基于CT影像组学模型预测人表皮生长因子受体-2弱阳性胃癌患者基因扩增的价值

doi:10.3877/cma.j.issn.2095-2015.2022.02.002

目的

探讨基于CT门脉期影像组学预测人表皮生长因子受体-2（HER-2）弱阳性胃癌患者基因扩增的可行性。

方法

回顾性分析2012年1月至2021年10月郑州大学第一附属医院收治的术后经免疫组织化学法（IHC）证实为HER-2（++），进一步行荧光原位杂交（FISH）检测的胃癌患者的CT图像，其中基因扩增38例，基因非扩增127例。使用放射组学软件对CT门脉期轴位最大层面图像上的病灶沿边缘勾画感兴趣区域（ROI）并提取特征。将165例数据按照2∶1的比例随机分配为训练集和测试集，采用随机森林法以较优特征参数在训练集上进行预测模型的搭建，并在测试集上进行验证，绘制相应受试者操作特征（ROC）曲线，以曲线下面积（AUC）、敏感度、特异度及准确性评价其鉴别效能，其中ROC曲线的最佳截断值采用约登指数进行判断。

结果

经特征选择，共筛选出4个具有较高价值的影像组学特征参数预测HER-2弱阳性胃癌患者基因扩增，训练组中AUC为0.904[95%CI（0.845，0.955）]，验证组中AUC为0.751[95%CI（0.636，0.862）]，其中在最佳截断值处预测HER-2弱阳性胃癌患者基因扩增的敏感度为0.667，特异度为0.800。

结论

基于随机森林的CT门脉期影像组学作为一种简便、无创的非侵入性检测方法，可用于预测HER-2弱阳性患者是否出现基因扩增，鉴别效能较高，可为临床决策和个体化治疗提供依据。

关键词: 胃癌, 诊断, 人表皮生长因子受体2, 基因扩增, 计算机体层成像, 影像组学

Objective

To explore the feasibility of predicting gene amplification in patients with human epidermal growth factor receptor 2 (HER-2) weakly positive gastric cancer based on CT portal phase imaging.

Methods

The CT images of patients with gastric cancer confirmed by immunohistochemistry (IHC) as HER-2 (++) and further detected by fluorescence in situ hybridization (FISH) from January 2012 to October 2021 in the First Affiliated Hospital of Zhengzhou University were analyzed retrospectively, including 38 cases of gene amplification and 127 cases of non gene amplification. The region of interest (ROI) of the lesions on the axial maximum slice image of CT portal phase was outlined along the edge using the radiomics software and the features were extracted. One hundred and sixty-five cases of data were randomly divided into training set and test set according to the ratio of 2:1. The random forest method was used to build the prediction model on the training set with better characteristic parameters, and the model was verified on the test set. The corresponding receiver operating characteristic (ROC) curve was drawn, and the identification efficiency was evaluated by the area under the curve (AUC), sensitivity, specificity and accuracy. The best cut-off value of ROC curve was judged by Youden index.

Results

After feature selection, a total of four high-value omics characteristic parameters were selected to predict gene amplification in patients with HER-2 weakly positive gastric cancer. The AUC value in the training group was 0.904 [95%CI (0.845, 0.955)], and the AUC value in the validation group was 0.751 [95%CI (0.636, 0.862)]. The sensitivity and specificity of predicting gene amplification in patients with HER-2 weakly positive gastric cancer at the best cut-off value were 0.667 and 0.800.

Conclusion

Random forest-based CT portal phase imaging histology can be used as a simple and non-invasive test to predict the presence of gene amplification in patients with weakly positive HER-2 with high discriminatory performance, which can provide a basis for clinical decision making and individualized treatment.

Key words: Gastric cancer, Diagnosis, Human epidermal growth factor receptor 2, Gene amplification, Computed tomography, Radiomics

图1 患者，男性，52岁，贲门腺癌，中分化，浸润肌层。图A为门脉期轴位CT扫描显示贲门胃壁局限性增厚，边缘尚光整；图B为手工勾画ROI示意图；图C为FISH检测结果显示HER-2基因无扩增（×1000）

图2 患者，男性，71岁，贲门腺癌，中-低分化，浸润全层。图A为门脉期轴位CT扫描显示贲门胃壁不规则增厚，边界不清；图B为手工勾画ROI示意图；图C为FISH检测结果显示HER-2基因扩增（×1000）

图3 ROC曲线

表1 两组患者一般临床资料比较

指标		HER-2扩增组（n=38）	HER-2无扩增组（n=127）	统计值	P值
年龄（±s，岁）		63.5±10.3	56.7±11.1	t=3.366	0.001
性别（男性/女性，例）		31/7	88/39	χ²=2.196	0.138
部位（例）				χ²=9.443	0.224
	贲门胃底	24	50
	胃体	8	29
	胃窦	3	38
	累及2个部位及以上	3	10
T分期（例）				χ²=0.609	0.435^a
	T1	5	19
	T2	7	13
	T3	2	3
	T4	24	92
分化程度（例）				χ²=2.177	0.337
	中分化	14	36
	中-低分化	12	34
	低分化	12	57

表1 两组患者一般临床资料比较

指标		HER-2扩增组（n=38）	HER-2无扩增组（n=127）	统计值	P值
年龄（±s，岁）		63.5±10.3	56.7±11.1	t=3.366	0.001
性别（男性/女性，例）		31/7	88/39	χ²=2.196	0.138
部位（例）				χ²=9.443	0.224
	贲门胃底	24	50
	胃体	8	29
	胃窦	3	38
	累及2个部位及以上	3	10
T分期（例）				χ²=0.609	0.435^a
	T1	5	19
	T2	7	13
	T3	2	3
	T4	24	92
分化程度（例）				χ²=2.177	0.337
	中分化	14	36
	中-低分化	12	34
	低分化	12	57

表2 随机森林模型中各特征的重要性系数

特征名称	重要性系数
wavelet-LHH_glszm_HighGrayLevelZoneEmphasis	0.296
wavelet-LHH_glszm_LowGrayLevelZoneEmphasis	0.285
wavelet-LHL_glcm_Correlation	0.194
wavelet-LHL_glszm_SizeZoneNonUniformity	0.225

表2 随机森林模型中各特征的重要性系数

特征名称	重要性系数
wavelet-LHH_glszm_HighGrayLevelZoneEmphasis	0.296
wavelet-LHH_glszm_LowGrayLevelZoneEmphasis	0.285
wavelet-LHL_glcm_Correlation	0.194
wavelet-LHL_glszm_SizeZoneNonUniformity	0.225

图4 各特征的小提琴图比较

1	周岩冰.食管胃结合部腺癌当前临床研究开展现状与挑战[J].中华胃肠外科杂志, 2019, 22(2): 112-118.
2	Bartley AN, Washington MK, Ventura CB, et al. HER2 Testing and Clinical Decision Making in Gastroesophageal Adenocarcinoma: Guideline From the College of American Pathologists, American Society for Clinical Pathology, and American Society of Clinical Oncology [J]. Am J Clin Pathol, 2016, 146(6): 647-669.
3	池苗苗,戴飞飞,王亚坤,等. Her-2表达在食管胃结合部腺癌中的作用研究进展[J].中国肿瘤, 2015, 24(1): 49-52.
4	Chang X, Guo X, Li X, et al. Potential Value of Radiomics in the Identification of Stage T3 and T4a Esophagogastric Junction Adenocarcinoma Based on Contrast-Enhanced CT Images [J]. Front Oncol, 2021, 11: 627947.
5	Bodalal Z, Trebeschi S, Nguyen-Kim TDL, et al. Radiogenomics: bridging imaging and genomics [J]. Abdom Radiol (NY), 2019, 44(6): 1960-1984.
6	Kursa MB, Rudnicki WR. Feature Selection with Boruta Package [J]. J Stat Software, 2010, 36(11): 1-13.
7	Global Burden of Disease Cancer Collaboration, Fitzmaurice C, Abate D, et al. Global, Regional, and National Cancer Incidence, Mortality, Years of Life Lost, Years Lived With Disability, and Disability-Adjusted Life-Years for 29 Cancer Groups, 1990 to 2017: A Systematic Analysis for the Global Burden of Disease Study [J]. JAMA Oncol, 2019, 5(12): 1749-1768.
8	Petryszyn P, Chapelle N, Matysiak-Budnik T. Gastric Cancer: Where Are We Heading? [J]. Dig Dis, 2020, 38(4): 280-285.
9	李源,吴钟华,林嗣涵,等.胃癌分子生物学研究现状[J].中国实用外科杂志, 2021, 41(1): 66-71.
10	Boku N. HER2-positive gastric cancer [J]. Gastric Cancer, 2014, 17(1): 1-12.
11	Meric-Bernstam F, Johnson AM, Dumbrava EEI, et al. Advances in HER2-Targeted Therapy: Novel Agents and Opportunities Beyond Breast and Gastric Cancer [J]. Clin Cancer Res, 2019, 25(7): 2033-2041.
12	Bang YJ, Van Cutsem E, Feyereislova A, et al. Trastuzumab in combination with chemotherapy versus chemotherapy alone for treatment of HER2-positive advanced gastric or gastro-oesophageal junction cancer (ToGA): a phase 3, open-label, randomised controlled trial [J]. Lancet, 2010, 376(9742): 687-697.
13	Gong J, Liu T, Fan Q, et al. Optimal regimen of trastuzumab in combination with oxaliplatin/capecitabine in first-line treatment of HER2-positive advanced gastric cancer (CGOG1001): a multicenter, phase Ⅱ trial [J]. BMC Cancer, 2016, 16: 68.
14	Rivera F, Romero C, Jimenez-Fonseca P, et al. Phase Ⅱ study to evaluate the efficacy of Trastuzumab in combination with Capecitabine and Oxaliplatin in first-line treatment of HER2-positive advanced gastric cancer: HERXO trial [J]. Cancer Chemother Pharmacol, 2019, 83(6): 1175-1181.
15	Hudis CA. Trastuzumab--mechanism of action and use in clinical practice [J]. N Engl J Med, 2007, 357(1): 39-51.
16	李琳,付尧,吴鸿雁,等.胃腺癌中c-MET、EGFR和HER-2的表达及其与临床病理特征的分析[J].临床与实验病理学杂志, 2019, 35(1): 6-10.
17	Bhandari A, Ibrahim M, Sharma C, et al. CT-based radiomics for differentiating renal tumours: a systematic review [J]. Abdom Radiol (NY), 2021, 46(5): 2052-2063.
18	Reginelli A, Nardone V, Giacobbe G, et al. Radiomics as a New Frontier of Imaging for Cancer Prognosis: A Narrative Review [J]. Diagnostics (Basel), 2021, 11(10): 1796.
19	Kotrotsou A, Zinn PO, Colen RR. Radiomics in Brain Tumors: An Emerging Technique for Characterization of Tumor Environment [J]. Magn Reson Imaging Clin N Am, 2016, 24(4): 719-729.
20	唐磊.进展期胃癌的影像学评估:从图像到大数据影像组学[J].中华胃肠外科杂志, 2018, 21(10): 1106-1112.
21	Lewis S, Hectors S, Taouli B. Radiomics of hepatocellular carcinoma [J]. Abdom Radiol (NY), 2021, 46(1): 111-123.
22	黄文鹏,刘思耘,李莉明,等.基于不同时相增强CT的影像组学对胰腺实性假乳头状肿瘤侵袭性行为的预测价值[J].中华放射学杂志, 2022, 56(1): 55-61.
23	Yang L, Dong D, Fang M, et al. Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer? [J]. Eur Radiol, 2018, 28(5): 2058-2067.
24	Bădescu A, Georgescu CV, Vere CC, et al. Correlations between Her2 oncoprotein, VEGF expression, MVD and clinicopathological parameters in gastric cancer [J]. Rom J Morphol Embryol, 2012, 53(4): 997-1005.
25	Chen C, Yang JM, Hu TT, et al. Prognostic role of human epidermal growth factor receptor in gastric cancer: a systematic review and meta-analysis [J]. Arch Med Res, 2013, 44(5): 380-389.
26	Gao X, Ma T, Cui J, et al. A CT-based Radiomics Model for Prediction of Lymph Node Metastasis in Early Stage Gastric Cancer [J]. Acad Radiol, 2021, 28(6): e155-e164.
27	Aggarwal A, Liu ML, Krasnow SH. Breast cancer in male veteran population: an analysis from VA cancer registry [J]. J Community Support Oncol, 2014, 12(8): 293-297.
28	Wang N, Wang X, Li W, et al. Contrast-Enhanced CT Parameters of Gastric Adenocarcinoma: Can Radiomic Features Be Surrogate Biomarkers for HER2 Over-Expression Status? [J]. Cancer Manag Res, 2020, 12: 1211-1219.
29	Li Y, Cheng Z, Gevaert O, et al. A CT-based radiomics nomogram for prediction of human epidermal growth factor receptor 2 status in patients with gastric cancer [J]. Chin J Cancer Res, 2020, 32(1): 62-71.
30	Wang Y, Yu Y, Han W, et al. CT Radiomics for Distinction of Human Epidermal Growth Factor Receptor 2 Negative Gastric Cancer [J]. Acad Radiol, 2021, 28(3): e86-e92.
31	Ahn SJ, Kim JH, Park SJ, et al. Prediction of the therapeutic response after FOLFOX and FOLFIRI treatment for patients with liver metastasis from colorectal cancer using computerized CT texture analysis [J]. Eur J Radiol, 2016, 85(10): 1867-1874.

[1]	王亚红, 蔡胜, 葛志通, 杨筱, 李建初. 颅骨骨膜窦的超声表现一例[J/OL]. 中华医学超声杂志（电子版）, 2024, 21(11): 1089-1091.
[2]	李刘庆, 陈小翔, 吕成余. 全腹腔镜与腹腔镜辅助远端胃癌根治术治疗进展期胃癌的近中期随访比较[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 23-26.
[3]	屈翔宇, 张懿刚, 李浩令, 邱天, 谈燚. USP24及其共表达肿瘤代谢基因在肝细胞癌中的诊断和预后预测作用[J/OL]. 中华普外科手术学杂志(电子版), 2024, 18(06): 659-662.
[4]	赵林娟, 吕婕, 王文胜, 马德茂, 侯涛. 超声引导下染色剂标记切缘的梭柱型和圆柱型保乳区段切除术的效果研究[J/OL]. 中华普外科手术学杂志(电子版), 2024, 18(06): 634-637.
[5]	熊鹰, 林敬莱, 白奇, 郭剑明, 王烁. 肾癌自动化病理诊断：AI离临床还有多远？[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(06): 535-540.
[6]	中华医学会器官移植学分会. 肝移植术后缺血性胆道病变诊断与治疗中国实践指南[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 739-748.
[7]	郑大雯, 王健东. 胆囊癌辅助诊断研究进展[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 769-773.
[8]	王秋生. 胆道良性疾病诊疗策略[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 779-782.
[9]	陆镜明, 韩大为, 任耀星, 黄天笑, 向俊西, 张谞丰, 吕毅, 王傅民. 基于术前影像组学的肝内胆管细胞癌淋巴结转移预测的系统性分析[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 852-858.
[10]	袁雨涵, 杨盛力. 体液和组织蛋白质组学分析在肝癌早期分子诊断中的研究进展[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 883-888.
[11]	李浩, 陈棋帅, 费发珠, 张宁伟, 李元东, 王硕晨, 任宾. 慢性肝病肝纤维化无创诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(09): 863-867.
[12]	谭瑞义. 小细胞骨肉瘤诊断及治疗研究现状与进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 781-784.
[13]	王子阳, 王宏宾, 刘晓旌. 血清标志物对甲胎蛋白阴性肝细胞癌诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 677-681.
[14]	陈慧, 邹祖鹏, 周田田, 张艺丹, 张海萍. 皮肤镜对头皮红斑性皮肤病辅助鉴别诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 692-698.
[15]	胡云鹤, 周玉焯, 付瑞瑛, 于凡, 李爱东. CHS-DRG付费制度下GB1分组住院费用影响因素分析与管理策略探讨[J/OL]. 中华临床医师杂志(电子版), 2024, 18(06): 568-574.

阅读次数

全文

摘要

选择文件类型/文献管理软件名称

选择包含的内容

Predictive value of gene amplification in patients with weakly human epidermal growth factor receptor 2 positive gastric cancer based on CT radiomics model

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

Predictive value of gene amplification in patients with weakly human epidermal growth factor receptor 2 positive gastric cancer based on CT radiomics model