Radiogenomics of muscle invasive bladder cancer.

Abstract

e16587 Background: Accurate staging of Muscle Invasive Bladder Cancer (MIBC) is essential to ensure optimal treatment (e.g., radical cystectomy vs. bladder preservation). However, currently about 1/3 of patients are overstaged and 1/3 are understaged. There is a pressing need of accurate noninvasive staging for MIBC to assist clinical decision making. Methods: In this preliminary study, an extensive radiogenomic analysis of MIBC cases was performed to identify potential indicators of MIBC stages, and to automate the staging process. A total of 28 MRI scans and their matched transcriptomic profiles were obtained from subjects diagnosed with MIBC at different stages. In the genomics, a bulk RNA-seq from FFPE tissues was performed that identified 3 major clusters, high, intermediate, and low infiltrating immune cells and fibroblasts. This was followed by a bioinformatic analyses, such as pathway enrichment and gene set enrichment analyses, 15 most significant signatures were identified for stage categorization of MIBC (Fig. 1). In the radiomics, several hundred image-based features from bladder tumor in MRI were extracted and analyzed. The tumors were manually outlined and grouped into lower-stage (stage I and II) and higher-stage (stage III and IV) by the trained radiologists. Using various statistical tests, several radiomic features (e.g., heterogeneity, inverse contrast, entropy) were inferred as significant at discriminating the two groups (Fig. 2). A naïve Bayes machine learning model was then used to integrate such features and perform automated binary classification of cases into their true class. A 4-fold cross validation was performed in which a unique 75% and 25% of 28 cases were used for training and testing of the model respectively. Results: The model performance was assessed in terms of prediction (binary classification) of stages as mean sensitivity, specificity, and accuracy, reaching 84%, 86%, and 86% respectively. Conclusions: The radiogenomics of MIBC provides insight into features associated with cancer stages. Assisted with AI, the discriminative features can accurately stage MIBC. Source of Funding: Cedars-Sinai Cancer Internal Funds: Developmental Funds for Investigator Initiated Trials Using Advanced Imaging Methods.