What question did this study set out to answer?

To enhance lymph node metastasis detection in pancreatic cancer using a federated deep learning framework.

April 11, 2026Scientific ReportsOpen Access

Federated CT foundation models for multi-center detection of lymph node metastasis in pancreatic cancer

View Full Paper

Ask AI

Bookmark

Authors

Multi-center study demonstrates improved lymph node metastasis detection in pancreatic cancer using advanced federated learning.

To enhance lymph node metastasis detection in pancreatic cancer using a federated deep learning framework.
Conducted a retrospective multi-center study with 546 patients.
Utilized a CT Vision Foundation Model pre-trained on 148,000 scans.
Employed a federated learning approach to mitigate inter-institutional variability.
Compared performance against classical machine learning baselines.
Achieved a balanced accuracy of 0.601 and a diagnostic odds ratio of 3.45.
Improved balanced accuracy by 12.6% over the standard FedAvg method.
Demonstrated superior discriminative ability across all participating cohorts.

Bhalla et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark