CT影像组学对肺纯磨玻璃结节浸润性的预测价值

doi:10.6040/j.issn.1671-7554.0.2022.0500

摘要/Abstract

摘要： 目的评估从平扫CT及增强CT图像中提取的组学特征是否能提高对纯磨玻璃结节(pGGNs)组织学浸润性的鉴别能力,建立诺模图协助预测pGGNs的浸润性。方法回顾性分析山东第一医科大学附属省立医院2018年12月至2021年6月332例患者,共364个pGGN,按照病理类型分为前驱病变组［包括不典型腺瘤样增生(AAH)和原位腺癌(AIS),共157个］和浸润性病变组［包括微浸润性腺癌(MIA)和浸润性腺癌(IAC),共207个］。在平扫和增强图像上勾画感兴趣区域(ROI)并提取特征。运用最小绝对收缩选择算子(LASSO)进行特征筛选,并对筛选出的放射组学特征进行线性拟合,根据各自加权系数,生成放射组学得分(Rad-score)。将临床资料和CT形态学特征作为临床特征进行多因素回归分析筛选独立预测因子建立临床因素模型。采用多元逻辑回归的方法结合放射组学模型和临床因素模型,构建诺模图。通过受试者操作特性曲线(ROC)、校正曲线和决策曲线(DCA)评估诺模图性能。结果三期(包括平扫、动脉期和静脉期)融合放射组学模型在训练集和验证集中预测pGGN浸润性的AUC是0.915和0.841,显著高于平扫(0.882, 0.796)、动脉期(0.884, 0.814)、静脉期(0.897, 0.841)组学模型、以及临床因素模型(0.805,0.747)。结合三期融合模型及临床因素构建的诺模图 AUC值为0.928(训练集)和0.854(验证集),优于组学模型及临床因素模型。结论增强CT图像提取的影像组学特征可提高对pGGNs浸润性的鉴别能力,诺模图可更好地预测pGGNs的浸润性。

关键词: 放射组学, 肺, 纯磨玻璃结节, 腺癌, 计算机断层扫描

Abstract: Objective To assess whether radiomic characteristics extracted from non-contrast computed tomography(NCCT)and contrast enhanced computed tomography(CECT)images could improve the ability to distinguish the histological invasive lesions manifesting as pure ground-glass nodules(pGGNs), and to develop a nomogram to improve the prediction ability to differentiate atypical adenomatous hyperplasia(AAH)and adenocarcinoma in situ(AIS)from minimally invasive adenocarcinoma(MIA)and invasive adenocarcinoma(IAC). Methods Our study recruited 332 patients with 364 lung pGGNs during Dec. 2018 and Jun. 2021 in Shandong Provincial Hospital Affiliated to Shandong First Medical University. According to pathological types, the patients were divided into prodromal lesion group(n=157, including AAH and AIS)and invasive lesion group(n=207, including MIA and IAC). Image features were extracted from each nodular region of interests on NCCT and CECT images. Least absolute shrinkage and selection operator(LASSO)was employed for feature selection, and the chosen characteristics were used to build a radiomics signature according to their weights in LASSO. Clinical variables and CT morphological features were combined to develop a clinical factor model. A nomogram including independent clinical variables and Rad-score was developed. The nomogram performance was confirmed by receiver operating characteristic(ROC)curve, calibration and decision curve analysis(DCA). Results The tri-phase including non-contrast, arterial and venous phase Rad-score showed a good discrimination in an average area under ROC curve(AUC)of 0.915 and 0.841 in the training and validation sets, higher than those in normal scan(0.882, 0.796), arterial phase(0.884, 0.814), venous phase(0.897, 0.841), and clinical factor model(0.805, 0.747). Radiomics nomogram consisting of tri-phase Rad-score and clinical factors had a better performance(AUC=0.928, 0.854)than the performance of Rad-score and clinical factor models. Conclusion The radiomic features extracted from CECT images can improve the determination ability, and the radiomics nomogram can help in predicting the invasiveness of adenocarcinoma manifesting as pGGNs.

Key words: Radiomics, Lung, Pure ground-glass nodule, Adenocarcinoma, Computed tomography

中图分类号:

R445.3

高琳,于鑫鑫,康冰,张帅,王锡明. CT影像组学对肺纯磨玻璃结节浸润性的预测价值[J]. 山东大学学报 (医学版), 2022, 60(5): 87-97.

