Abstract
Background and objective
Highrisk nonmuscleinvasive bladder cancer (HRNMIBC) is treated with transurethral resection and intravesical BCG instillations, yet 50% recur and 20% progress to invasive disease. Although molecular subtyping, e.g., BCG-response-subtype (BRS), is associated with progression risk and may aid risk stratification, yet is costly and time-consuming. Intratumoral heterogeneity complicates accurate subtyping. To address these challenges, we developed a deep-learning model that predicts BRS from routine hematoxylin-eosin-stained images. We verified the model's area-by-area predictions against tissue-level gene-expression maps.
Methods and participants
Hematoxylin-eosin-stained images from 231 HR-NMIBC patients with known BRS were used to develop a deep-learning model through cross-validation, then validated in 83 independent samples. The model's spatial predictions were assessed using spatial transcriptomics to map gene expression to tissue locations in five HR-NMIBC tumors.
Outcome measurements and statistical analysis
Discriminative ability for BRS3 vs. BRS1/2 was measured by AUC. Spatial alignment was assessed by calculating Pearson and Spearman correlation coefficients between model predictions and BRS fractions; significance was assessed through permutation analysis.
Key findings and limitations
The trained algorithm achieved AUC of 0.79 (development) and 0.71 (external) to detect BRS3 vs BRS1/2. Tile-level correlation between model output and molecular labels was significant (Pearson r = 0.33-0.44; p <= 0.002). Limitations include retrospective sampling and limited spatial transcriptomic cases.
Conclusions and clinical implications
Our trained algorithm showed potential to stratify HRNMIBC patients by clinically relevant BCGresponse subtypes using routine hematoxylin-eosin-stained images and showed predicted spatial heterogeneity comparable to molecular profiling. Prospective validation is required before any clinical implementation.
Patient summary
Standard pathology images contain hidden details related to tumor's molecular subtype. We trained an AI model to read these routine images and identify specific bladder cancer subtypes associated with poor response to BCG therapy. This approach may help reveal molecular subtype-associated information from routine pathology images, without additional laboratory procedures.