Assess students' ability to evaluate ethical, legal, and technical trade-offs when deploying federated learning across multiple institutions for medical imaging diagnostics. Scope includes privacy-preserving techniques (e.g., differential privacy, secure aggregation), sources and mitigation of dataset and algorithmic bias, impacts on diagnostic accuracy and clinical metrics (sensitivity, specificity, AUC), system constraints (communication, compute, model heterogeneity), and regulatory/governance considerations (HIPAA/GDPR, consent, liability). Require comparative analysis, quantification of trade-offs, and justified deployment recommendations.