GAO Lin, YU Xinxin, KANG Bing, ZHANG Shuai, WANG Ximing. Predictive value of CT-based radiomics nomogram for the invasiveness of lung pure ground-glass nodules[J]. Journal of Shandong University (Health Sciences), 2022, 60(5): 87-97.

参考文献

[1] Li M, Narayan V, Gill RR, et al. Computer-aided diagnosis of ground-glass opacity nodules using open-source software for quantifying tumor heterogeneity [J]. Am J Roentgenol, 2017, 209(6): 1216-1227.
[2] Mei X, Wang R, Yang W, et al. Predicting malignancy of pulmonary ground-glass nodules and their invasiveness by random forest [J]. J Thorac Dis, 2018, 10(1): 458-463.
[3] Zappa C, Mousa SA. Non-small cell lung cancer: current treatment and future advances [J]. Transl Lung Cancer Res, 2016, 5(3): 288-300.
[4] Li Q, Fan L, Cao ET, et al. Quantitative CT analysis of pulmonary pure ground-glass nodule predicts histological invasiveness [J]. Eur J Radiol, 2017, 89: 67-71. doi: 10.1016/j.ejrad.2017.01.024.
[5] Wu F, Tian SP, Jin X, et al. CT and histopathologic characteristics of lung adenocarcinoma with pure ground-glass nodules 10 mm or less in diameter [J]. Eur Radiol, 2017, 27(10): 4037-4043.
[6] World Health Organization(2021). WHO classification of tumours of the lung [EB/OL].(2021-01)[2021-05-10]. https://tumourclassification.iarc.who.int.
[7] Eisenberg RL, Bankier AA, Boiselle PM. Compliance with Fleischner Society Guidelines for management of small lung nodules: a survey of 834 radiologists [J]. Radiology, 2010, 255(1): 218-224.
[8] Song L, Xing T, Zhu Z, et al. Hybrid clinical-radiomics model for precisely predicting the invasiveness of lung adenocarcinoma manifesting as pure ground-glass nodule [J]. Acad Radiol, 2021, 28(9): e267-e277.
[9] Yagi T, Yamazaki M, Ohashi R, et al. HRCT texture analysis for pure or part-solid ground-glass nodules: distinguishability of adenocarcinoma in situ or minimally invasive adenocarcinoma from invasive adenocarcinoma [J]. Jpn J Radiol, 2018, 36(2): 113-121.
[10] She Y, Zhao L, Dai C, et al. Preoperative nomogram for identifying invasive pulmonary adenocarcinoma in patients with pure ground-glass nodule: a multi-institutional study [J]. Oncotarget, 2017, 8(10): 17229-17238.
[11] Dai J, Shi J, Soodeen-Lalloo AK, et al. Air bronchogram: a potential indicator of epidermal growth factor receptor mutation in pulmonary subsolid nodules [J]. Lung Cancer, 2016, 98: 22-28. doi: 10.1016/j.lungcan.2016.05.009.
[12] Oudkerk M, Devaraj A, Vliegenthart R, et al. European position statement on lung cancer screening [J]. Lancet Oncol, 2017, 18(12): e754-e766.
[13] White CS, Dharaiya E, Campbell E, et al. The vancouver lung cancer risk prediction model: assessment by using a subset of the national lung screening trial cohort [J]. Radiology, 2017, 283(1): 264-272.
[14] Zhan Y, Peng X, Shan F, et al. Attenuation and morphologic characteristics distinguishing a ground-glass nodule measuring 5-10 mm in diameter as invasive lung adenocarcinoma on thin-slice CT [J]. Am J Roentgenol, 2019, 213(4): W162-W170.
[15] Lee HW, Jin KN, Lee JK, et al. Long-term follow-up of ground-glass nodules after 5 years of stability [J]. J Thorac Oncol, 2019, 14(8): 1370-1377.
[16] 陈琦, 杨文广, 郁义星, 等. 肺部单发微小磨玻璃结节内部血管及支气管改变对肺腺癌侵袭性的诊断预测价值[J]. 临床放射学杂志, 2019, 38(12): 2322-2327. CHEN Qi, YANG Wenguang, YU Yixing, et al. Diagnostic and prognostic value of pulmonary adenocarcinoma invasivity due to vascular and bronchial changes in single microground glass nodules [J]. Journal of Clinical Radiology, 2019, 38(12): 2322-2327.
