
浏览全部资源
扫码关注微信
川北医学院附属医院放射科,南充 637000
李小英,Email:2681664039@qq.com,研究方向:胸腹部疾病诊断。
李 杨,Email:552410618@qq.com。
收稿日期:2025-03-05,
网络出版日期:2025-07-31,
移动端阅览
李小英,杨朝凤,李杨.CT影像组学预测非小细胞肺癌EGFR-TKIs疗效评估的研究[J].重庆医科大学学报,
Li Xiaoying,Yang Chaofeng,Li Yang.CT-based radiomics for predicting the response of non-small cell lung cancer to EGFR-TKIs[J].Journal of Chongqing Medical University,
李小英,杨朝凤,李杨.CT影像组学预测非小细胞肺癌EGFR-TKIs疗效评估的研究[J].重庆医科大学学报, DOI:10.13406/j.cnki.cyxb..
Li Xiaoying,Yang Chaofeng,Li Yang.CT-based radiomics for predicting the response of non-small cell lung cancer to EGFR-TKIs[J].Journal of Chongqing Medical University, DOI:10.13406/j.cnki.cyxb..
目的
2
探究基于X线计算机体层摄影(computed tomography,CT)的影像组学预测非小细胞肺癌(non-small cell lung cancer,NSCLC)经表皮生长因子受体酪氨酸激酶抑制剂(epidermal growth factor receptor tyrosine kinase inhibitors,EGFR-TKIs)治疗后无进展生存期(progression-free survival,PFS)的价值。
方法
2
回顾性收集经EGFR-TKIs治疗的NSCLC患者135例,按照7:3的比例随机分为训练组(96例)及测试组(39例)。首先,从肿瘤影像中提取影像组学特征,在训练组中采用观察者内观察者间相关性、单因素COX回归及最小绝对收缩与选择算子的COX回归分析筛选最具预测价值的影像组学特征。同时,采用单因素及多因素COX回归分析筛选具有独立预测价值的临床特征。然后,基于筛选的特征建立影像组学模型、临床模型及联合模型。评估并比较各模型的区分度及临床获益,最后进行风险分层生存分析。
结果
2
基于训练组最终筛选出12个与PFS最为相关的影像组学特征。年龄、平均红细胞体积、中性粒细胞与淋巴细胞比率是PFS的临床独立危险因素。在训练组中,影像组学模型、临床模型、联合模型的C-index分别是0.690(95%CI=0.616~0.763)、0.649(95%CI=0.582~0.716)、0.752(95%CI=0.688~0.815);在测试组中,C-index分别是0.711(95%CI=0.593~0.830)、0.574(95%CI=0.428~0.719)、0.739(95%CI=0.633~0.845);联合模型性能最高。临床决策曲线分析(decision curve analysis,DCA)显示联合模型与影像组学模型的临床净获益接近,但高于临床模型。Kaplan-Meier曲线和Log-rank 检验显示联合模型具备对患者风险分层生存分析的能力。
结论
2
CT影像组学对接受EGFR-TKIs治疗的NSCLC患者的PFS具有良好的预测性能,对临床医师筛选快速进展人群、改善患者预后具有重要意义。
Objective
2
To explore the value of radiomics based on X-ray computed tomography(CT) in predicting the progression-free survival(PFS) of patients with non-small cell lung cancer(NSCLC) treated with epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs).
Methods
2
A retrospective study was conducted on 135 NSCLC patients who were treated with EGFR-TKIs. The patients were randomly divided into a training set(96 cases) and a testing set(39 cases) at a 7:3 ratio. Firstly,radiomics features were extracted from tumor medical images. In the training set,optimal predictive radiomics features were selected by intra-class and inter-class correlation coefficient,univariate and least absolute shrinkage and selection operator COX regression analyses. Meanwhile,clinical risk factors with independent predictive value were selected by univariate and multivariate COX regression analyses. Then,radiomics,clinical,and combined models were constructed based on the selected features. The discrimination performance and clinical benefit of each model were evaluated and compared. Finally,risk stratification based on survival analysis was performed.
