Preoperative Prediction of Inferior Vena Cava Wall Invasion of Tumor Thrombus in Renal Cell Carcinoma: Radiomics Models Based on Magnetic Resonance Imaging

Zhaonan Sun, Yingpu Cui, Chunru Xu, Yanfei Yu, Chao Han, Xiang Liu, Zhiyong Lin, Xiangpeng Wang, Changxin Li, Xiaodong Zhang, Xiaoying Wang, Zhaonan Sun, Yingpu Cui, Chunru Xu, Yanfei Yu, Chao Han, Xiang Liu, Zhiyong Lin, Xiangpeng Wang, Changxin Li, Xiaodong Zhang, Xiaoying Wang

Abstract

Objective: To develop radiomics models to predict inferior vena cava (IVC) wall invasion by tumor thrombus (TT) in patients with renal cell carcinoma (RCC).

Methods: Preoperative MR images were retrospectively collected from 91 patients with RCC who underwent radical nephrectomy (RN) and thrombectomy. The images were randomly allocated into a training (n = 64) and validation (n = 27) cohort. The inter-and intra-rater agreements were organized to compare masks delineated by two radiologists. The masks of TT and IVC were manually annotated on axial fat-suppression T2-weighted images (fsT2WI) by one radiologist. The following models were trained to predict the probability of IVC wall invasion: two radiomics models using radiomics features extracted from the two masks (model 1, radiomics model_IVC; model 2, radiomics model_TT), two combined models using radiomics features and radiological features (model 3, combined model_IVC; model 4, combined model_TT), and one radiological model (model 5) using radiological features. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were applied to validate the discriminatory effect and clinical benefit of the models.

Results: Model 1 to model 5 yielded area under the curves (AUCs) of 0.881, 0.857, 0.883, 0.889, and 0.769, respectively, in the validation cohort. No significant differences were found between these models (p = 0.108-0.951). The dicision curve analysis (DCA) showed that the model 3 had a higher overall net benefit than the model 1, model 2, model 4, and model 5.

Conclusions: The combined model_IVC (model 3) based on axial fsT2WI exhibited excellent predictive performance in predicting IVC wall invasion status.

Keywords: carcinoma; inferior; magnetic resonance imaging; radiomics; renal cell; thrombus; vena cava.

Conflict of interest statement

The reviewer JL declared a shared parent affiliation with the author(s) CX, YY, XL, ZL, XZ and XW to the handling editor at the time of review. Author XW and CL were employed by Beijing Smart Tree Medical Technology Co. Ltd. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Copyright © 2022 Sun, Cui, Xu, Yu, Han, Liu, Lin, Wang, Li, Zhang and Wang.

Figures

Figure 1
Figure 1
Patient enrollment folw chart. RCC, renal cell carcinoma; TT, tumor thrombus; IVC, inferior vena cava. Other renal mass include four angiomyolipoma, one inflammatory myofibroblastic tumor, one synovial sarcoma, one malignant solitary fibrous tumors, and one primitive neuroectodermal tumor.
Figure 2
Figure 2
(A) Axial fat-suppression T2-weighted image (fsT2WI) in a 68-year old man with a clear cell renal cell carcinoma (cRCC) and an inferior vena cava (IVC) tumor thrombus (TT) with wall invasion. Subjective features of complete occlusion of the IVC lumen, the irregular margin of the TT (arrow), thickened IVC wall (arrow and triangle), and abnormal signal of the IVC wall (arrow) can be found. (B) Axial fsT2WI in a 76-year old woman with cRCC and a TT in IVC without wall invasion. The crescent-shaped black areas on the laterodorsal aspect of IVC stand for flow void (star). (C–F) Examples for annotation of IVC and TT. The red represents the mask of the IVC, and the green represents the mask of the TT. The three-dimensional (3D) volumes of interest (VOIs) are at the upper right corner.
Figure 3
Figure 3
ROC curves of the five models in the training cohort (A) and validation cohort (B). model 1 = radiomics model_IVC; model 2= radiomics model_TT; model 3 = combined model_IVC; model 4 = combined model_TT; model 5 = radiological model.
Figure 4
Figure 4
DeLong test of the areas under the curve (AUCs) of the 5 models in the training cohort (A) and validation cohort (B). Blue boxes represent p<0.05; Other grey boxes show p > 0.05. model 1 = radiomics model_IVC; model 2= radiomics model_TT; model 3 = combined model_IVC; model 4 = combined model_TT; model 5 = radiological model.
Figure 5
Figure 5
Decision curve analysis (DCA) comparing the net benefits of different models in the training cohort (A) and validation cohort (B). The y-axis measures the net benefit and the x-axis indicates the threshold probability. model 1 = radiomics model_IVC; model 2= radiomics model_TT; model 3 = combined model_IVC; model 4 = combined model_TT; model 5 = radiological model.

References

    1. Motzer RJ, Jonasch E, Agarwal N, Bhayani S, Bro WP, Chang SS, et al. . Kidney Cancer, Version 2.2017, Nccn Clinical Practice Guidelines in Oncology. J Natl Compr Cancer Network JNCCN (2017) 15(6):804–34. doi: 10.6004/jnccn.2017.0100
    1. Paner GP, Stadler WM, Hansel DE, Montironi R, Lin DW, Amin MB. Updates in the Eighth Edition of the Tumor-Node-Metastasis Staging Classification for Urologic Cancers. Eur Urol (2018) 73(4):560–9. doi: 10.1016/j.eururo.2017.12.018
    1. Ljungberg B, Bensalah K, Canfield S, Dabestani S, Hofmann F, Hora M, et al. . Eau Guidelines on Renal Cell Carcinoma: 2014 Update. Eur Urol (2015) 67(5):913–24. doi: 10.1016/j.eururo.2015.01.005
    1. Blute ML, Leibovich BC, Lohse CM, Cheville JC, Zincke H. The Mayo Clinic Experience With Surgical Management, Complications and Outcome for Patients With Renal Cell Carcinoma and Venous Tumour Thrombus. BJU Int (2004) 94(1):33–41. doi: 10.1111/j.1464-410X.2004.04897.x
    1. Lambert EH, Pierorazio PM, Shabsigh A, Olsson CA, Benson MC, McKiernan JM. Prognostic Risk Stratification and Clinical Outcomes in Patients Undergoing Surgical Treatment for Renal Cell Carcinoma With Vascular Tumor Thrombus. Urology (2007) 69(6):1054–8. doi: 10.1016/j.urology.2007.02.052
    1. Manassero F, Mogorovich A, Di Paola G, Valent F, Perrone V, Signori S, et al. . Renal Cell Carcinoma With Caval Involvement: Contemporary Strategies of Surgical Treatment. Urol Oncol (2011) 29(6):745–50. doi: 10.1016/j.urolonc.2009.09.018
    1. Hatcher PA, Anderson EE, Paulson DF, Carson CC, Robertson JE. Surgical Management and Prognosis of Renal Cell Carcinoma Invading the Vena Cava. J Urol (1991) 145(1):20–3. doi: 10.1016/s0022-5347(17)38235-6
    1. Zini L, Destrieux-Garnier L, Leroy X, Villers A, Haulon S, Lemaitre L, et al. . Renal Vein Ostium Wall Invasion of Renal Cell Carcinoma With an Inferior Vena Cava Tumor Thrombus: Prediction by Renal and Vena Caval Vein Diameters and Prognostic Significance. J Urol (2008) 179(2):450–4. doi: 10.1016/j.juro.2007.09.042
    1. Ciancio G, Livingstone AS, Soloway M. Surgical Management of Renal Cell Carcinoma With Tumor Thrombus in the Renal and Inferior Vena Cava: The University of Miami Experience in Using Liver Transplantation Techniques. Eur Urol (2007) 51(4):988–94. doi: 10.1016/j.eururo.2006.11.055
    1. Jibiki M, Iwai T, Inoue Y, Sugano N, Kihara K, Hyochi N, et al. . Surgical Strategy for Treating Renal Cell Carcinoma With Thrombus Extending Into the Inferior Vena Cava. J Vasc Surg (2004) 39(4):829–35. doi: 10.1016/j.jvs.2003.12.004
    1. Campi R, Tellini R, Sessa F, Mari A, Cocci A, Greco F, et al. . Techniques and Outcomes of Minimally-Invasive Surgery for Nonmetastatic Renal Cell Carcinoma With Inferior Vena Cava Thrombosis: A Systematic Review of the Literature. Minerva Urol Nefrol = Ital J Urol Nephrol (2019) 71(4):339–58. doi: 10.23736/s0393-2249.19.03396-4
    1. Brassetti A, Anceschi U, Bertolo R, Ferriero M, Tuderti G, Costantini M, et al. . Comprehensive Long-Term Assessment of Outcomes Following Robot-Assisted Partial Nephrectomy for Renal Cell Carcinoma: The Rome's Achievement and Its Predicting Nomogram. Minerva Urol Nefrol = Ital J Urol Nephrol (2020) 72(4):482–9. doi: 10.23736/s0393-2249.20.03813-8
    1. Liu Z, Li L, Hong P, Zhu G, Tang S, Zhao X, et al. . A Predictive Model for Tumor Invasion of the Inferior Vena Cava Wall Using Multimodal Imaging in Patients With Renal Cell Carcinoma and Inferior Vena Cava Tumor Thrombus. BioMed Res Int (2020) 2020:9530618. doi: 10.1155/2020/9530618
    1. Adams LC, Ralla B, Bender YY, Bressem K, Hamm B, Busch J, et al. . Renal Cell Carcinoma With Venous Extension: Prediction of Inferior Vena Cava Wall Invasion by Mri. Cancer Imaging Off Publ Int Cancer Imaging Soc (2018) 18(1):17. doi: 10.1186/s40644-018-0150-z
    1. Alayed A, Krishna S, Breau RH, Currin S, Flood TA, Narayanasamy S, et al. . Diagnostic Accuracy of Mri for Detecting Inferior Vena Cava Wall Invasion in Renal Cell Carcinoma Tumor Thrombus Using Quantitative and Subjective Analysis. AJR Am J Roentgenol (2019) 212(3):562–9. doi: 10.2214/ajr.18.20209
    1. Wu JY, Mi Y, Liu S, Yao L, Tang Q, He ZS, et al. . [Evaluating Inferior Vena Cava Wall Invasion in Renal Cell Carcinoma Tumor Thrombus With Mri]. Beijing da xue xue bao Yi xue ban = J Peking Univ Health Sci (2019) 51(4):673–7. doi: 10.19723/j.issn.1671-167X.2019.04.013
    1. Aslam Sohaib SA, Teh J, Nargund VH, Lumley JS, Hendry WF, Reznek RH. Assessment of Tumor Invasion of the Vena Caval Wall in Renal Cell Carcinoma Cases by Magnetic Resonance Imaging. J Urol (2002) 167(3):1271–5. doi: 10.1097/00005392-200203000-00015
    1. Oto A, Herts BR, Remer EM, Novick AC. Inferior Vena Cava Tumor Thrombus in Renal Cell Carcinoma: Staging by Mr Imaging and Impact on Surgical Treatment. AJR Am J Roentgenol (1998) 171(6):1619–24. doi: 10.2214/ajr.171.6.9843299
    1. Laissy JP, Menegazzo D, Debray MP, Toublanc M, Ravery V, Dumont E, et al. . Renal Carcinoma: Diagnosis of Venous Invasion With Gd-Enhanced Mr Venography. Eur Radiol (2000) 10(7):1138–43. doi: 10.1007/s003309900296
    1. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More Than Pictures, They Are Data. Radiology (2016) 278(2):563–77. doi: 10.1148/radiol.2015151169
    1. Zou KH, Warfield SK, Bharatha A, Tempany CM, Kaus MR, Haker SJ, et al. . Statistical Validation of Image Segmentation Quality Based on a Spatial Overlap Index. Acad Radiol (2004) 11(2):178–89. doi: 10.1016/s1076-6332(03)00671-8
    1. van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res (2017) 77(21):e104–e7. doi: 10.1158/0008-5472.Can-17-0339
    1. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the Areas Under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach. Biometrics (1988) 44(3):837–45. doi: 10.2307/2531595
    1. Xie H, Zhang X, Ma S, Liu Y, Wang X. Preoperative Differentiation of Uterine Sarcoma From Leiomyoma: Comparison of Three Models Based on Different Segmentation Volumes Using Radiomics. Mol Imaging Biol (2019) 21(6):1157–64. doi: 10.1007/s11307-019-01332-7
    1. Lin Z, Tang B, Cai J, Wang X, Li C, Tian X, et al. . Preoperative Prediction of Clinically Relevant Postoperative Pancreatic Fistula After Pancreaticoduodenectomy. Eur J Radiol (2021) 139:109693. doi: 10.1016/j.ejrad.2021.109693
    1. Xie H, Hu J, Zhang X, Ma S, Liu Y, Wang X. Preliminary Utilization of Radiomics in Differentiating Uterine Sarcoma From Atypical Leiomyoma: Comparison on Diagnostic Efficacy of Mri Features and Radiomic Features. Eur J Radiol (2019) 115:39–45. doi: 10.1016/j.ejrad.2019.04.004
    1. Ji GW, Zhang YD, Zhang H, Zhu FP, Wang K, Xia YX, et al. . Biliary Tract Cancer at Ct: A Radiomics-Based Model to Predict Lymph Node Metastasis and Survival Outcomes. Radiology (2019) 290(1):90–8. doi: 10.1148/radiol.2018181408
    1. Huang YQ, Liang CH, He L, Tian J, Liang CS, Chen X, et al. . Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer. J Clin Oncol Off J Am Soc Clin Oncol (2016) 34(18):2157–64. doi: 10.1200/jco.2015.65.9128
    1. Lecler A, Duron L, Balvay D, Savatovsky J, Bergès O, Zmuda M, et al. . Combining Multiple Magnetic Resonance Imaging Sequences Provides Independent Reproducible Radiomics Features. Sci Rep (2019) 9(1):2068. doi: 10.1038/s41598-018-37984-8
    1. Ma S, Xie H, Wang H, Yang J, Han C, Wang X, et al. . Preoperative Prediction of Extracapsular Extension: Radiomics Signature Based on Magnetic Resonance Imaging to Stage Prostate Cancer. Mol Imaging Biol (2020) 22(3):711–21. doi: 10.1007/s11307-019-01405-7
    1. Peduzzi P, Concato J, Kemper E, Holford TR, Feinstein AR. A Simulation Study of the Number of Events Per Variable in Logistic Regression Analysis. J Clin Epidemiol (1996) 49(12):1373–9. doi: 10.1016/s0895-4356(96)00236-3

Source: PubMed

Patrocinadores y Colaboradores

Condiciones médicas

Intervenciones de drogas

3
Suscribir