[17] 任开明, 赵俊刚, 林爱军, 等. 肺磨玻璃结节的CT影像特征与病理分类的对照分析研究[J]. 中国临床医学影像杂志, 2019, 30(8): 558-561. REN Kaiming, ZHAO Jungang, LIN Aijun, et al. Comparison analysis of CT image characteristics and pathological classification of pulmonary ground glass nodules [J]. Chinese Journal of Clinical Medical Imaging, 2019, 30(8): 558-561.
[18] Gao F, Sun Y, Zhang G, et al. CT characterization of different pathological types of subcentimeter pulmonary ground-glass nodular lesions [J]. Br J Radiol, 2019, 92(1094): 20180204. doi: 10.1259/bjr.20180204.
[19] Cho HH, Lee G, Lee HY, et al. Marginal radiomics features as imaging biomarkers for pathological invasion in lung adenocarcinoma [J]. Eur Radiol, 2020, 30(5): 2984-2994.
[20] Xu F, Zhu W, Shen Y, et al. Radiomic-based quantitative CT analysis of pure ground-glass nodules to predict the invasiveness of lung adenocarcinoma [J]. Front Oncol, 2020, 10: 872. doi:10.3389/fonc.2020.00872.
[21] Wu G, Woodruff HC, Shen J, et al. Diagnosis of invasive lung adenocarcinoma based on chest CT radiomic features of part-solid pulmonary nodules: a multicenter study [J]. Radiology, 2020, 297(2): 451-458.
[22] Wu L, Gao C, Xiang P, et al. CT-imaging based analysis of invasive lung adenocarcinoma presenting as ground glass nodules using peri- and intra-nodular radiomic features [J]. Front Oncol, 2020, 10: 838. doi:10.3389/fonc.2020.00838.
[23] Liu CL, Zhang F, Cai Q, et al. Establishment of a predictive model for surgical resection of ground-glass nodules [J]. J Am Coll Radiol, 2019, 16(4 Pt A): 435-445.
[24] Xue X, Yang Y, Huang Q, et al. Use of a radiomics model to predict tumor invasiveness of pulmonary adenocarcinomas appearing as pulmonary ground-glass nodules [J]. Biomed Res Int, 2018, 2018: 6803971. doi:10.1155/2018/6803971.
[25] Li H, Gao L, Ma H, et al. Radiomics-based features for prediction of histological subtypes in central lung cancer [J]. Front Oncol, 2021, 11: 658887
[26] Nie P, Yang G, Guo J, et al. A CT-based radiomics nomogram for differentiation of focal nodular hyperplasia from hepatocellular carcinoma in the non-cirrhotic liver [J]. Cancer Imaging, 2020, 20(1): 20.
[27] Nie P, Yang G, Wang Z, et al. A CT-based radiomics nomogram for differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma [J]. Eur Radiol, 2020, 30(2): 1274-1284.
[28] 杨蕾, 张在先, 国建林, 等. 基于增强CT影像组学模型预测肺腺癌ALK突变[J]. 中国医学影像学杂志, 2021, 29(5): 454-458. YANG Lei, ZHANG Zaixian, GUO Jianlin, et al. Prediction of ALK mutation in lung adenocarcinoma based on enhanced CT imaging omics model [J]. Chinese Journal of Medical Imaging, 2021, 29(5): 454-458.
[29] Cong M, Feng H, Ren JL, et al. Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stage IA non-small cell lung cancer [J]. Lung Cancer, 2020, 139: 73-79. doi: 10.1016/j.lungcan.2019.11.003
[30] Son JY, Lee HY, Kim JH, et al. Quantitative CT analysis of pulmonary ground-glass opacity nodules for distinguishing invasive adenocarcinoma from non-invasive or minimally invasive adenocarcinoma: the added value of using iodine mapping [J]. Eur Radiol, 2016, 26(1): 43-54.
[31] Yi CA, Lee KS, Kim EA, et al. Solitary pulmonary nodules: dynamic enhanced multi-detector row CT study and comparison with vascular endothelial growth factor and microvessel density [J]. Radiology, 2004, 233(1): 191-199.
[32] Gao C, Xiang P, Ye J, et al. Can texture features improve the differentiation of infiltrative lung adenocarcinoma appearing as ground glass nodules in contrast-enhanced CT? [J]. Eur J Radiol, 2019, 117: 126-131. doi: 10.1016/j.ejrad.2019.06.010.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed