[1]张国晋,孔维芳,李昕,等.联合瘤内和瘤周CT影像组学特征预测纯磨玻璃结节肺腺癌浸润性[J].中国医学物理学杂志,2026,43(9):1171-1177.[doi:DOI:10.3969/j.issn.1005-202X.2026.09.003]
　ZHANG Guojin,KONG Weifang,LI Xin,et al.Prediction of invasiveness of lung adenocarcinoma manifesting as pure ground-glass nodules using intratumoral and peritumoral CT radiomic features[J].Chinese Journal of Medical Physics,2026,43(9):1171-1177.[doi:DOI:10.3969/j.issn.1005-202X.2026.09.003]
点击复制

联合瘤内和瘤周CT影像组学特征预测纯磨玻璃结节肺腺癌浸润性()

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
43卷
期数:
2026年第9期
页码:
1171-1177
栏目:
医学影像物理
出版日期:
2026-09-30

文章信息/Info

Title:
Prediction of invasiveness of lung adenocarcinoma manifesting as pure ground-glass nodules using intratumoral and peritumoral CT radiomic features
文章编号:
1005-202X（2026）09-1171-07
作者:
张国晋1; 孔维芳1; 李昕1; 张鑫2; 钱蓉1; 尚兰1; 蒲红1; 李昇霖1; 3
1.四川省医学科学院[?四川省人民医院（电子科技大学附属医院）放射科， 四川 成都 610072；2.通用电气药业（上海）有限公司， 上海 210000；3.兰州大学第二医院放射科， 甘肃 兰州 730030
Author(s):
ZHANG Guojin1;  KONG Weifang1;  LI Xin1;  ZHANG Xin2;  QIAN Rong1;  SHANG Lan1;  PU Hong1;  LI Shenglin1;  3
1. Department of Radiology, Sichuan Academy of Medical Sciences[?Sichuan Provincial Peoples Hospital (the Affiliated Hospital of University of Electronic Science and Technology of China), Chengdu 610072, China 2. General Electric Pharmaceutical (Shanghai) Co., Ltd., Shanghai 210000, China 3. Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China
关键词:
肺腺癌; 影像组学; 瘤周微环境; X线计算机
Keywords:
lung adenocarcinoma radiomics peritumoral microenvironment X-ray computed tomography
分类号:
R318；R734.2
DOI:
DOI:10.3969/j.issn.1005-202X.2026.09.003
文献标志码:
A
摘要:
目的：探讨基于瘤内及瘤周CT影像组学模型在预测纯磨玻璃结节（pGGN）肺腺癌浸润性的价值。方法：回顾性纳入2024年1月至2025年2月于四川省人民医院和兰州大学第二医院370例经病理学证实的pGGN肺腺癌患者。从肿瘤总体积（GTV）和瘤内-瘤周总体积（GPTV）感兴趣区内分别提取1 544个特征，并通过最大相关性且最小冗余、最小绝对收缩和选择算子、多元逻辑回归对特征进行降维。采用逻辑回归方法分别构建临床、GTV和GPTV模型，并联合GPTV特征和临床独立危险因素构建联合模型。ROC曲线评估各模型的性能，并用DeLong检验比较各模型曲线下面积（AUC）值的差异；分别计算AUC、准确性、敏感度和特异度。结果：GPTV模型在训练集（AUC：0.807，95% CI：0.750~0.864）和测试集（AUC：0.781，95% CI：0.685~0.877）中的性能优于临床模型（训练集AUC：0.724，95% CI：0.654~0.795；测试集AUC：0.662，95% CI：0.543~0.781）和GTV模型（训练集AUC：0.745，95% CI：0.674~0.816；测试集AUC：0.724，95% CI：0.614~0.834）。联合模型的性能进一步提升（训练集AUC：0.853，95% CI：0.806~0.899；测试集AUC：0.804，95% CI：0.708~0.899）。结论：瘤内和瘤周CT影像组学特征的整合提高预测pGGN肺腺癌浸润性方面的性能。 【关键词】肺腺癌；影像组学；瘤周微环境；X线计算机
Abstract:
Objective To explore the predictive value of intratumoral and peritumoral CT radiomic features for the invasiveness of lung adenocarcinoma manifesting as pure ground-glass nodules (pGGN). Methods A retrospective analysis was performed on 370 patients with pathologically confirmed lung adenocarcinoma manifesting as pGGN at Lanzhou University Second Hospital and Sichuan Provincial Peoples Hospital from January 2024 to February 2025. In total, 1 544 features were extracted from regions of interest covering the gross tumor volume (GTV) and gross-peritumoral volume (GPTV), and the features were dimensionally reduced through the max-relevance and min-redundancy, least absolute shrinkage and selection operator, and multivariate logistic regression. Logistic regression was utilized to establish the clinical, GTV, and GPTV models. Furthermore, a combined model was constructed by integrating GPTV features with independent clinical risk factors. ROC curve was used to evaluate the performance of each model, and the DeLong test was performed to compare differences in AUC value among models. The AUC, accuracy, sensitivity, and specificity were calculated. Results The GPTV model in the training set (AUC: 0.807, 95% CI: 0.750-0.864) and test set (AUC: 0.781, 95% CI: 0.685-0.877) outperformed the clinical model (training set AUC: 0.724, 95% CI: 0.654-0.795 test set AUC: 0.662, 95% CI: 0.543-0.781) and the GTV model (training set AUC: 0.745, 95% CI: 0.674-0.816 test set AUC: 0.724, 95% CI: 0.614-0.834). The performance of the combined model was further improved (training set AUC: 0.853, 95% CI: 0.806-0.899 test set AUC: 0.804, 95% CI: 0.708-0.899). Conclusion The integration of intratumoral and peritumoral CT radiomic features enhances the predictive performance for the invasiveness in lung adenocarcinoma manifesting as pGGN.

