切换至 "中华医学电子期刊资源库"

中华消化病与影像杂志(电子版) ›› 2021, Vol. 11 ›› Issue (03) : 111 -116. doi: 10.3877/cma.j.issn.2095-2015.2021.03.003

所属专题: 文献

临床研究

基于多参数MRI影像组学模型预测直肠腺瘤癌变的研究
李盼盼1, 贾玉萍2, 吴瑞3, 洪宇2, 宋歌声4, 李爱银4,()   
  1. 1. 250014 济南,山东第一医科大学第一附属医院(山东省千佛山医院)影像科;250012 济南,山东大学临床医学院
    2. 250000 济南,山东第一医科大学研究生院
    3. 250012 济南,山东大学临床医学院
    4. 250014 济南,山东第一医科大学第一附属医院(山东省千佛山医院)影像科
  • 收稿日期:2020-12-04 出版日期:2021-06-01
  • 通信作者: 李爱银
  • 基金资助:
    济南市科技计划(201907034)

A Multiparametric MRI-Based Machine Learning Model for Preoperatively Prediction of canceration ofrectal adenoma based on multi-parameter MRI imaging omics model

Panpan Li1, Yuping Jia2, Rui Wu3, Yu Hong2, Gesheng Song4, Aiyin Li4,()   

  1. 1. Department of Radiology, First Affiliated Hospital of Shandong First Medical University&Shandong Provincial Qianfoshan Hospital, Jinan 250014, China; School of Clinical Medicine, Shandong University, Jinan 250012, China
    2. Graduate School, Shandong First Medical University, Jinan 250000, China
    3. School of Clinical Medicine, Shandong University, Jinan 250012, China
    4. Department of Radiology, First Affiliated Hospital of Shandong First Medical University&Shandong Provincial Qianfoshan Hospital, Jinan 250014, China
  • Received:2020-12-04 Published:2021-06-01
  • Corresponding author: Aiyin Li
引用本文:

李盼盼, 贾玉萍, 吴瑞, 洪宇, 宋歌声, 李爱银. 基于多参数MRI影像组学模型预测直肠腺瘤癌变的研究[J/OL]. 中华消化病与影像杂志(电子版), 2021, 11(03): 111-116.

Panpan Li, Yuping Jia, Rui Wu, Yu Hong, Gesheng Song, Aiyin Li. A Multiparametric MRI-Based Machine Learning Model for Preoperatively Prediction of canceration ofrectal adenoma based on multi-parameter MRI imaging omics model[J/OL]. Chinese Journal of Digestion and Medical Imageology(Electronic Edition), 2021, 11(03): 111-116.

目的

基于多参数MRI影像组学模型预测直肠腺瘤癌变。

方法

回顾性分析山东省千佛山医院2016年11月至2018年12月46例经病理证实为直肠腺瘤(n=25)和直肠腺瘤癌变患者(n=21)。所有患者均在术前2周接受盆腔MRI检查,包括高分辨率T2WI序列及弥散加权成像序列(DWI)。通过RadCloud v2.2平台分别从高分辨率T2WI和DWI序列中提取1396个影像组学特征。采用LASSO算法从1396个T2WI特征、1396个DWI特征及2792个联合特征(T2WI序列和DWI序列)中筛选直肠腺瘤癌变相关特征。采用Logistic regression(LR)算法和五折交叉验证构建三个影像组学预测模型:模型1(T2WI)、模型2(DWI)、模型3(T2WI+DWI)。通过准确度、敏感度、特异度和曲线下面积(AUC)评估影像组学模型的预测性能。

结果

三个影像组学模型预测直肠腺瘤癌变的AUC分别为0.80、0.84、0.92,模型3的诊断效能最优。模型3的准确度、敏感度、特异度分别为0.85、0.81、0.88。

结论

基于多参数MRI的影像组学模型具有预测直肠腺瘤癌变的潜力,联合高分辨率T2WI及DWI序列比单一序列预测效能更佳。

Objective

To predictthe canceration of rectal adenoma based on multi-parameter MRI imaging omics model.

Methods

A total of 46 patients with rectal adenoma (n=25) and cancerous rectal adenoma (n=21) confirmed by pathology from November 2016 to December 2018 in Shandong Provincial Qianfoshan Hospital were retrospectively analyzed. All patients underwent pelvic MRI examination 2 weeks before surgery, including high-resolution T2WI and diffusion-weighted imaging (DWI). A total of 1396 image omics features were extracted from the high-resolutionT2WI and DWI sequences respectively by RadCloud v2.2 platform. The least absolute shrinkageand selection operator (LASSO) wasused toscreen cancer-related features ofrectal adenomafrom 1396 T2WI features, 1396 DWI features and 2792 combined features (T2WI sequence and DWI sequence). Logistic regression (LR) algorithm and5-fold cross-validation were used to construct three imaging omics predictionmodels: Model 1(T2WI), Model 2(DWI) and Model 3(T2WI+ DWI). The diagnostic performance of the imaging omics modelwas evaluated by accuracy, sensitivity, specificity and area under the curve (AUC).

