Objective:

To summarize current advancements in the application of radiomics and deep learning in upper tract urothelial carcinoma (UTUC) and evaluate the methodological quality of existing studies.

Approach:

Key Findings:

• Radiomics and deep learning models show promising performance in predicting pathological grade, differentiating UTUC from renal cell carcinoma, assessing muscle invasion, and stratifying survival or recurrence risk.
• However, most studies are retrospective, single-center, and limited by small sample sizes, heterogeneous imaging protocols, inconsistent segmentation methods, insufficient external validation, and limited evidence of clinical utility.

Interpretation:

Radiomics and deep learning are promising for noninvasive preoperative risk stratification in UTUC, but further methodological standardization and validation are needed.

Limitations:

• Studies are primarily retrospective and single-center.
• Limited sample sizes and heterogeneous imaging protocols.
• Inconsistent segmentation methods and insufficient external validation.

Conclusion:

Future studies should focus on methodological standardization, multicenter external validation, and prospective evaluation.

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.