基于增强CT影像组学技术在术前预测结直肠癌错配修复系统分型中的应用

doi:10.3969/j.issn.1674-490X.2025.01.004

摘要/Abstract

摘要： 目的建立基于增强CT影像组学特征与临床特征的联合多种机器学习模型,比较其术前预测结直肠癌(colorectal cancer, CRC)患者错配修复系统(mismatch repair, MMR)分型模型的效能。方法回顾性收集来自河北北方学院附属第一医院120例CRC患者的临床及影像学资料,将其按照7∶3随机分为训练集和验证集。于增强CT门静脉期绘制感兴趣区(region of interest, ROI),并提取影像组学特征选择最优集合。对于临床资料使用统计学方法进行分析。采用受试者操作特征曲线下面积(area under the curve, AUC)、敏感性、准确率、特异度及F1评分评估模型的诊断效能,并绘制校准及决策曲线。结果 3种算法中根据影像组学特征与临床参数特征相联合所建立的影像组学特征-临床参数特征联合模型(简称影像-临床联合模型)的效能高于其他模型。其中影像-临床联合模型中的逻辑回归算法展现了较高的性能,其验证集逻辑回归算法AUC为0.93(95% CI=0.89~0.96),支持向量机算法的AUC为0.91(95%CI=0.83~0.98),随机森林算法的AUC值为0.91(95% CI=0.73~0.97)。结论应用基于增强CT图像所建立的影像-临床联合模型可以有效鉴别CRC的MMR分型。

关键词: 结直肠癌, 错配修复系统, 影像组学, 机器学习, 逻辑回归

Abstract: Objective To establish a multi-component machine learning model based on enhanced CT radiomics features and clinical features and compare the performance of the preoperative prediction of Mismatch Repair(MMR)typing model in colorectal cancer(CRC)patients. Methods The clinical and imaging data of 120 colorectal cancer patients from the First Affiliated Hospital of Hebei North University were retrospectively collected, and they were randomly divided into training group and validation group according to 7∶3. The Region of Interest(ROI)was drawn during the portal vein phase of enhanced CT, and the radiomics features were extracted to select the optimal set. Clinical data were analysed using statistical methods. The area under the receiver operating characteristic curve(AUC), sensitivity, accuracy, specificity and FI score were used to evaluate the diagnostic performance of the model, and the calibration and decision curves were plotted. Results The performance of the radiomics features-clinical parameters combined model(hereinafter referred to as the radiomics-clinical combined model, established by combining radiomics features with clinical parameters in 3 algorithms was higher than that of other models. Among them, the logistic regression algorithm in the radiomicsinical combined model showed high performance, with an AUC value of 0.93(95% CI=0.89~0.96)in the validation set, an AUC value of 0.91(95% CI=0.83~0.98)the support vector machine algorithm, and an AUC value of 0.91(95% CI=0.73~0.97)for the random forest algorithm. Conclusion The image-proximity joint model based on enhanced CT images can effectively identify the MMR typing of CRC.

Key words: colorectal cancer, mismatch repair systems, radiomics, machine learning, logistic regression

中图分类号:

王梓萌,王文江,常霄,王磊,王大伟,崔书君. 基于增强CT影像组学技术在术前预测结直肠癌错配修复系统分型中的应用[J]. 医学研究与教育, 2025, 42(1): 35-45.

参考文献

[1] BUCCAFUSCA G, PROSERPIO I, TRALONGO A C, et al. Early colorectal cancer: diagnosis, treatment and survivorship care[J]. Crit Rev Oncol Hematol, 2019, 136: 20-30. DOI: 10.1016/j.critrevonc.2019.01.023.
[2] SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2020[J]. CA Cancer J Clin, 2020, 70(1): 7-30. DOI: 10.3322/caac.21590.
[3] ARNOLD M, SIERRA M S, LAVERSANNE M, et al. Global patterns and trends in colorectal cancer incidence and mortality[J]. Gut, 2017, 66(4): 683-691. DOI: 10.1136/gutjnl-2015-310912.
[4] 舒密,南琼.间期大肠癌临床和分子学特征的研究进展[J].医学研究生学报, 2018, 31(9): 1005-1008. DOI: 10.16571/j.cnki.1008-8199.2018.09.022.
[5] TOH J W T, PHAN K, REZA F, et al. Rate of dissemination and prognosis in early and advanced stage colorectal cancer based on microsatellite instability status: systematic review and meta-analysis[J]. Int J Colorectal Dis, 2021, 36(8): 1573-1596. DOI: 10.1007/s00384-021-03874-1.
[6] BENSON A B, VENOOK A P, AL-HAWARY M M, et al. NCCN guidelines insights: colon cancer, version 2.2018[J]. J Natl Compr Canc Netw, 2018, 16(4): 359-369. DOI: 10.6004/jnccn.2018.0021.
[7] LUCHINI C, BIBEAU F, LIGTENBERG M J L, et al. ESMO recommendations on microsatellite instability testing for immunotherapy in cancer, and its relationship with PD-1/PD-L1 expression and tumour mutational burden: a systematic review-based approach[J]. Ann Oncol, 2019, 30(8): 1232-1243. DOI: 10.1093/annonc/mdz116.
[8] ANJOMSHOAA A, NASRI S, HUMAR B, et al. Slow proliferation as a biological feature of colorectal cancer metastasis[J]. Br J Cancer, 2009, 101(5): 822-828. DOI: 10.1038/sj.bjc.6605229.
[9] MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[10] MEROK M A, AHLQUIST T, RØYRVIK E C, et al. Microsatellite instability has a positive prognostic impact on stage Ⅱ colorectal cancer after complete resection: results from a large, consecutive Norwegian series[J]. Ann Oncol, 2013, 24(5): 1274-1282. DOI: 10.1093/annonc/mds614.
[11] YING M L, PAN J F, LU G H, et al. Development and validation of a radiomics-based nomogram for the preoperative prediction of microsatellite instability in colorectal cancer[J]. BMC Cancer, 2022, 22(1): 524. DOI: 10.1186/s12885-022-09584-3.
[12] CAO W, HU H, GUO J, et al. CT-based deep learning model for the prediction of DNA mismatch repair deficient colorectal cancer: a diagnostic study[J]. J Transl Med, 2023, 21(1): 214. DOI: 10.1186/s12967-023-04023-8.
[13] WANG Q, XU J, WANG A, et al. Systematic review of machine learning-based radiomics approach for predicting microsatellite instability status in colorectal cancer[J]. Radiol Med, 2023, 128(2): 136-148. DOI: 10.1007/s11547-023-01593-x.
[14] GOLIA PERNICKA J S, GAGNIERE J, CHAKRABORTY J, et al. Radiomics-based prediction of microsatellite instability in colorectal cancer at initial computed tomography evaluation[J]. Abdom Radiol(NY), 2019, 44(11): 3755-3763. DOI: 10.1007/s00261-019-02117-w.
[15] FAN S X, LI X B, CUI X N, et al. Computed tomography-based radiomic features could potentially predict microsatellite instability status in stage Ⅱ colorectal cancer: a preliminary study[J]. Acad Radiol, 2019, 26(12): 1633-1640. DOI: 10.1016/j.acra.2019.02.009.
[16] WU J J, ZHANG Q H, ZHAO Y, et al. Radiomics analysis of iodine-based material decomposition images with dual-energy computed tomography imaging for preoperatively predicting microsatellite instability status in colorectal cancer[J]. Front Oncol, 2019, 9: 1250. DOI: 10.3389/fonc.2019.01250.
[17] WANG X H, LIU Z Q, YIN X P, et al. A radiomics model fusing clinical features to predict microsatellite status preoperatively in colorectal cancer liver metastasis[J]. BMC Gastroenterol, 2023, 23(1): 308. DOI: 10.1186/s12876-023-02922-0.
[18] 陈渝宏,杨彪,廖正银.免疫治疗相关生物标志物在消化道肿瘤中的应用[J].中国肿瘤临床, 2022, 49(12): 631-635. DOI: 10.12354/j.issn.1000-8179.2022.20211501.
[19] PRICE T J, BEEKE C, ULLAH S, et al. Does the primary site of colorectal cancer impact outcomes for patients with metastatic disease? [J]. Cancer, 2015, 121(6): 830-835. DOI: 10.1002/cncr.29129.
[20] LOUPAKIS F, YANG D Y, YAU L, et al. Primary tumor location as a prognostic factor in metastatic colorectal cancer[J]. J Natl Cancer Inst, 2015, 107(3): dju427. DOI: 10.1093/jnci/dju427.
[21] ZAANAN A, SHI Q, TAIEB J, et al. Role of deficient DNA mismatch repair status in patients with stage Ⅲ colon cancer treated with FOLFOX adjuvant chemotherapy: a pooled analysis from 2 randomized clinical trials[J]. JAMA Oncol, 2018, 4(3): 379-383. DOI: 10.1001/jamaoncol.2017.2899.
[22] RIBIC C M, SARGENT D J, MOORE M J, et al. Tumor microsatellite-instability status as a predictor of benefit from fluorouracil-based adjuvant chemotherapy for colon cancer[J]. N Engl J Med, 2003, 349(3): 247-257. DOI: 10.1056/NEJMoa022289.
[23] SHULMAN K, BARNETT-GRINESS O, FRIEDMAN V, et al. Outcomes of chemotherapy for microsatellite instable-high metastatic colorectal cancers[J]. JCO Precis Oncol, 2018, 2: PO.17.00253. DOI: 10.1200/PO.17.00253.
[24] SARGENT D J, MARSONI S, MONGES G, et al. Defective mismatch repair as a predictive marker for lack of efficacy of fluorouracil-based adjuvant therapy in colon cancer[J]. J Clin Oncol, 2010, 28(20): 3219-3226. DOI: 10.1200/JCO.2009.27.1825.