基于人工智能的影像组学及深度学习在非小 细胞肺癌治疗中的应用进展
Application Progress of Artificial Intelligence-Based Radiomics and Deep Learning in the Treatment of Non-Small Cell Lung Cancer
DOI: 10.12677/acm.2026.1672576, PDF,    科研立项经费支持
作者: 秦文恒*, 刘慧君#：济宁医学院附属医院影像科，山东 济宁；崔元元：济宁市第一人民医院康复科，山东 济宁
关键词: 非小细胞肺癌；人工智能；影像组学；深度学习；疗效评估；Non-Small Cell Lung Cancer； Artificial Intelligence； Radiomics； Deep Learning； Therapeutic Effect Evaluation
摘要: 肺癌为我国发病率、死亡率极高的恶性肿瘤，而非小细胞肺癌(NSCLC)占比较高且预后差异显著。传统疗效评估依赖肿瘤形态学与临床指标的变化，难以反映肿瘤异质性及早期生物学改变。人工智能驱动的影像组学与深度学习可无创提取影像定量特征，挖掘肿瘤深层信息，在NSCLC诊疗中展现重要价值。本文系统综述其在手术、放疗、化疗、靶向治疗、免疫治疗中的应用进展，重点阐述术前风险分层、放疗预后与不良反应预测、化疗敏感性评估、驱动基因突变预测、免疫治疗获益人群筛选及不良反应预警等核心方向。未来随着多中心验证、标准化流程与多学科融合推进，该技术将进一步推动NSCLC精准诊疗与个体化治疗落地。
Abstract: Lung cancer is one of the most malignant tumors with extremely high morbidity and mortality in China. Non-small cell lung cancer (NSCLC) constitutes the majority of lung cancer cases and presents remarkable prognostic heterogeneity. Traditional therapeutic efficacy evaluation mainly depends on morphological changes of tumors and clinical indicators, which fails to fully reflect tumor heterogeneity and early biological alterations. Artificial intelligence-based radiomics and deep learning enable non-invasive extraction of quantitative imaging features and in-depth mining of tumor information, exhibiting significant value in the diagnosis and treatment of NSCLC. This article systematically reviews the research progress of these technologies in surgery, radiotherapy, chemotherapy, targeted therapy and immunotherapy for NSCLC, focusing on core applications including preoperative risk stratification, prediction of radiotherapy prognosis and adverse reactions, evaluation of chemosensitivity, prediction of driver gene mutations, identification of immunotherapy beneficiaries and early warning of adverse events. In the future, with the implementation of multi-center validation, standardized workflows and multidisciplinary integration, these approaches will further promote the development of precise diagnosis and individualized treatment of NSCLC.
文章引用：秦文恒, 崔元元, 刘慧君. 基于人工智能的影像组学及深度学习在非小 细胞肺癌治疗中的应用进展[J]. 临床医学进展, 2026, 16(7): 694-702. https://doi.org/10.12677/acm.2026.1672576

参考文献

[1] Siegel, R.L., Giaquinto, A.N. and Jemal, A. (2024) Cancer Statistics, 2024. CA: A Cancer Journal for Clinicians, 74, 12-49. [Google Scholar] [CrossRef] [PubMed]
[2] Schwartz, L.H., Seymour, L., Litière, S., Ford, R., Gwyther, S., Mandrekar, S., et al. (2016) RECIST 1.1—Standardisation and Disease-Specific Adaptations: Perspectives from the RECIST Working Group. European Journal of Cancer, 62, 138-145. [Google Scholar] [CrossRef] [PubMed]
[3] Guiot, J., Vaidyanathan, A., Deprez, L., Zerka, F., Danthine, D., Frix, A., et al. (2022) A Review in Radiomics: Making Personalized Medicine a Reality via Routine Imaging. Medicinal Research Reviews, 42, 426-440. [Google Scholar] [CrossRef] [PubMed]
[4] Doppalapudi, S., Qiu, R.G. and Badr, Y. (2021) Lung Cancer Survival Period Prediction and Understanding: Deep Learning Approaches. International Journal of Medical Informatics, 148, Article ID: 104371. [Google Scholar] [CrossRef] [PubMed]
[5] Arimura, H., Soufi, M., Kamezawa, H., Ninomiya, K. and Yamada, M. (2019) Radiomics with Artificial Intelligence for Precision Medicine in Radiation Therapy. Journal of Radiation Research, 60, 150-157. [Google Scholar] [CrossRef] [PubMed]
[6] 中国临床肿瘤学会指南工作委员会, 编撰. 中国临床肿瘤学会(CSCO)非小细胞肺癌诊疗指南-2025[M]. 北京: 人民卫生出版社, 2025.
[7] Park, Y., Park, E.S., Kim, S.B., Kim, S.C., Sohn, B.H., Chu, I., et al. (2012) Development and Validation of a Prognostic Gene-Expression Signature for Lung Adenocarcinoma. PLOS ONE, 7, e44225. [Google Scholar] [CrossRef] [PubMed]
[8] Chen, X., Fang, M., Dong, D., Wei, X., Liu, L., Xu, X., et al. (2018) A Radiomics Signature in Preoperative Predicting Degree of Tumor Differentiation in Patients with Non-Small Cell Lung Cancer. Academic Radiology, 25, 1548-1555. [Google Scholar] [CrossRef] [PubMed]
[9] Yang, B., Guo, L., Lu, G., Shan, W., Duan, L. and Duan, S. (2019) Radiomic Signature: A Non-Invasive Biomarker for Discriminating Invasive and Non-Invasive Cases of Lung Adenocarcinoma. Cancer Management and Research, 11, 7825-7834. [Google Scholar] [CrossRef] [PubMed]
[10] Akinci D’Antonoli, T., Farchione, A., Lenkowicz, J., Chiappetta, M., Cicchetti, G., Martino, A., et al. (2020) CT Radiomics Signature of Tumor and Peritumoral Lung Parenchyma to Predict Non-Small Cell Lung Cancer Postsurgical Recurrence Risk. Academic Radiology, 27, 497-507. [Google Scholar] [CrossRef] [PubMed]
[11] Ahn, H.K., Lee, H., Kim, S.G. and Hyun, S.H. (2019) Pre-Treatment 18F-FDG Pet-Based Radiomics Predict Survival in Resected Non-Small Cell Lung Cancer. Clinical Radiology, 74, 467-473. [Google Scholar] [CrossRef] [PubMed]
[12] Huang, P., Illei, P.B., Franklin, W., Wu, P., Forde, P.M., Ashrafinia, S., et al. (2022) Lung Cancer Recurrence Risk Prediction through Integrated Deep Learning Evaluation. Cancers, 14, Article 4150. [Google Scholar] [CrossRef] [PubMed]
[13] Cong, M., Feng, H., Ren, J., Xu, Q., Cong, L., Hou, Z., et al. (2020) Development of a Predictive Radiomics Model for Lymph Node Metastases in Pre-Surgical CT-Based Stage IA Non-Small Cell Lung Cancer. Lung Cancer, 139, 73-79. [Google Scholar] [CrossRef] [PubMed]
[14] Zhang, H., Liao, M., Guo, Q., Chen, J., Wang, S., Liu, S., et al. (2023) Predicting N2 Lymph Node Metastasis in Presurgical Stage I‐II Non‐small Cell Lung Cancer Using Multiview Radiomics and Deep Learning Method. Medical Physics, 50, 2049-2060. [Google Scholar] [CrossRef] [PubMed]
[15] Yang, H., Wang, L., Shao, G., Dong, B., Wang, F., Wei, Y., et al. (2022) A Combined Predictive Model Based on Radiomics Features and Clinical Factors for Disease Progression in Early-Stage Non-Small Cell Lung Cancer Treated with Stereotactic Ablative Radiotherapy. Frontiers in Oncology, 12, Article 967360. [Google Scholar] [CrossRef] [PubMed]
[16] Chang, J.Y., Liu, H., Balter, P., Komaki, R., Liao, Z., Welsh, J., et al. (2012) Clinical Outcome and Predictors of Survival and Pneumonitis after Stereotactic Ablative Radiotherapy for Stage I Non-Small Cell Lung Cancer. Radiation Oncology, 7, Article No. 152. [Google Scholar] [CrossRef] [PubMed]
[17] Timmerman, R.D., Paulus, R., Pass, H.I., Gore, E.M., Edelman, M.J., Galvin, J., et al. (2018) Stereotactic Body Radiation Therapy for Operable Early-Stage Lung Cancer. JAMA Oncology, 4, 1263-1266. [Google Scholar] [CrossRef] [PubMed]
[18] Jiao, Z., Li, H., Xiao, Y., Dorsey, J., Simone, C.B., Feigenberg, S., et al. (2022) Integration of Deep Learning Radiomics and Counts of Circulating Tumor Cells Improves Prediction of Outcomes of Early Stage NSCLC Patients Treated with Stereotactic Body Radiation Therapy. International Journal of Radiation Oncology Biology Physics, 112, 1045-1054. [Google Scholar] [CrossRef] [PubMed]
[19] 盛玉杰, 王泽静, 冯长超. 18F-FDG PET/CT显像在肺癌术前分期诊断及复发转移预测中的应用价值[J]. 中国CT和MRI杂志, 2024, 22(3): 61-63.
[20] Lucia, F., Louis, T., Cousin, F., Bourbonne, V., Visvikis, D., Mievis, C., et al. (2024) Multicentric Development and Evaluation of [18F]FDG PET/CT and CT Radiomic Models to Predict Regional and/or Distant Recurrence in Early-Stage Non-Small Cell Lung Cancer Treated by Stereotactic Body Radiation Therapy. European Journal of Nuclear Medicine and Molecular Imaging, 51, 1097-1108. [Google Scholar] [CrossRef] [PubMed]
[21] Dissaux, G., Visvikis, D., Da-ano, R., Pradier, O., Chajon, E., Barillot, I., et al. (2020) Pretreatment 18F-FDG PET/CT Radiomics Predict Local Recurrence in Patients Treated with Stereotactic Body Radiotherapy for Early-Stage Non-Small Cell Lung Cancer: A Multicentric Study. Journal of Nuclear Medicine, 61, 814-820. [Google Scholar] [CrossRef] [PubMed]
[22] Kakino, R., Nakamura, M., Mitsuyoshi, T., Shintani, T., Kokubo, M., Negoro, Y., et al. (2020) Application and Limitation of Radiomics Approach to Prognostic Prediction for Lung Stereotactic Body Radiotherapy Using Breath‐Hold CT Images with Random Survival Forest: A Multi‐institutional Study. Medical Physics, 47, 4634-4643. [Google Scholar] [CrossRef] [PubMed]
[23] 罗楠, 钱柳, 海丽且姆∙艾力, 等. III期非小细胞肺癌患者放疗所致放射性肺炎CT特点及识别[J]. 中国CT和MRI杂志, 2025, 23(2): 74-76.
[24] Bousabarah, K., Blanck, O., Temming, S., Wilhelm, M., Hoevels, M., Baus, W.W., et al. (2021) Radiomics for Prediction of Radiation-Induced Lung Injury and Oncologic Outcome after Robotic Stereotactic Body Radiotherapy of Lung Cancer: Results from Two Independent Institutions. Radiation Oncology, 16, Article No. 74. [Google Scholar] [CrossRef] [PubMed]
[25] Liang, B., Tian, Y., Chen, X., Yan, H., Yan, L., Zhang, T., et al. (2020) Prediction of Radiation Pneumonitis with Dose Distribution: A Convolutional Neural Network (CNN) Based Model. Frontiers in Oncology, 9, Article 1500. [Google Scholar] [CrossRef] [PubMed]
[26] Khorrami, M., Khunger, M., Zagouras, A., Patil, P., Thawani, R., Bera, K., et al. (2019) Combination of Peri-and Intratumoral Radiomic Features on Baseline CT Scans Predicts Response to Chemotherapy in Lung Adenocarcinoma. Radiology: Artificial Intelligence, 1, Article ID: 180012. [Google Scholar] [CrossRef] [PubMed]
[27] Chang, R., Qi, S., Yue, Y., Zhang, X., Song, J. and Qian, W. (2021) Predictive Radiomic Models for the Chemotherapy Response in Non-Small-Cell Lung Cancer Based on Computerized-Tomography Images. Frontiers in Oncology, 11, Article 646190. [Google Scholar] [CrossRef] [PubMed]
[28] Chang, R., Qi, S., Wu, Y., Song, Q., Yue, Y., Zhang, X., et al. (2022) Deep Multiple Instance Learning for Predicting Chemotherapy Response in Non-Small Cell Lung Cancer Using Pretreatment CT Images. Scientific Reports, 12, Article No. 19829. [Google Scholar] [CrossRef] [PubMed]
[29] Chang, R., Qi, S., Wu, Y., Yue, Y., Zhang, X., Guan, Y., et al. (2023) Deep Radiomic Model Based on the Sphere-Shell Partition for Predicting Treatment Response to Chemotherapy in Lung Cancer. Translational Oncology, 35, Article ID: 101719. [Google Scholar] [CrossRef] [PubMed]
[30] de Jong, E.E.C., van Elmpt, W., Leijenaar, R.T.H., Hoekstra, O.S., Groen, H.J.M., Smit, E.F., et al. (2017) [18F]FDG PET/CT-Based Response Assessment of Stage IV Non-Small Cell Lung Cancer Treated with Paclitaxel-Carboplatin-Bevacizumab with or without Nitroglycerin Patches. European Journal of Nuclear Medicine and Molecular Imaging, 44, 8-16. [Google Scholar] [CrossRef] [PubMed]
[31] de Geus-Oei, L.F., van der Heijden, H.F.M., Visser, E.P., Hermsen, R., van Hoorn, B.A., Timmer-Bonte, J.N.H., et al. (2007) Chemotherapy Response Evaluation with 18F-FDG PET in Patients with Non-Small Cell Lung Cancer. Journal of Nuclear Medicine, 48, 1592-1598. [Google Scholar] [CrossRef] [PubMed]
[32] Buizza, G., Toma-Dasu, I., Lazzeroni, M., Paganelli, C., Riboldi, M., Chang, Y., et al. (2018) Early Tumor Response Prediction for Lung Cancer Patients Using Novel Longitudinal Pattern Features from Sequential PET/CT Image Scans. Physica Medica, 54, 21-29. [Google Scholar] [CrossRef] [PubMed]
[33] Agazzi, G.M., Ravanelli, M., Roca, E., Medicina, D., Balzarini, P., Pessina, C., et al. (2021) CT Texture Analysis for Prediction of EGFR Mutational Status and ALK Rearrangement in Patients with Non-Small Cell Lung Cancer. La radiologia medica, 126, 786-794. [Google Scholar] [CrossRef] [PubMed]
[34] Le, N.Q.K., Kha, Q.H., Nguyen, V.H., Chen, Y., Cheng, S. and Chen, C. (2021) Machine Learning-Based Radiomics Signatures for EGFR and KRAS Mutations Prediction in Non-Small-Cell Lung Cancer. International Journal of Molecular Sciences, 22, Article 9254. [Google Scholar] [CrossRef] [PubMed]
[35] Agüloğlu, N., Aksu, A., Akyol, M., Katgı, N. and Doksöz, T.Ç. (2022) Importance of Pretreatment 18F-FDG PET/CT Texture Analysis in Predicting EGFR and Alk Mutation in Patients with Non-Small Cell Lung Cancer. Nuklearmedizin—NuclearMedicine, 61, 433-439. [Google Scholar] [CrossRef] [PubMed]
[36] Mu, W., Jiang, L., Zhang, J., Shi, Y., Gray, J.E., Tunali, I., et al. (2020) Non-Invasive Decision Support for NSCLC Treatment Using PET/CT Radiomics. Nature Communications, 11, Article No. 5228. [Google Scholar] [CrossRef] [PubMed]
[37] Khorrami, M., Bera, K., Thawani, R., Rajiah, P., Gupta, A., Fu, P., et al. (2021) Distinguishing Granulomas from Adenocarcinomas by Integrating Stable and Discriminating Radiomic Features on Non-Contrast Computed Tomography Scans. European Journal of Cancer, 148, 146-158. [Google Scholar] [CrossRef] [PubMed]
[38] Yamazaki, M., Yagi, T., Tominaga, M., Minato, K. and Ishikawa, H. (2022) Role of Intratumoral and Peritumoral CT Radiomics for the Prediction of EGFR Gene Mutation in Primary Lung Cancer. The British Journal of Radiology, 95, Article ID: 20220374. [Google Scholar] [CrossRef] [PubMed]
[39] Gao, S., Li, N., Wang, S., Zhang, F., Wei, W., Li, N., et al. (2020) Lung Cancer in People’s Republic of China. Journal of Thoracic Oncology, 15, 1567-1576. [Google Scholar] [CrossRef] [PubMed]
[40] 张成孟, 丁治民, 陈鹏, 等. CT影像组学联合细胞角蛋白19片段预测EGFR突变阳性非小细胞肺癌患者EGFR-TKIs的疗效[J]. 放射学实践, 2023, 38(12): 1532-1538.
[41] Yang, F., Zhang, J., Zhou, L., Xia, W., Zhang, R., Wei, H., et al. (2022) CT-Based Radiomics Signatures Can Predict the Tumor Response of Non-Small Cell Lung Cancer Patients Treated with First-Line Chemotherapy and Targeted Therapy. European Radiology, 32, 1538-1547. [Google Scholar] [CrossRef] [PubMed]
[42] Liu, C., Gong, J., Yu, H., Liu, Q., Wang, S. and Wang, J. (2021) A CT-Based Radiomics Approach to Predict Nivolumab Response in Advanced Non-Small-Cell Lung Cancer. Frontiers in Oncology, 11, Article 544339. [Google Scholar] [CrossRef] [PubMed]
[43] Yoon, J., Suh, Y.J., Han, K., Cho, H., Lee, H., Hur, J., et al. (2020) Utility of CT Radiomics for Prediction of PD‐L1 Expression in Advanced Lung Adenocarcinomas. Thoracic Cancer, 11, 993-1004. [Google Scholar] [CrossRef] [PubMed]
[44] 田琪, 冯峰, 陈巧玲, 等. CT影像组学列线图评估非小细胞肺癌程序性死亡受体1表达[J]. 中国医学影像技术, 2023, 39(4): 543-548.
[45] Li, J., Ge, S., Sang, S., Hu, C. and Deng, S. (2021) Evaluation of PD-L1 Expression Level in Patients with Non-Small Cell Lung Cancer by 18F-FDG PET/CT Radiomics and Clinicopathological Characteristics. Frontiers in Oncology, 11, Article 789014. [Google Scholar] [CrossRef] [PubMed]
[46] Coroller, T.P., Agrawal, V., Huynh, E., Narayan, V., Lee, S.W., Mak, R.H., et al. (2017) Radiomic-Based Pathological Response Prediction from Primary Tumors and Lymph Nodes in NSCLC. Journal of Thoracic Oncology, 12, 467-476. [Google Scholar] [CrossRef] [PubMed]
[47] Zhou, F., Qiao, M. and Zhou, C. (2021) The Cutting-Edge Progress of Immune-Checkpoint Blockade in Lung Cancer. Cellular & Molecular Immunology, 18, 279-293. [Google Scholar] [CrossRef] [PubMed]
[48] Trebeschi, S., Drago, S.G., Birkbak, N.J., Kurilova, I., Cǎlin, A.M., Delli Pizzi, A., et al. (2019) Predicting Response to Cancer Immunotherapy Using Noninvasive Radiomic Biomarkers. Annals of Oncology, 30, 998-1004. [Google Scholar] [CrossRef] [PubMed]
[49] Mu, W., Tunali, I., Gray, J.E., Qi, J., Schabath, M.B. and Gillies, R.J. (2020) Radiomics of 18F-FDG PET/CT Images Predicts Clinical Benefit of Advanced NSCLC Patients to Checkpoint Blockade Immunotherapy. European Journal of Nuclear Medicine and Molecular Imaging, 47, 1168-1182. [Google Scholar] [CrossRef] [PubMed]
[50] Yang, Y., Yang, J., Shen, L., et al. (2021) A Multi-Omics-Based Serial Deep Learning Approach to Predict Clinical Outcomes of Single-Agent Anti-PD-1/PD-L1 Immunotherapy in Advanced Stage Non-Small-Cell Lung Cancer. American Journal of Translational Research, 13, 743-756.
[51] Mu, W., Tunali, I., Qi, J., Schabath, M.B. and Gillies, R.J. (2020) Radiomics of 18F Fluorodeoxyglucose PET/CT Images Predicts Severe Immune-Related Adverse Events in Patients with NSCLC. Radiology: Artificial Intelligence, 2, e190063. [Google Scholar] [CrossRef] [PubMed]

为你推荐