Congratulations to Puja Saha on Her Successful Master's Defense!
We are thrilled to announce the successful master's defense of Puja Saha from the School of Engineering.
🎓 Puja Saha – MASc Graduate
Thesis: Optimizing Differentially Private Federated Learning for Medical Image Segmentation
Puja's thesis focused on developing a privacy-preserving and scalable federated learning framework for medical image segmentation, with methods specifically designed to minimize the privacy-induced trade-off in model performance.
This approach can enable the use of vast amounts of medical data across institutions that often remain under-utilized, to develop robust medical AI models, all while adhering to privacy regulations such as HIPAA, PIPEDA, and GDPR. She evaluated the approach across diverse imaging modalities (2D and 3D), varying levels of complexity, and real-world institutional heterogeneity, demonstrating significantly improved performance compared to conventional differential privacy-based federated learning methods.
Puja will soon be presenting this work at SPIE Medical Imaging in the Computer-Aided Diagnosis track. A journal article is also forthcoming, covering the method's effectiveness under real-world institutional heterogeneity.
We congratulate Puja on her remarkable achievement and her contribution to advancing healthcare and medical AI research. Her dedication, innovative approach, and successful defense are a testament to her hard work and the excellence of our graduate programs. 🎉
