Technical AI/DL Advances Syed Rakin Ahmed
Papers
Estimating test performance for AI medical devices under distribution shift with conformal prediction.
Inconsistent Partitioning and Unproductive Feature Associations Yield Idealized Radiomic Models.
Addressing catastrophic forgetting by modulating global batch normalization statistics for medical domain expansion
Cycle-GANs Generated Difference Maps to Interpret Race Prediction from Medical Images.
Improving the repeatability of deep learning models using novel loss function combination and optimization approaches.
An assessment of novel distance metric correlation with out-of-distribution performance of deep learning models.
A diffusion-inspired self-supervised framework for affine medical image registration.
The process of disentangling AI features associates with race and ethnicity in retinal images.
Presentations and Symposia
Distance metrics predict out-of-distribution performance of AI oncology models for clinical deployment.
Focal loss improves clinical deployability of deep learning models.
Estimating test performance for AI medical devices under distribution shift with conformal prediction.
Focal loss improves repeatability of deep learning models.
Hamiltonian Dynamics of Love Triangles.
Self-supervision and diabetic retinopathy.
Monitoring disease progression with stable diffusion: a visual approach.