相似文献/References:

[1]李双双,侯震,刘娟,等.影像组学分析与建模工具综述[J].中国医学物理学杂志,2018,35(9):1043.[doi:10.3969/j.issn.1005-202X.2018.09.010]
　LI Shuangshuang,HOU Zhen,LIU Juan,et al.Review of radiomic analysis and modeling tools[J].Chinese Journal of Medical Physics,2018,35(9):1043.[doi:10.3969/j.issn.1005-202X.2018.09.010]
[2]鲁晓腾,龚敬,聂生东. 基于CT图像特征的肺腺癌预后因素分析[J].中国医学物理学杂志,2019,36(3):291.[doi:DOI:10.3969/j.issn.1005-202X.2019.03.009]
　LU Xiaoteng,GONG Jing,NIE Shengdong. CT image feature-based analysis on the prognostic factors of lung adenocarcinoma[J].Chinese Journal of Medical Physics,2019,36(9):291.[doi:DOI:10.3969/j.issn.1005-202X.2019.03.009]
[3]沙雪,巩贯忠,邓红彬,等. 18F-FDG PET/CT影像组学预测非小细胞肺癌亚型的研究[J].中国医学物理学杂志,2019,36(3):311.[doi:DOI:10.3969/j.issn.1005-202X.2019.03.013]
　SHA Xue,GONG Guanzhong,DENG Hongbin,et al. 18F-FDG PET/CT radiomic features for predicting the subtypes of non-small-cell lung cancer[J].Chinese Journal of Medical Physics,2019,36(9):311.[doi:DOI:10.3969/j.issn.1005-202X.2019.03.013]
[4]李腾翔,巩贯忠,仇清涛,等. 鼻咽癌CT影像组学量化分析研究[J].中国医学物理学杂志,2019,36(5):551.[doi:DOI:10.3969/j.issn.1005-202X.2019.05.011]
　LI Tengxiang,GONG Guanzhong,QIU Qingtao,et al. Quantitative analysis of CT radiomics features of nasopharyngeal carcinoma[J].Chinese Journal of Medical Physics,2019,36(9):551.[doi:DOI:10.3969/j.issn.1005-202X.2019.05.011]
[5]周榴,董怡,夏威,等.基于超声影像组学的原发性肝细胞癌分级预测[J].中国医学物理学杂志,2020,37(1):59.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.012]
　ZHOU Liu,DONG Yi,XIA Wei,et al.Prediction of grade of hepatocellular carcinoma by radiomics based on ultrasound[J].Chinese Journal of Medical Physics,2020,37(9):59.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.012]
[6]刘发明,江桂华,杨宁,等.新型冠状病毒肺炎的影像组学研究[J].中国医学物理学杂志,2020,37(4):463.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.012]
　LIU Faming,JIANG Guihua,YANG Ning,et al.Radiomics analysis on COVID-19[J].Chinese Journal of Medical Physics,2020,37(9):463.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.012]
[7]张白霖,戴振晖,朱琳,等.不同设备不同扫描参数对影像组学特征可再现性影响分析[J].中国医学物理学杂志,2021,38(1):61.[doi:DOI:10.3969/j.issn.1005-202X.2021.01.011]
　ZHANG Bailin,DAI Zhenhui,ZHU Lin,et al.An analysis of influence of different equipment and different scanning parameters on reproducibility of radiomics features[J].Chinese Journal of Medical Physics,2021,38(9):61.[doi:DOI:10.3969/j.issn.1005-202X.2021.01.011]
[8]张祥斌,戴谷宇,肖青,等.基于电子射野影像装置通量变化的影像组学特征进行眼突放射治疗摆位误差探测的初步研究[J].中国医学物理学杂志,2021,38(2):153.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.005]
　ZHANG Xiangbin,DAI Guyu,XIAO Qing,et al.Preliminary study of radiomics features of EPID image in detecting setup errors in eye lens radiotherapy[J].Chinese Journal of Medical Physics,2021,38(9):153.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.005]
[9]陈文韬,孙磊,谭爱斌,等.基于CT的影像组学特征同临床物理剂量特征预测肺癌放疗放射性肺炎研究[J].中国医学物理学杂志,2021,38(6):672.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.003]
　CHEN Wentao,SUN Lei,et al.Prediction of radiation pneumonia in lung cancer patients by CT-based radiomics signatures and clinical physical dosimetric features[J].Chinese Journal of Medical Physics,2021,38(9):672.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.003]
[10]范晓鸿,董可,杨银,等.放射性肺损伤与三维剂量分布的相关性研究[J].中国医学物理学杂志,2021,38(6):692.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.007]
　FAN Xiaohong,DONG Ke,YANG Yin,et al.Correlation between radiation-induced lung injury and 3D dose distribution[J].Chinese Journal of Medical Physics,2021,38(9):692.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.007]

备注/Memo

备注/Memo:
【收稿日期】2026-03-02 【基金项目】国家自然科学基金（82202147）；成都市医学科研课题（2024075）；四川省医疗卫生与健康促进会科研项目（WTKY2025SJ0002） 【作者简介】张国晋，博士，主治医师，研究方向：胸部影像学，E-mail: zhnaggj15@lzu.edu.cn 【通信作者】李昇霖，博士，主治医师，研究方向：胸部影像学，E-mail: lishl18@lzu.edu.cn
更新日期/Last Update: 2026-09-30