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

Abstract

ObjectiveTo develop radiomics models to predict inferior vena cava (IVC) wall invasion by tumor thrombus (TT) in patients with renal cell carcinoma (RCC).MethodsPreoperative 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.ResultsModel 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.ConclusionsThe combined model_IVC (model 3) based on axial fsT2WI exhibited excellent predictive performance in predicting IVC wall invasion status.

A MRI-based radiomics nomogram for differentiation of fat-poor renal angiomyolipoma from nodular clear cell renal cell carcinoma

“…In recent years, the development and advancement of radiomics have signi cantly enhanced the ability to predict and classify renal tumors. CT and MRI imaging have been extensively utilized in radiomics and machine learning research to differentiate renal masses [Kim et al 2022;Sun et al 2022]. Given that T2, DWI, and ADC maps are widely adopted sequences in MRI examinations in various clinical settings, these three sequences were selected for feature extraction in the current study.…”

A Contemporary Clinicopathologic Analysis of Patients With Renal Cell Carcinoma and Vena Cava Involvement

“…Even though extended lymph node dissection in higher staged RCC may be beneficial in some patients, its role in management is still debatable. 22,23 Diagnostic and perioperative imaging have always played an indispensable role in the management of RCC, even more so in patients with vena cava involvement, with some studies showing promising results in predicting vena cava wall invasion, 24,25 which is crucial for optimal treatment planning and prognosis, as if wall invasion is evident; inferior vena cava resection, either segmental or circumferential, along with caval reconstruction is often necessary. 26,27 This can become more challenging when considering other potential complications both intraoperatively and postoperatively, as well as a myriad of technical issues in the surgical approach.…”

Renal cell carcinoma with inferior vena cava thrombus: did we make progress in oncologic outcomes and complications?

“…In particular, recent efforts have sought to identify the degree of TT caval invasion, as a more invasive thrombus may require caval resection and potential reconstruction to maximize negative margin status, as a positive margin predisposes the patient to a greater risk of local tumor recurrence [15 ▪ ]. Although the degree of invasion frequently can only be determined during the operative exploration, MRI offers direct and indirect indicators of wall invasion including contact with caval wall, abnormal IVC wall signal, IVC lumen occlusion, and IVC diameter [16 ▪ ,17 ▪ ,18]. However, thus far, these MRI assessments lack objective measures and proven fidelity [18].…”

“…However, thus far, these MRI assessments lack objective measures and proven fidelity [18]. In an effort to overcome these limitations, Sun et al [16 ▪ ] utilized radiomics to build a predictive MRI-based model for caval wall invasion. Based on fat-suppression T2-weighted MRI, 1070 radiomics features were extracted from 64 patients for model building.…”