Results
2
Based on the training set,12 radiomic features significantly associated with PFS were selected. Age,mean corpuscular volume,and neutrophil-to-lymphocyte ratio were independent clinical risk factors for PFS. In the training set,the C-index of the radiomics model,clinical model,and combined model was 0.690(95%CI=0.616-0.763),0.649(95%CI=0.582-0.716),and 0.752(95%CI=0.688-0.815),respectively. In the testing set,the C-index values were 0.711(95%CI=0.593-0.830),0.574(95%CI=0.428-0.719),and 0.739(95%CI=0.633-0.845),respectively. The combined model had the highest performance. The decision curve analysis showed that the net clinical benefit of the combined model was similar to radiomics model,but higher than clinical model. The Kaplan-Meier curve and Log-rank test showed that the combined model had the ability of risk stratification based on survival analysis.
Conclusion
2
CT-based radiomics can effectively predict the PFS of NSCLC patients treated with EGFR-TKIs,which is significant for clinicians to identify rapid progressors and improve the prognosis of patients.
Han BF , Zheng RS , Zeng HM , et al . Cancer incidence and mortality in China,2022 [J ] . J Natl Cancer Cent , 2024 , 4 ( 1 ): 47 - 53 .
中华医学会肿瘤学分会 . 中华医学会肺癌临床诊疗指南(2024版) [J ] . 中华医学杂志 , 2024 , 104 ( 34 ): 3175 - 3213 .
Oncology Society of Chinese Medical Association . Chinese medical association guideline for clinical diagnosis and treatment of lung cancer (2024 edition) [J ] . Nal Med J China , 2024 , 104 ( 34 ): 3175 - 3213 .
国家卫生健康委办公厅 . 原发性肺癌诊疗指南(2022年版) [J ] . 协和医学杂志 , 2022 , 13 ( 04 ): 549 - 570 .
General office of national health commission of the people's republic of China . Clinical practice guideline for primary lung cancer(2022 version) [J ] . Med J PUMCH , 2022 , 13 ( 04 ): 549 - 570 .
Genova C , Rossi G , Tagliamento M , et al . Targeted therapy of oncogenic-driven advanced non-small cell lung cancer:recent advances and new perspectives [J ] . Expert Rev Respir Med , 2020 , 14 ( 4 ): 367 - 383 .
Liao D , Yu L , Shangguan D , et al . Recent advancements of monotherapy,combination,and sequential treatment of EGFR/ALK-TKIs and ICIs in non-small cell lung cancer [J ] . Front Pharmacol , 2022 , 13 : 905947 .
Soria JC , Ohe Y , Vansteenkiste J , et al . Osimertinib in untreated EGFR-mutated advanced non-small-cell lung cancer [J ] . N Engl J Med , 2018 , 378 ( 2 ): 113 - 125 .
Mok TS , Wu Y-L , Ahn M-J , et al . Osimertinib or platinum-pemetrexed in EGFR T790M-positive lung cancer [J ] . N Engl J Med , 2017 , 376 ( 7 ): 629 - 640 .
Therasse P , Arbuck SG , Eisenhauer EA , et al . New guidelines to evaluate the response to treatment in solid tumors. European Organization for Research and Treatment of Cancer,National Cancer Institute of the United States,National Cancer Institute of Canada [J ] . J Natl Cancer Inst , 2000 , 92 ( 3 ): 205 - 216 .
Pan F , Feng L , Liu B , et al . Application of radiomics in diagnosis and treatment of lung cancer [J ] . Front Pharmacol , 2023 , 14 : 1295511 .
Dong H , Yin L , Chen L , et al . Establishment and validation of a radiological-radiomics model for predicting high-grade patterns of lung adenocarcinoma less than or equal to 3 cm [J ] . Front Oncol , 2022 , 12 : 964322 .
Yang FC , Zhang JY , Zhou L , et al . CT-based radiomics signatures can predict the tumor response of non-small cell lung cancer patients treated with first-line chemotherapy and targeted therapy [J ] . Eur Radiol , 2022 , 32 ( 3 ): 1538 - 1547 .
Bracci S , Dolciami M , Trobiani C , et al . Quantitative CT texture analysis in predicting PD-L1 expression in locally advanced or metastatic NSCLC patients [J ] . La Radiol Med , 2021 , 126 ( 11 ): 1425 - 1433 .
Laface C , Maselli FM , Santoro AN , et al . The resistance to EGFR-TKIs in non-small cell lung cancer:from molecular mechanisms to clinical application of new therapeutic strategies [J ] . Pharmaceutics , 2023 , 15 ( 6 ): 1604 .
Giaccone G , He Y . Current knowledge of small cell lung cancer transformation from non-small cell lung cancer [J ] . Semin Cancer Biol , 2023 , 94 : 1 - 10 .
Dong RF , Zhu ML , Liu MM , et al . EGFR mutation mediates resistance to EGFR tyrosine kinase inhibitors in NSCLC:From molecular mechanisms to clinical research [J ] . Pharmacol Res , 2021 , 167 : 105583 .
Reita D , Pabst L , Pencreach E , et al . Molecular mechanism of EGFR-TKI resistance in EGFR -mutated non-small cell lung cancer:application to biological diagnostic and monitoring [J ] . Cancers (Basel) , 2021 , 13 ( 19 ): 4926 .
Ge G , Zhang J . Feature selection methods and predictive models in CT lung cancer radiomics [J ] . J Appl Clin Med Phys , 2023 , 24 ( 1 ): e13869 .
Lambin P , Rios-Velazquez E , Leijenaar R , et al . Radiomics:Extracting more information from medical images using advanced feature analysis [J ] . Eur J Cancer , 2012 , 48 ( 4 ): 441 - 446 .
Song J , Shi J , Dong D , et al . A new approach to predict progression-free survival in stage IV EGFR-mutant NSCLC patients with EGFR-TKI therapy [J ] . Clin Cancer Res , 2018 , 24 ( 15 ): 3583 - 3592 .
Li KJ , Gu WY , Xia XF , et al . High mean corpuscular volume as a predictor of poor overall survival in patients with esophageal cancer receiving concurrent chemoradiotherapy [J ] . Cancer Manag Res , 2020 , 12 : 7467 - 7474 .
Kato M , Kubosawa Y , Hiarai Y , et al . Usefulness of mean corpuscular volume for detection of advanced colorectal cancer in patients older than 85 years [J ] . Digestion , 2018 , 97 ( 2 ): 177 - 182 .
Nakamura K , Seishima R , Matsui S , et al . The prognostic impact of preoperative mean corpuscular volume in colorectal cancer [J ] . Jpn J Clin Oncol , 2022 , 52 ( 6 ): 562 - 570 .
Mantovani A , Allavena P , Sica A , et al . Cancer-related inflammation [J ] . Nature , 2008 , 454 ( 7203 ): 436 - 444 .
Balkwill F , Mantovani A . Inflammation and cancer:back to Virchow? [J ] . Lancet , 2001 , 357 ( 9255 ): 539 - 545 .
Keit E , Coutu B , Zhen W , et al . Systemic inflammation is associated with inferior disease control and survival in stage III non-small cell lung cancer [J ] . Ann Transl Med , 2021 , 9 ( 3 ): 227 .
Ono T , Igawa S , Kurahayashi S , et al . Impact of neutrophil-to-lymphocyte ratio in patients with EGFR-mutant NSCLC treated with tyrosine kinase inhibitors [J ] . Invest New Drugs , 2020 , 38 ( 3 ): 885 - 893 .
Zhang X , Lu B , Yang X , et al . Prognostic analysis and risk stratification of lung adenocarcinoma undergoing EGFR-TKI therapy with time-serial CT-based radiomics signature [J ] . Eur Radiol , 2023 , 33 ( 2 ): 825 - 835 .
Lu CF , Liao CY , Chao HS , et al . A radiomics-based deep learning approach to predict progression free-survival after tyrosine kinase inhibitor therapy in non-small cell lung cancer [J ] . Cancer Imaging , 2023 , 23 ( 1 ): 9 .
Tang X , Li Y , Yan WF , et al . Machine learning-based CT radiomics analysis for prognostic prediction in metastatic non-small cell lung cancer patients with EGFR -T790M mutation receiving third-generation EGFR-TKI osimertinib treatment [J ] . Front Oncol , 2021 , 11 : 719919 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621