Related Experiment Video
Updated: May 5, 2026
07:48
An Orthotopic Bladder Cancer Model for Gene Delivery Studies
Published on: December 1, 2013
13.2K
Computational pathology in bladder cancer: A scoping review
Michael Superdock1, Sara E Wobker1,2, Iain Carmicheal2,3
1Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
Bladder Cancer (Amsterdam, Netherlands)
|March 2, 2026
Summary
Computational pathology, using artificial intelligence (AI), shows promise for bladder cancer diagnosis and treatment. This review synthesizes current AI applications in analyzing pathology images for improved patient care.
Area of Science:
- Digital pathology and artificial intelligence (AI) in oncology.
- Computational pathology for histopathology image analysis.
Background:
- Histologic assessment is crucial for bladder cancer diagnosis and management.
- Digital pathology and AI are advancing the analysis of pathology images.
- Computational pathology offers a new approach to extract information from bladder cancer tissue.
Purpose of the Study:
- To provide a comprehensive overview of computational pathology in bladder cancer.
- To describe AI and machine learning approaches for whole slide image (WSI) analysis.
- To summarize AI applications in bladder cancer diagnosis, grading, staging, molecular classification, prognostication, and treatment response prediction.
Main Methods:
- Scoping review conducted following PRISMA-ScR 2018 guidelines.
- Searched PubMed/MEDLINE for studies on computational or AI-based analysis of bladder cancer histopathology images.
- Included 53 studies after screening 2055 abstracts and full-text review.
Main Results:
- Fifty-three studies met the eligibility criteria for the review.
- The review synthesized findings narratively based on predefined predictive tasks.
Conclusions:
- Computational pathology holds significant potential for enhancing pathologist workflows and personalized bladder cancer care.
- While current studies are largely retrospective, rapid innovation points towards clinical implementation.
- Standardized frameworks and multi-institutional datasets are needed to accelerate the adoption of computational pathology tools in bladder cancer.
