Using DCE‐MRI Quantitative Analysis. The Clinical Respiratory Journal, 19, e70125. [Google Scholar] [CrossRef] 
[32] Messana, G., Bortolotto, C., Thulasi Seetha, S., Marrocco, A., Pairazzi, C., Sanvito, F., et al. (2025) Non-Invasive PD-L1 Stratification in Non-Small Cell Lung Cancer Using Dynamic Contrast-Enhanced MRI. European Radiology, 35, 5569-5580. [Google Scholar] [CrossRef] [PubMed]

为你推荐