Papers/2609.26920
🧪 Test?View on arXiv

Cross-Modal Contrastive Learning from Histopathology and CT for Automated Renal Cell Carcinoma Grading

Not specified in the provided content

cross-modalcontrastive learningmedical imagingcancer grading
2609.26920
Builder Relevance
70%
2h ago

Abstract

A cross-modal contrastive learning framework, RCC-Align, improves noninvasive CT-based grade prediction for clear cell renal cell carcinoma by aligning histopathology and CT data.

Reality Card

Core Claim

RCC-Align outperforms CT-only baselines in low-grade ccRCC prediction while requiring only CT data at inference.

Method / Result

Achieved an AUC of 0.601 and significantly improved low-grade prediction (p = 0.004).

Limitations

Validation in larger, multi-institutional cohorts with external testing is needed before clinical translation.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers