山东大学学报 (医学版) ›› 2023, Vol. 61 ›› Issue (12): 70-77.doi: 10.6040/j.issn.1671-7554.0.2023.0748
• 医学影像人工智能的创新与挑战—临床研究 • 上一篇
艾江山1,高会江1,艾仕文2,李恒艳3,石国栋1,魏煜程1
AI Jiangshan1, GAO Huijiang1, AI Shiwen2, LI Hengyan3, SHI Guodong1, WEI Yucheng1
摘要: 目的 建立一个基于临床特征和术前计算机断层扫描(CT)影像组学的预测模型辅助诊断囊腔型肺癌。 方法 回顾性分析2020年1月至2021年12月在青岛大学附属医院及济宁医学院附属医院接受手术治疗的患者,纳入病变中含有囊腔的患者296例,并分为囊腔型肺癌和良性病变两组。从术前CT图像上提取病灶的影像组学特征,并综合分析临床病理特征。将上述特征进行筛选后以随机森林算法构建诊断模型,其中来自青岛大学附属医院的214例患者进行训练和内部验证(D1)。其余82例来自济宁医学院附属医院的患者作为独立的外部验证队列(D2)。通过受试者工作特征曲线(ROC)、校准曲线及决策曲线分析(DCA)对模型的分类能力进行评估。 结果 囊腔型肺癌组患者年龄高于良性病变组(60.12±9.95 vs 50.86 ±13.66, P<0.001),其余临床特征差异无统计学意义。影像组学特征经筛选后获得形状平坦度、稳健平均绝对偏差、差异方差等5种影像组学纹理特征。临床与影像组学特征融合后构建随机森林模型在D1(AUC 0.97)和D2(AUC 0.74)上均显示出较好的诊断效能,在D1中的准确性、敏感性与特异性分别为0.92、0.85和0.99。 结论 构建并外部验证了一个实用的诊断模型,可以比较准确地区分囊腔型肺癌和囊腔样良性病变。这种创新的方法可作为囊腔型肺癌的一种新的无创诊断工具。
中图分类号:
[1] Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J]. CA Cancer J Clin, 2021, 71(3): 209-249. [2] Detterbeck FC, Kumbasar U, Li AX, et al. Lung cancer with air lucency: a systematic review and clinical management guide [J]. J Thorac Dis, 2023, 15(2): 731-746. [3] Mascalchi M, Attina D, Bertelli E, et al. Lung cancer associated with cystic airspaces [J]. J Comput Assist Tomogr, 2015, 39(1): 102-108. [4] Fintelmann FJ, Brinkmann JK, Jeck WR, et al. Lung cancers associated with cystic airspaces: natural history, pathologic correlation, and mutational analysis [J]. J Thorac Imaging, 2017, 32(3): 176-188. [5] Shen Y, Xu X, Zhang Y, et al. Lung cancers associated with cystic airspaces: CT features and pathologic correlation[J]. Lung Cancer, 2019, 135: 110-115. doi: 10.1016/j.lungcan.2019.05.012. [6] ?瘙塁ahin C, Yılmaz O, Üçpınar BA, et al. Computed tomography-guided transthoracic core needle biopsy of lung masses: technique, complications and diagnostic yield rate [J]. Sisli Etfal Hastanesi tip bulteni, 2020, 54(1): 47-51. [7] Huang EP, OConnor JPB, McShane LM, et al. Criteria for the translation of radiomics into clinically useful tests [J]. Nat Rev Clin Oncol, 2023, 20(2): 69-82. [8] Yu M, Wang Z, Yang G, et al. A model of malignant risk prediction for solitary pulmonary nodules on(18)F-FDG PET/CT: building and estimating [J]. Thorac Cancer, 2020, 11(5): 1211-1215. [9] Lv Y, Ye J, Yin YL, et al. A comparative study for the evaluation of CT-based conventional, radiomic, combined conventional and radiomic, and delta-radiomic features, and the prediction of the invasiveness of lung adenocarcinoma manifesting as ground-glass nodules [J]. Clin Radiol, 2022, 77(10): e741-e748. [10] Zhang N, Liu JF, Wang YN, et al. A nomogram to predict invasiveness in lung adenocarcinoma presenting as ground glass nodule [J]. Transl Cancer Res, 2020, 9(3): 1660-1669. [11] 肖寿勇, 吴四云, 赵炜杰, 等. 浸润性肺腺癌高分辨率CT征象与病理亚型的对照研究[J]. 临床放射学杂志, 2022, 41(1): 75-80. XIAO Shouyong, WU Siyun, ZHAO Weijie, et al. A comparative study of high-resolution CT signs and pathological subtypes of invasive lung adenocarcinoma [J]. Journal of Clinical Radiology, 2022, 41(1): 75-80. [12] van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype [J]. Cancer Res, 2017, 77(21): e104-e107. [13] 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. [14] 高琳, 于鑫鑫, 康冰, 等. 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, et al. 