Bladder Cancer and Artificial Intelligence: Emerging Applications

Abstract

Bladder cancer is a common and heterogeneous disease that poses a significant burden to the patient and health care system. Major unmet needs include effective early detection strategy, imprecision of risk stratification, and treatment-associated morbidities. The existing clinical paradigm is imprecise, which results in missed tumors, suboptimal therapy, and disease progression. Artificial intelligence holds immense potential to address many unmet needs in bladder cancer, including early detection, risk stratification, treatment planning, quality assessment, and outcome prediction. Despite recent advances, extensive work remains to affirm the efficacy of artificial intelligence as a decision-making tool for bladder cancer management.

Keywords: AI-assisted diagnosis; Artificial intelligence; Bladder cancer; Deep learning; Image processing; Outcome prediction; Treatment planning; Urology.

Fig. 1.

Application of artificial intelligence for bladder cancer diagnosis and outcome prediction. AI can be used for bladder cancer diagnosis and outcome prediction. Subapplications of bladder cancer diagnosis include tumor detection, staging, grading, and segmentation. For outcome prediction, prediction of recurrence, survival, and chemotherapy response have also been investigated using AI. Challenges to be addressed before integration into the clinical workflow include ensuring that AI models be generalizable, interpretable, and specific enough to not overburden the existing health care system with false-positive diagnoses. CT, computed tomography; H&E, hematoxylin-eosin.

Fig. 2.

Representative sample of the types of bladder tumors encountered during TURBT overlayed with expert-verified annotations. Here one can observe the wide variety of tumor morphologies, locations, and sizes, along with various pathologic assessments (not pictured).