Development and Validation of a CT-Based Radiomics Nomogram for Predicting Postoperative Progression-Free Survival in Stage I–III Renal Cell Carcinoma

Abstract

BackgroundMany patients experience recurrence of renal cell carcinoma (RCC) after radical and partial nephrectomy. Radiomics nomogram is a newly used noninvasive tool that could predict tumor phenotypes.ObjectiveTo investigate Radiomics Features (RFs) associated with progression-free survival (PFS) of RCC, assessing its incremental value over clinical factors, and to develop a visual nomogram in order to provide reference for individualized treatment.MethodsThe RFs and clinicopathological data of 175 patients (125 in the training set and 50 in the validation set) with clear cell RCC (ccRCC) were retrospectively analyzed. In the training set, RFs were extracted from multiphase enhanced CT tumor volume and selected using the stability LASSO feature selection algorithm. A radiomics nomogram final model was developed that incorporated the RFs weighted sum and selected clinical predictors based on the multivariate Cox proportional hazard regression. The performances of a clinical variables-only model, RFs-only model, and the final model were compared by receiver operator characteristic (ROC) analysis and DeLong test. Nomogram performance was determined and validated with respect to its discrimination, calibration, reclassification, and clinical usefulness.ResultsThe radiomics nomogram included age, clinical stage, KPS score, and RFs weighted sum, which consisted of 6 selected RFs. The final model showed good discrimination, with a C-index of 0.836 and 0.706 in training and validation, and good calibration. In the training set, the C-index of the final model was significantly larger than the clinical-only model (DeLong test, p = 0.008). From the clinical variables-only model to the final model, the reclassification of net reclassification improvement was 18.03%, and the integrated discrimination improvement was 19.08%. Decision curve analysis demonstrated the clinical usefulness of the radiomics nomogram.ConclusionThe CT-based RF is an improvement factor for clinical variables-only model. The radiomics nomogram provides individualized risk assessment of postoperative PFS for patients with RCC.

Multiregional radiomics nomogram for postoperative recurrence risk stratification in localized clear cell renal cell carcinoma

“…Multiple studies have developed diverse radiomics models for the prediction of recurrence and metastasis in clear cell carcinoma [19,[27][28][29]. For example, Bing Kang et al created a radiomic model for use in T1 stage ccRCC consisting of ten intratumoral features for the prediction of postoperative recurrence risks [28], and achieve a high AUC (training, 0.91; validation, 0.92).…”

“…However, the study is limited mainly by its relatively small sample size and recruiting only 168 patients. While other studies [19,20,27,29] have included stage I-III patients, they have utilized the predictive capacities of intratumoral radiomics (C-index 0.706-0.780). The accuracy of these models in predicting RFS is limited.…”

Radiomics vs radiologist in bladder and renal cancer. Results from a systematic review

“…Finally, 39 studies were accepted and included. Four papers were pertinent to bladder cancer [ 6 – 9 ], and 18 to renal cancer [ 10 , 11 , 20 – 27 , 12 – 19 ]. Figure 2 shows the flow chart of the literature search.…”

Emerging Trends in AI and Radiomics for Bladder, Kidney, and Prostate Cancer: A Critical Review

“…The study focused on the reproducibility and accuracy of texture features from MR and CT images, finding that MR-and CT-based models effectively distinguished high-from low-grade ccRCCs. Zhang et al [6] focused on investigating radiomics features (RFs) related to the progression-free survival of RCC, aiming to develop a nomogram for individualized treatment reference. The research involved analyzing RFs and clinical data from 175 patients, using enhanced CT imaging and the LASSO algorithm for feature selection.…”

“…In the realm of kidney cancer, particularly renal cell carcinoma (RCC), with its inherent heterogeneity, AI and radiomics adeptly address diagnostic and prognostic challenges. ML algorithms, when applied to MRI-derived radiomics features, have shown promise in distinguishing RCC subtypes and grades [5,6]. Cui et al [5] investigated MR-and CT-based ML models for grading clear cell RCC.…”