The preoperative predictive value of a multimodal MR radiomics and clinical risk factors combined model for bladder cancer pathological grading
Su Qiaona1,2, Yin Manxin1,2, Song Xin3, Ma Qiuyu3, Zhang Jianxin2
1Department of Medical Imaging, Shanxi Medical University, Taiyuan 030013, China; 2Department of Radiology, Shanxi Province Cancer Hospital, Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences, Cancer Hospital Affiliated to Shanxi Medical University, Taiyuan 030013, China; 3Department of Public Health, Shanxi Medical University, Taiyuan 030013, China
Abstract:Objective This study aims to explore the application value of a combined predictive model based on preoperative multimodal magnetic resonance imaging (MRI) radiomics features and clinical risk factors in predicting the pathological grade of bladder cancer. Methods Retrospective cohort study. The study included a total of 135 patients with bladder cancer who underwent MRI and clinical pathological examination in Shanxi Cancer Hospital from May 2013 to July 2022. Among them, there were 116 males and 19 females, with ages ranging from 34 to 92 years old (mean age: 67.0± 10.5 years old). A random sampling method was used to divide the patients into a training set (94 cases) and a validation set (41 cases) in a ratio of 7∶ 3. ITK-SNAP software was used to manually segment and delineate the regions of interest (ROI) along the edge of the primary lesion of bladder cancer layer by layer in T2-weighted images (T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) maps, and enhanced T1-weighted images (T1WI). Pyradiomics, an open-source software package was used to extract radiomics features. The radiomics features of the primary lesion of bladder cancer were screened and a radiomics prediction model was constructed using methods such as Mann-Whitney U test, Pearson correlation coefficient, and LASSO regression. Clinical risk factors for the pathological histological grading of bladder cancer were screened by univariate and multivariate logistic regression analysis, and a clinical prediction model was constructed. The optimal radiomics features were combined with the clinical risk factors to build a joint prediction model. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the predictive performance and clinical utility of the prediction models. Results A total of 1 574 radiomics features were extracted from the four modalities, and 6 296 radiomics features were extracted from the combination of the four modalities. Moreover, 19, 7, 8, 14, and 31 radiomics features were correlated with the pathological grading of bladder cancer in five different sequences. The MRI radiomics prediction model based on T2WI, DWI, ADC and enhanced T1WI sequences and the multimodal MRI radiomics prediction model based on the combination of the four sequences were constructed. The area under the curve (AUC) values of the five radiomics predictive models in the training and validation sets were 0.923 and 0.823, 0.770 and 0.797, 0.781 and 0.812, 0.870 and 0.617, and 0.971 and 0.912, respectively. The clinical risk factor selected by logistic regression was clinical T stage, and the AUC values of the clinical predictive models in the training and validation sets were 0.726 and 0.755, respectively. The AUC values of the joint predictive model were 0.974 and 0.980 in the training and validation sets, respectively. The decision curve analysis showed that the joint predictive model had higher net benefit than the two other models. The calibration curve also demonstrated good predictive value of the joint predictive model in the training and validation sets. Conclusion The joint predictive model based on preoperative multimodal MRI radiomics features and clinical risk factors can improve the predictive efficiency of bladder cancer pathological grading and provide non-invasive guidance for treatment.
苏巧娜, 殷满心, 宋鑫, 马欣雨, 张建新. 基于多模态MRI的影像组学与临床危险因素联合模型对膀胱癌病理学分级的术前预测价值[J]. 中华解剖与临床杂志, 2023, 28(7): 460-468.
Su Qiaona, Yin Manxin, Song Xin, Ma Qiuyu, Zhang Jianxin. The preoperative predictive value of a multimodal MR radiomics and clinical risk factors combined model for bladder cancer pathological grading. Chinese Journal of Anatomy and Clinics, 2023, 28(7): 460-468.
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 R, Zhang S, Zeng H, et al.Cancer incidence and mortality in China, 2016[J]. Journal of the National Cancer Center, 2022, 2(1): 1-9. DOI:10.1016/j.jncc.2022.02.002
[3]
Liu Z, Zhang Y, Sun G, et al.Comparison of thulium laser resection of bladder tumors and conventional transurethral resection of bladder tumors for non-muscle-invasive bladder cancer[J]. Urol Int, 2022,106(2):116-121. DOI: 10.1159/000514042
[4]
Flaig TW, Spiess PE, Agarwal N, et al.Bladder cancer, version 3.2020, NCCN clinical practice guidelines in oncology[J]. J Natl Compr Canc Netw, 2020,18(3):329-354. DOI: 10.6004/jnccn.2020.0011
[5]
Ueno Y, Takeuchi M, Tamada T, et al.Diagnostic accuracy and interobserver agreement for the vesical imaging-reporting and data system for muscle-invasive bladder cancer: a multireader validation study[J]. Eur Urol, 2019,76(1):54-56. DOI:1016/j.eururo.2019.03.012
[6]
Messina E, Pecoraro M, Pisciotti ML, et al.Seeing is believing: state of the art imaging of bladder cancer[J]. Semin Radiat Oncol, 2023,33(1):12-20. DOI:10.1016/j.semradonc.2022.10.002
[7]
Barchetti G, Simone G, Ceravolo I, et al.Multiparametric MRI of the bladder: inter-observer agreement and accuracy with the Vesical Imaging-Reporting and Data System (VI-RADS) at a single reference center[J]. Eur Radiol,2019,29(10):5498-5506. DOI:10.1007/s00330-019-06117-8
[8]
Lambin P, Rios-Velazquez E, Leijenaar R, et al.Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012,48(4):441-446. DOI: 10.1016/j.ejca.2011.11.036
[9]
Kumar V, Gu Y, Basu S, et al.Radiomics: the process and the challenges[J]. Magn Reson Imaging, 2012,30(9):1234-1248. DOI: 10.1016/j.mri.2012.06.010
[10]
Zhang X, Xu X, Tian Q, et al.Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging[J]. J Magn Reson Imaging, 2017,46(5):1281-1288. DOI: 10.1002/jmri.25669
[11]
Feng C, Zhou Z, Huang Q, et al.Radiomics nomogram based on high-b-value diffusion-weighted imaging for distinguishing the grade of bladder cancer[J]. Life (Basel),2022,12(10):1510. DOI:10.3390/life12101510
[12]
Kirkali Z, Chan T, Manoharan M, et al.Bladder cancer: epidemiology, staging and grading, and diagnosis[J]. Urology, 2005,66(6 Suppl 1):4-34. DOI: 10.1016/j.urology.2005.07.062
[13]
Humphrey PA, Moch H, Cubilla AL, et al.The 2016 WHO classification of tumours of the urinary system and male genital organs-part B: prostate and bladder tumours[J]. Eur Urol, 2016,70(1):106-119. DOI: 10.1016/j.eururo.2016.02.028
[14]
Wu S, Zheng J, Li Y, et al.Development and validation of an MRI-based radiomics signature for the preoperative prediction of lymph node metastasis in bladder cancer[J]. EBioMedicine, 2018,34:76-84. DOI: 10.1016/j.ebiom.2018.07.029
[15]
Zhang S, Song M, Zhao Y, et al.Radiomics nomogram for preoperative prediction of progression-free survival using diffusion-weighted imaging in patients with muscle-invasive bladder cancer[J]. Eur J Radiol, 2020,131:109219. DOI: 10.1016/j.ejrad.2020.109219
[16]
Cha KH, Hadjiiski L, Chan HP, et al.Bladder cancer treatment response assessment in CT using Radiomics with deep-learning[J]. Sci Rep, 2017,7(1):8738. DOI: 10.1038/s41598-017-09315-w
[17]
Hansel DE, Amin MB, Comperat E, et al.A contemporary update on pathology standards for bladder cancer: transurethral resection and radical cystectomy specimens[J]. Eur Urol, 2013,63(2):321-332. DOI: 10.1016/j.eururo.2012.10.008
[18]
Smith CP, Czarniecki M, Mehralivand S, et al.Radiomics and radiogenomics of prostate cancer[J]. Abdom Radiol (NY), 2019,44(6):2021-2029. DOI: 10.1007/s00261-018-1660-7
[19]
Tagliafico AS, Piana M, Schenone D, et al.Overview of radiomics in breast cancer diagnosis and prognostication[J]. Breast, 2020,49:74-80. DOI: 10.1016/j.breast.2019.10.018
[20]
Choi YS, Bae S, Chang JH, et al.Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics[J]. Neuro Oncol, 2021,23(2):304-313. DOI: 10.1093/neuonc/noaa177
[21]
Kolinger GD, García DV, Kramer GM, et al.Effects of tracer uptake time in non-small cell lung cancer 18F-FDG PET radiomics[J]. J Nucl Med, 2022,63(6):919-924. DOI: 10.2967/jnumed.121.262660
[22]
侯丽娜, 崔艳芬, 郭凌云, 等. 多参数MRI的影像组学融合模型在术前预测宫颈癌淋巴结转移的应用价值[J].中华解剖与临床杂志, 2020,25(3):213-220. DOI:10.3760/cma.j.cn101202-20200310-00074.Hou LN, Cui YF, Guo LY, et al.Multiparametric magnetic resonance imaging-based radiomics model for the preoperative prediction of lymph node metastasis in cervical cancer[J]. Chin J Anat Clin, 2020,25(3):213-220. DOI:10.3760/cma.j.cn101202-20200310-00074
[23]
Garapati SS, Hadjiiski L, Cha KH, et al.Urinary bladder cancer staging in CT urography using machine learning[J]. Med Phys, 2017,44(11):5814-5823. DOI: 10.1002/mp.12510
[24]
Cha KH, Hadjiiski LM, Cohan RH, et al.Diagnostic accuracy of CT for prediction of bladder cancer treatment response with and without computerized decision support[J]. Acad Radiol, 2019,26(9):1137-1145. DOI: 10.1016/j.acra.2018.10.010
[25]
Wu S, Zheng J, Li Y, et al.A radiomics nomogram for the preoperative prediction of lymph node metastasis in bladder cancer[J]. Clin Cancer Res, 2017,23(22):6904-6911. DOI: 10.1158/1078-0432.CCR-17-1510
[26]
Wang H, Hu D, Yao H, et al.Radiomics analysis of multiparametric MRI for the preoperative evaluation of pathological grade in bladder cancer tumors[J]. Eur Radiol, 2019,29(11):6182-6190. DOI: 10.1007/s00330-019-06222-8
[27]
Liu X, Elbanan MG, Luna A, et al.Radiomics in abdominopelvic solid-organ oncologic imaging: current status[J]. AJR Am J Roentgenol, 2022,219(6):985-995. DOI: 10.2214/AJR.22.27695
[28]
Naseri H, Skamene S, Tolba M, et al.Radiomics-based machine learning models to distinguish between metastatic and healthy bone using lesion-center-based geometric regions of interest[J]. Sci Rep, 2022,12(1):9866. DOI: 10.1038/s41598-022-13379-8.