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. [15] Wang T, She Y, Yang Y, et al. Radiomics for survival risk stratification of clinical and pathologic stage IA pure-solid non-small cell lung cancer [J]. Radiology, 2022, 302(2): 425-434. [16] Coroller TP, Agrawal V, Huynh E, et al. Radiomic-based pathological response prediction from primary tumors and lymph nodes in NSCLC [J]. J Thorac Oncol, 2017, 12(3): 467-476. [17] Farooqi AO, Cham M, Zhang L, et al. Lung cancer associated with cystic airspaces [J]. AJR Am J Roentgenol, 2012, 199(4): 781-786. [18] Zhu H, Zhang L, Huang Z, et al. Lung adenocarcinoma associated with cystic airspaces: predictive value of CT features in assessing pathologic invasiveness [J]. Eur J Radiol, 2023, 165: 110947. doi: 10.1016/j.ejrad.2023.110947. [19] Wang B, Hamal P, Sun K, et al. Clinical value and pathologic basis of cystic airspace within subsolid nodules confirmed as lung adenocarcinomas by surgery [J]. Clin Lung Cancer, 2021, 22(6): e881-e888. [20] Byrne D, English JC, Atkar-Khattra S, et al. Cystic primary lung cancer: evolution of computed tomography imaging morphology over time [J]. J Thorac Imaging, 2021, 36(6): 373-381. [21] 杨亚茹, 何慧, 薛松, 等. 囊腔型肺癌的CT特征动态变化及病理对照分析[J] , 中国医学影像学杂志, 2021, 29(7): 682-686. YANG Yaru, HE Hui, XUE Song, et al. CT serial findings and pathological features of cystic lung cancer: a comparative study [J]. Chinese Journal of Medical Imaging, 2021, 29(7): 682-686. [22] Shen Y, Zhang Y, Guo Y, et al. Prognosis of lung cancer associated with cystic airspaces: a propensity score matching analysis [J]. Lung Cancer, 2021, 159: 111-116. doi: 10.1016/j.lungcan.2021.07.003. [23] Ma Z, Wang S, Zhu H, et al. Comprehensive investigation of lung cancer associated with cystic airspaces: predictive value of morphology [J]. Eur J Cardiothorac Surg, 2022, 62(5): ezac297. doi: 10.1093/ejcts/ezac297. [24] Avanzo M, Wei L, Stancanello J, et al. Machine and deep learning methods for radiomics [J]. Med Phys, 2020, 47(5): e185-e202. [25] 李嘉威, 李夏东, 陈雪琴, 等. CT影像组学在肺癌诊治中应用的研究进展和问题探索[J] , 中国肺癌杂志, 2020, 23(10): 904-908. LI Jiawei, LI Xiadong, CHEN Xueqin, et al. Research advances and obstacles of CT-based radiomics in diagnosis and treatment of lung cancer [J]. Chinese Journal of Lung Cancer, 2020, 23(10): 904-908. |
[1] | 靳新娟,左立平,邓展昊,李安宁,于德新. MRI影像组学对135例肝癌耐药蛋白PFKFB3的预测价值[J]. 山东大学学报 (医学版), 2023, 61(6): 79-86. |
[2] | 刘艳,冷珊珊,夏晓娜,董昊,黄陈翠,孟祥水. 基于影像组学参数评估376例幕上自发性脑出血患者的功能状态[J]. 山东大学学报 (医学版), 2023, 61(5): 59-67. |
[3] | 朱正阳,沈靖菲,陈思璇,叶梅萍,杨惠泉,周佳南,梁雪,张鑫,张冰. 磁敏感加权成像不同影像组学模型预测胶质瘤IDH基因突变[J]. 山东大学学报 (医学版), 2023, 61(12): 44-50. |
[4] | 焦光丽,石子馨,陈蓉,宋亚博,杨飞,崔书君. 基于增强CT影像组学预测卵巢癌患者铂类药物敏感性[J]. 山东大学学报 (医学版), 2023, 61(12): 62-69. |
[5] | 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. |
[6] | 袁宏涛,纪淙山,康冰,秦松楠,于鑫鑫,高琳,王锡明. CT影像组学对肾上腺乏脂腺瘤与结节样增生的诊断价值[J]. 山东大学学报 (医学版), 2022, 60(4): 68-75. |
[7] | 王颖,顾慧,于鑫鑫,胡锦卓,王箬芃,王锡明. 71例腹主动脉瘤的基线CT特征与病变进展的相关性[J]. 山东大学学报 (医学版), 2022, 60(10): 62-67. |
[8] | 张嘉豪,刘东旭. 70例不同垂直骨面型骨性Ⅱ类错牙合磨牙及基骨横向特征[J]. 山东大学学报 (医学版), 2021, 59(2): 76-82. |
[9] | 宋珍珍,孙小玲,李海鸥,王芳,张冉,于德新. 120例胶质瘤及瘤周水肿MRI影像组学在评估肿瘤复发中的价值[J]. 山东大学学报 (医学版), 2021, 59(11): 53-60. |
[10] | 齐萌,黄燕,吴珊珊,刘波,张思伟. 单能量去金属伪影算法重建效果的系统评价及Meta分析[J]. 山东大学学报 (医学版), 2018, 56(9): 59-64. |
[11] | 狄钰,阎磊,杨飞龙,李大伟,徐忠华. 髓质海绵肾结石的计算机断层扫描、静脉肾盂造影表现[J]. 山东大学学报 (医学版), 2018, 56(3): 60-65. |
[12] | 王维军,周宁全,王超. CT定位微创徒手穿刺软通道技术治疗中等量高血压脑出血68例[J]. 山东大学学报(医学版), 2017, 55(5): 61-65. |
[13] | 戴建建,袁冰,张颖,林琦,袁苑,韩明勇. CT引导下125I粒子植入治疗Ⅲ期非小细胞肺癌疗效与并发症的临床观察[J]. 山东大学学报(医学版), 2017, 55(2): 32-37. |
[14] | 孟祥水,柴相君,马祥兴,任庆国,杨志成. CT、MRI对喉癌治疗方案选择的价值[J]. 山东大学学报(医学版), 2016, 54(10): 76-79. |
[15] | 刘青, 商蒙蒙, 孙霄, 李杰, 杨杰, 时丹丹, 宁松. 泌尿系结石化学成分对超声声影强弱的影响[J]. 山东大学学报(医学版), 2015, 53(9): 19-23. |
|