Radiomics for the Prediction of Overall Survival in Patients with Bladder Cancer Prior to Radical Cystectomy

Abstract

(1) Background: To evaluate radiomics features as well as a combined model with clinical parameters for predicting overall survival in patients with bladder cancer (BCa). (2) Methods: This retrospective study included 301 BCa patients who received radical cystectomy (RC) and pelvic lymphadenectomy. Radiomics features were extracted from the regions of the primary tumor and pelvic lymph nodes as well as the peritumoral regions in preoperative CT scans. Cross-validation was performed in the training cohort, and a Cox regression model with an elastic net penalty was trained using radiomics features and clinical parameters. The models were evaluated with the time-dependent area under the ROC curve (AUC), Brier score and calibration curves. (3) Results: The median follow-up time was 56 months (95% CI: 48–74 months). In the follow-up period from 1 to 7 years after RC, radiomics models achieved comparable predictive performance to validated clinical parameters with an integrated AUC of 0.771 (95% CI: 0.657–0.869) compared to an integrated AUC of 0.761 (95% CI: 0.617–0.874) for the prediction of overall survival (p = 0.98). A combined clinical and radiomics model stratified patients into high-risk and low-risk groups with significantly different overall survival (p < 0.001). (4) Conclusions: Radiomics features based on preoperative CT scans have prognostic value in predicting overall survival before RC. Therefore, radiomics may guide early clinical decision-making.

Feasibility Analysis of Arterial CT Radiomics Model to Predict the Risk of Local and Metastatic Recurrence after Radical Cystectomy for Bladder Cancer

“…To date, several relevant studies have reported the application value of CT radiomics in predicting the prognosis after BCa surgery, among which Piotr Woznicki et al found that radiological features based on preoperative CT scans had prognostic value in predicting overall survival before RC in a study of 301 BCa patients who underwent RC and pelvic lymphadenectomy. Among them, the AUC of the clinical model was 0.761, and the AUC of the radiology model was 0.771, which suggests that the predictive performance of the radiomics model is comparable to that of the veri ed clinical parameters (11). Qian et al reported that radiomic features extracted from multistage CT images combined with important clinicopathological risk factors can predict the recurrence of BCa 2 years after surgery, but the recurrence of BCa after RC was not included separately in the systematic study (12,13).…”

A CT-based deep learning model predicts overall survival in patients with muscle invasive bladder cancer after radical cystectomy: a multicenter retrospective cohort study

“… 26 constructed radiomics signature from diffusion-weighted imaging (DWI) images to predict progression-free survival (PFS) in MIBC patients and radiomics signature alone achieved a C-index of 0.612 in the test data set. In another study, the combination of radiomics features extracted from tumor and lymph node regions and clinical parameters to predict OS in bladder cancer patients achieved a mean area under the ROC curve of 0.785 integrated over 1 to 7 years after RC 28 . Our study found that radiomics model based on handcrafted radiomics features was able to predict OS in MIBC patients, with comparable predictive performance to previous studies [C-index of 0.652 (95% CI: 0.566–0.741) in the internal validation set and 0.601 (95% CI: 0.493–0.694) in the external validation set].…”

“…However, few studies have focused on survival prediction, which is very important for decision-making on treatment options. These previous studies were single-center studies and just relied on handcrafted radiomics features 26 – 28 . To the best of our knowledge, there is currently no validated DL model based on preoperative enhanced CT image for predicting overall survival (OS) outcome in patients with MIBC.…”

AI-powered radiomics: revolutionizing detection of urologic malignancies

“…Although traditional histological evaluations have driven therapeutic decision-making, the invasive nature of these procedures has propelled the search for more refined, noninvasive techniques for risk stratification [50]. Recent studies have explored the use of AI-powered radiomics in imaging modalities including MRI and CT to preoperatively distinguish between histological subtypes of bladder cancer, predict muscle invasion, and even forecast survival or response to neoadjuvant chemotherapy treatment [51][52][53][54][55].…”

“…Evrimler et al assembled a CT-based radiomics model to predict the presence of histological variant BCa, which can further improve targeted therapy and guide treatment decisions [51]. Further devising ways to guide patient management, Zhang et al , Woźnicki et al and Gresser et al created models to predict which patients who would be good responders to neoadjuvant chemotherapy, overall survival rates after radical cystectomy, and potential for lymph node metastasis [54,55,62 ▪ ]. Notably, the majority of these studies have depended on manual segmentation of lesions to extract radiomics data.…”