Results

The AUC of Model 1, Model 2 and Model 3was0.80, 0.84, 0.92 respectively. Model 3 showed the best predictive performance. The accuracy, sensitivity and specificity of Model 3were0.85, 0.81, 0.88 respectively.

Conclusion

Maging omics model based on multi-parameterMRI hasthe potential to predict canceration of rectal adenoma, and combination of high resolutionT2WI and DWI sequence is more effective than single sequence in predicting canceration.

表1 扫描序列和参数
图1 57岁的直肠腺瘤癌变患者ROI选择示例
表2 直肠腺瘤和腺瘤癌变的患者的临床特征
图2 使用LASSO回归模型从1396 HR-T2WI(a),1396 DWI(b)和2792联合特征(c)中选择的特征
图3 使用LASSO回归模型从1396 HR-T2WI特征(a),1396 DWI特征(b)和2792联合特征(c)中筛选出5、7、11个最佳特征以及每个特征对应的回归系数
图4 使用LR算法建立的模型1(a),模型2(b),模型3(c)的ROC曲线
表3 不同预测模型的诊断性能
1
Ferlay J, Colombet M, Soerjomataram I,et al.Estimating the global cancer incidence and mortality in 2018:GLOBOCAN sources and methods[J].Int J Cancer,2019,144(8): 1941-1953.
2
Ferlay J, Soerjomataram I, Dikshit R,et al.Cancer incidence and mortality worldwide:sources,methods and major patterns in GLOBOCAN 2012[J].Int J Cancer,2015,136(5): E359-386.
3
Pasha HF, Radwan MI, Yehia AM.Circulating methylated RUNX3 and SFRP1 genes as a noninvasive panel for early detection of colorectal cancer[J].Eur J Gastroenterol Hepatol,2019,31(11): 1342-1349.
4
Wang X, Kuang YY.Advances in epigenetic biomarker research in colorectal cancer[J].World J Gastroenterol,2014,20(15): 4276-4287.
5
Xue VW, Cheung MT, Chan PT,et al.Non-invasive Potential Circulating mRNA Markers for Colorectal Adenoma Using Targeted Sequencing[J].Sci Rep,2019,9(1): 12943.
6
Soto Y, Limia CM, González L,et al.Molecular evidence of high-risk human papillomavirus infection in colorectal tumours from Cuban patients[J].Memórias do Instituto Oswaldo Cruz,2016,111(12): 731-736.
7
Enquist IB, Good Z, Jubb AM,et al.Lymph node-independent liver metastasis in a model of metastatic colorectal cancer[J].Nature Communications,2014,5: 3530.
8
Jin Y, Yao L, Zhou P,et al.Risk analysis of the canceration of colorectal large polyps[J].Zhonghua wei chang wai ke za zhi,2018,21(10): 1161-1166.
9
Gillies RJ, Kinahan PE, Hricak H.Radiomics:Images Are More than Pictures,They Are Data[J]. Radiology,2016,278(2): 563-577.
10
Liang C, Huang Y, He L,et al.The development and validation of a CT-based radiomics signature for the preoperative discrimination of stage I-II and stage III-IV colorectal cancer[J].Oncotarget,2016,7(21): 31401-31412.
11
Huang YQ, Liang CH, He L,et al.Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer[J].J Clin Oncol,2016,34(18): 2157-2164.
12
张晓燕,朱海涛,王林,等.基于MRI影像组学模型预测局部进展期直肠癌新辅助放化疗后淋巴结状态的研究[J].中华放射学杂志,2017,51(12): 926-932.
13
董锐增,莫善兢,蔡宏.大肠腺瘤癌变研究进展[J].实用肿瘤杂志,2004,19(1): 80-83.
14
范娣,王德延.肿瘤病理诊断学(上册)[M].2版.天津:天津科学技术出版社,1999:845-847.
15
MUTO T, BUSSEY HJ.The evolution of cancer of the colon and rectum[J].Cancer,1975,36(6): 2251-2270.
16
仲光熙,吕珂,戴晴,等.直肠腔内超声弹性成像在直肠腺瘤恶变诊断中的价值[J/OL].中华医学超声杂志(电子版),2015,(3): 211-217.
17
Liu G.Role of miRNA in transformation from normal tissue to colorectal adenoma and cancer[J].Cancer Res Ther 2019,15: 278-285.
18
Lubner MG, Stabo N, Lubner SJ,et al.CT textural analysis of hepatic metastatic colorectal cancer:pre-treatment tumor heterogeneity correlates with pathology and clinical outcomes[J].Abdominal Imaging,2015,40(7): 2331-2337.
19
Huang Y, He L, Dong D,et al.Individualized prediction of perineural invasion in colorectal cancer:development and validation of a radiomics prediction model[J].Chin J Cancer Res,2018,30(1): 40-50.
20
Kudou M, Nakanishi M, Kuriu Y,et al.Value of intra-tumor heterogeneity evaluated by diffusion-weighted MRI for predicting pathological stages and therapeutic responses to chemoradiotherapy in lower rectal cancer[J].J Cancer,2020,11(1): 168-176.
21
Liang M, Cai Z, Zhang H,et al.Machine Learning-based Analysis of Rectal Cancer MRI Radiomics for Prediction of Metachronous Liver Metastasis[J].Acad Radiol,2019,26(11): 1495-1504.
[1] 洪玮, 叶细容, 刘枝红, 杨银凤, 吕志红. 超声影像组学联合临床病理特征预测乳腺癌新辅助化疗完全病理缓解的价值[J/OL]. 中华医学超声杂志(电子版), 2024, 21(06): 571-579.
[2] 杨倩, 李秋洋, 李楠, 罗渝昆, 唐杰. 基于超声纹理影像转录组学预测前列腺癌[J/OL]. 中华医学超声杂志(电子版), 2024, 21(03): 319-326.
[3] 张茜, 陈佳慧, 高雪萌, 赵傲雪, 黄瑛. 基于高帧频超声造影的影像组学特征鉴别诊断甲状腺结节良恶性的价值[J/OL]. 中华医学超声杂志(电子版), 2023, 20(09): 895-903.
[4] 邱琳, 刘锦辉, 组木热提·吐尔洪, 马悦心, 冷晓玲. 超声影像组学对致密型乳腺背景中非肿块型乳腺癌的诊断价值[J/OL]. 中华乳腺病杂志(电子版), 2024, 18(06): 353-360.
[5] 唐玮, 何融泉, 黄素宁. 深度学习在乳腺癌影像诊疗和预后预测中的应用[J/OL]. 中华乳腺病杂志(电子版), 2023, 17(06): 323-328.
[6] 吴佩琪. 乳腺癌瘤周影像组学研究进展[J/OL]. 中华乳腺病杂志(电子版), 2023, 17(05): 301-304.
[7] 杨勇军, 曾一鸣, 贺显雅, 卢强, 李远伟. ASA分级≥Ⅲ级患者局麻经会阴前列腺多模态影像融合穿刺的安全性和有效性[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(05): 441-447.
[8] 梁健, 何京伟, 关文峰, 梁其炎, 冯能卓, 黄亦欣, 覃文超. 多参数MRI与超声认知融合引导下前列腺靶向穿刺的前瞻性研究[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2023, 17(06): 558-562.
[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] 田娜, 韩飞天. 基于CT平扫影像组学模型与系统免疫炎症指数预测急性胰腺炎复发模型的建立[J/OL]. 中华消化病与影像杂志(电子版), 2024, 14(04): 355-359.
[11] 刘伟, 高续, 谢玉海, 蒋哲, 刘士成. 基于增强CT影像组学模型在预测急性胰腺炎复发中的应用价值[J/OL]. 中华消化病与影像杂志(电子版), 2024, 14(04): 348-354.
[12] 张志远, 李雯雯, 王帅, 古娇娇, 高佳茹, 贾琳娇, 李文涛. 超声影像组学在乳腺肿瘤中的应用进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(01): 87-90.
[13] 王林源, 熊鑫, 杨坤, 邓勇志. 基于冠状动脉CT血管成像的影像组学列线图鉴别诊断易损斑块的价值[J/OL]. 中华诊断学电子杂志, 2024, 12(01): 1-8.
[14] 刘云泽, 李宬润, 任红, 郭俊唐, 刘阳. CT影像组学在肺结节鉴别诊断中的价值[J/OL]. 中华胸部外科电子杂志, 2024, 11(02): 120-129.
[15] 于乐林, 尚海龙, 杜红娣, 王莺, 王一超, 徐长贺, 叶娟, 赵世伟, 郑芳慧, 沈慧, 沈海林. 基于CT平扫的影像组学特征预测急性大脑中动脉闭塞机械取栓术后造影剂外渗的价值[J/OL]. 中华脑血管病杂志(电子版), 2024, 18(03): 215-223.
阅读次数
全文


摘要