CT radiomics model for predicting progression-free survival of locally advanced cervical cancer after concurrent chemoradiotherapy
Liu Huiling1, Cui Yongbin2, Chang Cheng3, Qiu Qingtao2, Yin Yong2, Wang Ruozheng1,4
1Department of Radiation Oncology, the Affiliated Tumor Hospital of Xinjiang Medical University, Xinjiang Key Laboratory of Oncology, Wulumuqi 830011, China; 2Department of Radiation Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Ji'nan 250117, China; 3Department of Nuclear Medicine, the Affiliated Tumor Hospital of Xinjiang Medical University, State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asian, Wulumuqi 830011, China; 4Key Laboratory of Cancer Immunotherapy and Radiotherapy, Chinese Academy of Medical Sciences, Wulumuqi 830011, China; Liu Huiling studied at Shandong Cancer Hospital and is working on Department of Oncology, Binzhou People's Hospital, Binzhou 256600, China
Abstract：Objective To construct machine learning models based on CT imaging and clinical parameters for predicting progression-free survival (PFS) of locally advanced cervical cancer (LACC) patients after concurrent chemoradiotherapy (CCRT). Methods Clinical data of 167 LACC patients treated with CCRT at Shandong Cancer Hospital from September 2015 to October 2021 were retrospectively analyzed. All patients were randomly divided into the training and validation cohorts according to the ratio of 7 vs. 3. Clinical features were selected by univariate and multivariate Cox proportional hazards model (P<0.1). Radiomics models and nomograms were constructed by radiomics features which were selected by least absolute shrinkage and selection operator (LASSO) Cox regression model to predict the 1-, 3- and 5-year PFS. Combined models and nomogram models were developed by selected clinical and radiomics features. The Kaplan Meier-curve, receiver operating characteristic (ROC) curve, C-index and calibration curve were used to evaluate the model performance. Results A total of 1 409 radiomics features were extracted based on the region of interest (ROI) in CT images. CT radiomics models showed better performance for predicting 1-, 3-and 5-year PFS than the clinical model in the training and validation cohorts. The combined model displayed the optimal performance in predicting 1-, 3-and 5-year PFS in the training cohort [area under the curve (AUC): 0.760, 0.648, 0.661, C-index: 0.740, 0.667, 0.709] and verification cohort (AUC: 0.763, 0.677, 0.648, C-index: 0.748, 0.668, 0.678). Conclusions Combined model constructed based on CT radiomics and clinical features yield better prediction performance than that based on radiomics or clinical features alone. As an objective image analysis approach, it possesses high prediction efficiency for PFS of LACC patients after CCRT, which can provide reference for clinical decision-making.
Liu Huiling,Cui Yongbin,Chang Cheng et al. CT radiomics model for predicting progression-free survival of locally advanced cervical cancer after concurrent chemoradiotherapy[J]. Chinese Journal of Radiation Oncology, 2023, 32(8): 697-703.
[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. DOI: 10.3322/caac.21660. [2] Zheng RS, Zhang SW, Zeng HM, et al. Cancer incidence and mortality in China, 2016[J]. Journal of National Cancer Center, 2022, 2(1): 1-9. DOI: 10.1016/j.jncc.2022.02.002. [3] Pujade-Lauraine E, Tan D, Leary A, et al.Comparison of global treatment guidelines for locally advanced cervical cancer to optimize best care practices: a systematic and scoping review[J]. Gynecol Oncol, 2022,167(2): 360-372. DOI: 10.1016/j.ygyno.2022.08.013. [4] China NHCOTPRO.Chinese guidelines for diagnosis and treatment of cervical cancer 2018 (English version)[J]. Chin J Cancer Res, 2019,31(2):295-305. DOI: 10.21147/j.issn.1000-9604.2019.02.04. [5] Abu-Rustum NR, Yashar CM, Bean S, et al.NCCN guidelines insights: cervical cancer, version 1.2020[J]. J Natl Compr Canc Netw, 2020,18(6):660-666. DOI: 10.6004/jnccn.2020.0027. [6] Lucia F, Visvikis D, Desseroit MC, et al.Prediction of outcome using pretreatment 18F-FDG PET/CT and MRI radiomics in locally advanced cervical cancer treated with chemoradiotherapy[J]. Eur J Nucl Med Mol Imaging, 2018,45(5):768-786. DOI: 10.1007/s00259-017-3898-7. [7] Matsuo K, Machida H, Mandelbaum RS, et al.Validation of the 2018 FIGO cervical cancer staging system[J]. Gynecol Oncol, 2019,152(1):87-93. DOI: 10.1016/j.ygyno.2018.10.026. [8] Mohamud A, Høgdall C, Schnack T.Prognostic value of the 2018 FIGO staging system for cervical cancer[J]. Gynecol Oncol, 2022,165(3):506-513. DOI: 10.1016/j.ygyno.2022.02.017. [9] Scapicchio C, Gabelloni M, Barucci A, et al.A deep look into radiomics[J]. Radiol Med, 2021,126(10):1296-1311. DOI: 10.1007/s11547-021-01389-x. [10] Stanzione A, Cuocolo R, Ugga L, et al.Oncologic imaging and radiomics: a walkthrough review of methodological challenges[J]. Cancers (Basel), 2022,14(19):4871. DOI: 10.3390/cancers14194871. [11] Hu QM, Shi JM, Zhang AN, et al.Added value of radiomics analysis in MRI invisible early-stage cervical cancers[J]. Br J Radiol, 2022,95(1133):20210986. DOI: 10.1259/bjr.20210986. [12] Huang G, Cui YQ, Wang P, et al.Multi-parametric magnetic resonance imaging-based radiomics analysis of cervical cancer for preoperative prediction of lymphovascular space invasion[J]. Front Oncol, 2021,11:663370. DOI: 10.3389/fonc.2021.663370. [13] Ikushima H, Haga A, Ando K, et al.Prediction of out-of-field recurrence after chemoradiotherapy for cervical cancer using a combination model of clinical parameters and magnetic resonance imaging radiomics: a multi-institutional study of the Japanese Radiation Oncology Study Group[J]. J Radiat Res, 2022,63(1):98-106. DOI: 10.1093/jrr/rrab104. [14] Ren K, Shen L, Qiu JF, et al.Treatment planning computed tomography radiomics for predicting treatment outcomes and haematological toxicities in locally advanced cervical cancer treated with radiotherapy: a retrospective cohort study[J]. BJOG, 2023,130(2):222-230. DOI: 10.1111/1471-0528.17285. [15] 中华医学会放射肿瘤治疗分会近距离治疗学组, 中国医师协会放射肿瘤分会妇科肿瘤学组, 中国抗癌协会近距离治疗专委会. 宫颈癌图像引导三维近距离后装治疗中国专家共识[J].中华放射肿瘤学杂志,2020,29(9):712-717. DOI: 10.3760/cma.j.cn113030-20200420-00196. The Brachytherapy Group of China Society for Radiation Oncology, The Gynecological Oncology Group of Chinese Association for Therapeutic Radiation Oncologists, The Brachytherapy Special Committee of Chinese Anti-Cancer Association. Chinese expert consensus on three- dimensional image guided brachytherapy for cervical cancer[J].Chin J Radiat Oncol,2020,29(9):712-717. DOI: 10.3760/cma.j.cn113030-20200420-00196. [16] Zwanenburg A, Vallières M, Abdalah MA, et al.The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping[J]. Radiology, 2020,295(2):328-338. DOI: 10.1148/radiol.2020191145. [17] Bian Y, Guo SW, Jiang H, et al.Radiomics nomogram for the preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma[J]. Cancer Imaging, 2022,22(1):4. DOI: 10.1186/s40644-021-00443-1. [18] Altazi BA, Fernandez DC, Zhang GG, et al.Investigating multi-radiomic models for enhancing prediction power of cervical cancer treatment outcomes[J]. Phys Med, 2018,46:180-188. DOI: 10.1016/j.ejmp.2017.10.009. [19] Lee JW, Seol KH.Pretreatment neutrophil-to-lymphocyte ratio combined with platelet-to-lymphocyte ratio as a predictor of survival outcomes after definitive concurrent chemoradiotherapy for cervical cancer[J]. J Clin Med, 2021,10(10):2199. DOI: 10.3390/jcm10102199. [20] Wei GC, Jiang P, Tang ZC, et al.MRI radiomics in overall survival prediction of local advanced cervical cancer patients tread by adjuvant chemotherapy following concurrent chemoradiotherapy or concurrent chemoradiotherapy alone[J]. Magn Reson Imaging, 2022,91:81-90. DOI: 10.1016/j.mri.2022.05.019. [21] Jiang XT, Song JC, Duan SF, et al.MRI radiomics combined with clinicopathologic features to predict disease-free survival in patients with early-stage cervical cancer[J]. Br J Radiol, 2022,95(1136):20211229. DOI: 10.1259/bjr. 20211229. [22] Zhang JQ, Qin L, Chen HM, et al.Overall survival, locoregional recurrence, and distant metastasis of definitive concurrent chemoradiotherapy for cervical squamous cell carcinoma and adenocarcinoma: before and after propensity score matching analysis of a cohort study[J]. Am J Cancer Res, 2020,10(6):1808-1820. [23] Jajodia A, Gupta A, Prosch H, et al.Combination of radiomics and machine learning with diffusion-weighted MR imaging for clinical outcome prognostication in cervical cancer[J]. Tomography, 2021,7(3):344-357. DOI: 10.3390/tomography7030031. [24] Cui YB, Li ZJ, Xiang MY, et al.Machine learning models predict overall survival and progression free survival of non-surgical esophageal cancer patients with chemoradiotherapy based on CT image radiomics signatures[J]. Radiat Oncol, 2022,17(1):212. DOI: 10.1186/s13014-022-02186-0. [25] Cho HW, Lee ES, Lee JK, et al.Prognostic value of textural features obtained from F-fluorodeoxyglucose (F-18 FDG) positron emission tomography/computed tomography (PET/CT) in patients with locally advanced cervical cancer undergoing concurrent chemoradiotherapy[J]. Ann Nucl Med, 2023,37(1):44-51. DOI: 10.1007/s12149-022-01802-z.
2023, Vol. 32 
