Survival Prediction of Patients with Bladder Cancer after Cystectomy Based on Clinical, Radiomics, and Deep-Learning Descriptors

SIMPLE SUMMARY: Survival prediction of bladder cancer patients following cystectomy is essential for treatment planning. We propose a hybrid method that integrates clinical, radiomics, and deep-learning descriptors to improve survival prediction models. This approach demonstrates potential for more accurately predicting survival and prognosis in radical cystectomy treatment and in determining whether imaging adds additional predictive value over patients’ clinical information. ABSTRACT: Accurate survival prediction for bladder cancer patients who have undergone radical cystectomy can improve their treatment management. However, the existing predictive models do not take advantage of both clinical and radiological imaging data. This study aimed to fill this gap by developing an approach that leverages the strengths of clinical (C), radiomics (R), and deep-learning (D) descriptors to improve survival prediction. The dataset comprised 163 patients, including clinical, histopathological information, and CT urography scans. The data were divided by patient into training, validation, and test sets. We analyzed the clinical data by a nomogram and the image data by radiomics and deep-learning models. The descriptors were input into a BPNN model for survival prediction. The AUCs on the test set were (C): 0.82 ± 0.06, (R): 0.73 ± 0.07, (D): 0.71 ± 0.07, (CR): 0.86 ± 0.05, (CD): 0.86 ± 0.05, and (CRD): 0.87 ± 0.05. The predictions based on D and CRD descriptors showed a significant difference ([Formula: see text] = 0.007). For Kaplan–Meier survival analysis, the deceased and alive groups were stratified successfully by C ([Formula: see text] < 0.001) and CRD ([Formula: see text] < 0.001), with CRD predicting the alive group more accurately. The results highlight the potential of combining C, R, and D descriptors to accurately predict the survival of bladder cancer patients after cystectomy.