融合增强CT影像组学与临床特征的机器学习模型预测宫颈鳞癌淋巴结转移的研究

doi:10.3969/j.issn.1004-616x.2026.02.006

摘要/Abstract

摘要： 目的： 构建基于融合CT影像组学与临床特征的机器学习模型用以预测宫颈鳞癌患者淋巴结转移。方法： 回顾性纳入2016年1月—2021年12月在汕头大学医学院附属肿瘤医院经病理证实为宫颈鳞癌并行宫颈癌根治术的患者。收集术前3周内的增强CT图像，通过对肿瘤区域的勾画以及影像学特征的提取和筛选，计算出影像组学评分(Radscore)，同时收集患者临床特征资料。利用临床特征及影像组学评分构建逻辑回归(Logistic)、线性判别分析(LDA)、支持向量机(SVM)及朴素贝叶斯4种机器学习模型，选取最佳预测模型。结果： 朴素贝叶斯模型展现了最优且最稳定的综合性能，曲线下面积(AUC)达到0.957。其他模型的AUC分别为：SVM为0.953,Logistic为0.943,LDA为0.941。朴素贝叶斯模型在测试集上同样取得了优异的准确率(0.819)、灵敏度(0.915)、特异度(0.727)和F1分数(0.889)。SHAP解释性分析明确了CA125是模型决策中最重要的预测因子。结论： 本研究开发并验证了一个性能优异的朴素贝叶斯预测模型，用以预测宫颈鳞癌患者淋巴结转移的风险。SHAP解释性分析进一步明确了CA125、CEA、FIGO分期和影像组学评分是关键预测因子，增强了模型的透明度和临床可信度。

关键词: 宫颈癌, 影像组学, 淋巴结转移, 机器学习

Abstract: OBJECTIVE: Radiomics and machine learning show great potential in oncology prediction and prognosis. This study aimed to develop a machine learning model integrating contrast-enhanced CT radiomics features and clinical characteristics to predict lymph node metastasis in cervical squamous cell carcinoma(CSCC) patients. METHODS: In this retrospective study, patients with pathologically confirmed CSCC who underwent radical hysterectomy at the Cancer Hospital of Shantou University Medical College between January 2016 and December 2021 were enrolled. Preoperative contrast-enhanced CT images obtained within three weeks before surgery were collected. A Radscore was calculated by delineating tumor volumes and extracting/selecting radiomic features. Clinical characteristics were also collected. Four machine learning modelsLogistic regression, LDA, SVM, and Naïve Bayes-were built using the clinical features and Radscore to identify the optimal predictive model. RESULTS: The Naive Bayes model demonstrated the best and most stable overall performance,achieving an AUC of 0.957. The AUCs for the other models were 0.953 for SVM,0.943 for Logistic regression, and 0.941 for LDA. On the test set, the Naive Bayes model also achieved excellent accuracy(0.819), sensitivity(0.915), specificity(0.727), and an F1-score(0.889). SHAP analysis identified CA-125 as the most important predictor in the model's decision-making. CONCLUSION: We successfully developed and validated a high-performance Naïve Bayes model for predicting lymph node metastasis risk in CSCC patients. SHAP interpretability analysis further confirmed CA-125,CEA,FIGO stage,and Radscore as key predictors,enhancing the model's transparency and clinical credibility.

Key words: cervical cancer, radiomics, lymph node metastasis, machine learning

中图分类号:

R737.33

杨永康, 吕昕琪, 周莉. 融合增强CT影像组学与临床特征的机器学习模型预测宫颈鳞癌淋巴结转移的研究[J]. 癌变·畸变·突变, 2026, 38(2): 119-127,136.

YANG Yongkang, LU Xinqi, ZHOU Li. A machine learning model integrating contrast-enhanced CT radiomics and clinical features for predicting lymph node metastasis in cervical squamous cell carcinoma[J]. Carcinogenesis, Teratogenesis & Mutagenesis, 2026, 38(2): 119-127,136.

