(UroToday.com) The 2023 SESAUA annual meeting included a bladder cancer session, featuring a presentation by Dr. Kyle Rose discussing multi-faceted genomic, pathologic, and artificial intelligence analysis on low grade, non-invasive bladder tumors and the prediction of signatures on downstream tumor recurrence. Low-grade noninvasive bladder cancer is a heterogeneous form of non-muscle invasive bladder cancer, characterized by some downstream tumor recurrences, requiring repeated resections and surveillance studies. Dr. Rose and colleagues aimed to perform a multi-faceted analysis on index low-grade noninvasive tumors including genomics, tumor microenvironment analysis, and artificial intelligence to identify predictors for later recurrences.
Low-grade noninvasive index tumors were stratified by those with no downstream recurrences (nonrecurrent) versus those with later recurrences (recurrent). RNA sequencing was performed to identify differentially expressed genes, then deconvoluted for cell-type using xCell. Pathologic analysis was performed by a dedicated genitourinary pathologist and a deep-learning artificial intelligence platform for validation. An artificial intelligence deep learning algorithm segmented nuclei from digital whole slide images of the tumor specimens to extract quantitative features. These features were then correlated to recurrence risk utilizing a multivariable Cox proportional hazards model, while recurrence free survival was examined using Kaplan-Meier analysis and log-rank test.
This study had 29 index bladder tumors/patients, 17 (59%) of which had later recurrence. The median follow-up was 59.0 months (IQR 48.5-75.8), and the median number of recurrences following initial diagnosis was 4 (IQR 2-10) in the recurrence cohort:
There were 238 differentially expressed genes recognized between groups.
Recurrent tumors distinctly expressed signatures for epithelial-mesenchymal transition, myogenesis, TNFα signaling via NFκB, and angiogenesis:
Recurrent tumors also demonstrated a higher TME, stroma, and cancer-associated fibroblast score:
Pathologic TME analysis validated these findings, with recurrent tumors demonstrating a higher frequency of inverted growth pattern and a higher median stroma percentage (p<0.01):
Finally, the artificial intelligence-derived morphological signature was predictive of recurrence with an AUROC of 0.81, and risk-stratified the cohort robustly with a hazard ratio of 5.43 (95% CI 1.1-26.76) for predicting high and low risk of recurrence. Patients in the high risk group had a 87.5% recurrence rate while those in the low risk group had a 28.5% recurrent rate:
Dr. Rose concluded his presentation discussing multi-faceted genomic, pathologic, and artificial intelligence analysis on low grade, non-invasive bladder tumors and the prediction of signatures on downstream tumor recurrence with the following take-home messages:
- Using a multi-disciplinary approach this study identified key signatures of recurrent low-grade noninvasive bladder cancer
- Characterization of these factors is a critical first step in the risk-stratification of low-grade noninvasive tumors, and may allow urologists to risk-stratify surveillance protocols
- Additionally, knowledge of these genomic pathways unique to recurrent tumors provides possible targets for chemoprevention trials
Presented by: Kyle Rose, MD, Moffitt Cancer Center, Tampa, FL
Co-authors: Aram Vosoughi, MD1, Gustavo Borjas, BS, MS1, Heather Huelster, MD1, Shreyas Naidu, BS1, Philippe Spiess, MD, FACS1, Anders Berglund, PhD1, Rohit Jain, MD1, Daniel Grass, MD1, David McConkey, MD2, Seth Lerner, MD3, Wade Sexton, MD1, Anirudh Joshi4, Nagi Kumar, PhD1, Roger Li, MD1
Affiliations: 1. Moffitt Cancer Center, 2. Johns Hopkins, 3. Baylor College of Medicine, 4. Valar Labs, Inc.
Written by: Zachary Klaassen, MD, MSc – Urologic Oncologist, Assistant Professor of Urology, Georgia Cancer Center, Augusta University/Medical College of Georgia, @zklaassen_md on Twitter during the 2023 Southeastern Section of the American Urological Association (SESAUA) Annual Meeting, Amelia Island, FL, Wed, Mar 15 – Sat, Mar 18, 2023.