参考文献

[1] WU J, JIN Q Y, ZHANG Y M, et al. Global burden of cervical cancer:current estimates, temporal trend and future projections based on the GLOBOCAN 2022[J]. J Natl Cancer Cent, 2025, 5(3):322-329.
[2] ZHENG R S, ZHANG S W, ZENG H M, et al. Cancer incidence and mortality in China, 2016[J]. J Natl Cancer Cent,2022, 2(1):1-9.
[3] 秦琳,吴玉梅,王明,等.增强CT淋巴结短径及SCC-Ag在术前预测宫颈鳞癌淋巴结转移中的应用[J].中国医药导报,2022, 19(5):124-128.
[4] MENG X, SONG S Y, LI K, et al. Application of CT in predicting lymph node metastasis in cervical cancer and construction of a preoperative nomogram[J]. Sci Rep, 2025, 15(1):11674.
[5] HATT M, LE REST C C, TIXIER F, et al. Radiomics:data are also images[J]. J Nucl Med, 2019, 60(Suppl 2):38S-44S.
[6] HU Y H, XIE C Y, YANG H, et al. Assessment of intratumoral and peritumoral computed tomography radiomics for predicting pathological complete response to neoadjuvant chemoradiation in patients with esophageal squamous cell carcinoma[J]. JAMA Netw Open, 2020, 3(9):e2015927.
[7] XIA T Y, ZHOU Z H, MENG X P, et al. Predicting microvascular invasion in hepatocellular carcinoma using CTbased radiomics model[J]. Radiology, 2023, 307(4):e222729.
[8] 周益民.基于影像组学和深度迁移学习的宫颈癌淋巴结转移预测研究[D].衡阳:南华大学, 2023.
[9] OCHI T, MURASE K, FUJII T, et al. Survival prediction using artificial neural networks in patients with uterine cervical cancer treated by radiation therapy alone[J]. Int J Clin Oncol,2002, 7(5):294-300.
[10] OBRZUT B, KUSY M, SEMCZUK A, et al. Prediction of5-year overall survival in cervical cancer patients treated with radical hysterectomy using computational intelligence methods[J]. BMC Cancer, 2017, 17(1):840.
[11] OBRZUT B, KUSY M, SEMCZUK A, et al. Prediction of10-year overall survival in patients with operable cervical cancer using a probabilistic neural network[J]. J Cancer, 2019,10(18):4189-4195.
[12] LUO Y, TSENG H H, CUI S N, et al. Balancing accuracy and interpretability of machine learning approaches for radiation treatment outcomes modeling[J]. BJR Open, 2019, 1(1):20190021.
[13] YU Y F, HE Z F, OUYANG J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer:a machine learning, multicenter study[J]. EBioMedicine, 2021, 69:103460.
[14] ZHEN X, CHEN J W, ZHONG Z C, et al. Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy:a feasibility study[J]. Phys Med Biol, 2017, 62(21):8246-8263.
[15] SHARIATY F, PAVLOV V. Radiogenomics:transforming lung cancer care through non-invasive imaging and genomic integration[J]. Med Oncol, 2025, 42(12):552.
[16] YU H M, KONG D P, MO X J, et al. MRI-based 2.5D deep learning and radiomics effectively predicted microvascular invasion and Ki-67 expression in hepatocellular carcinoma[J].PLoS One, 2025, 20(11):e0336579.
[17] LI J T, XU Q W, FAN X, et al. Multi-Sequence MRI radiomics model for discrimination of recurrence and pseudoprogression in gliomas[J]. Eur J Radiol, 2026, 194:112508.
[18] QIAN Q, WU J R, XU Z, et al. Orthopedic perioperative nursing under navigation nurse management:Machine learningbased risk prediction models for postoperative recovery quality and explainable artificial intelligence analysis[J]. Medicine,2025, 104(46):e46015.
[19] ALKAN B B, KUZUCUK S, ALKAN N, et al. Using machine learning to predict student outcomes for early intervention and formative assessment[J]. Sci Rep, 2025, 15(1):39797.
[20] UCAR Y O, AYTEKIN O, YALCIN N, et al. Survival outcomes and prognostic factors for patients in early stage cervical cancer:a multicentric study in Türkiye[J]. Diagnostics, 2025, 15(21):1125.
[21] XU B, SHI X Y, LIU Y F, et al. CC/CXC chemokine risk signature at single-cell resolution:a machine learning model for precision stratification in cervical cancer[J]. Transl Cancer Res, 2025, 14(10):6834-6848.
[22] HETTIKANKANAMAGE N, SHAFIABADY N, CHATTEUR F, et al. eXplainable artificial intelligence(XAI):a systematic review for unveiling the black box models and their relevance to biomedical imaging and sensing[J]. Sensors, 2025, 25(21):6649.
[23] AL-SOFYANI K A, ALI MUZAFFAR I H, BAQASI A M, et al.Machine learning prediction of mortality in pediatric fungemia using the Candida score[J]. Sci Rep, 2025, 15(1):39868.
[24] QIU L, FEI Y J, ZHU Y C, et al. Development and validation of a machine learning model for predicting 3-year overall survival in metastatic nasopharyngeal carcinoma:a SEER database and web visualization study[J]. Transl Cancer Res, 2025, 14(10):7037-7052.
[25] TUERSUN A, ABUDOUBARI S, ABUDOUWAKE A, et al.Interpretable machine learning models to predict survival in esophageal cancer:a study based on the SEER database and external validation in China[J]. Front Physiol, 2025, 16:1665383.
[26] RAHIMI M, AKBARI A, ASADI F, et al. Cervical cancer survival prediction by machine learning algorithms:a systematic review[J]. BMC Cancer, 2023, 23(1):341.