Non-convex Super-resolution of OCT images via sparse representation
This work addresses image quality improvement for OCT analysis in medical imaging, but it is incremental as it builds on existing sparse representation techniques with non-convex penalties.
The paper tackles super-resolution of OCT images for murine eyes by proposing a non-convex variational model with sparsity enforced via dictionaries learned from high-resolution data, using α-stable distributions and non-convex penalties like Cauchy or MCP, and shows better performance compared to standard convex L1-based methods.
We propose a non-convex variational model for the super-resolution of Optical Coherence Tomography (OCT) images of the murine eye, by enforcing sparsity with respect to suitable dictionaries learnt from high-resolution OCT data. The statistical characteristics of OCT images motivate the use of α-stable distributions for learning dictionaries, by considering the non-Gaussian case, α=1. The sparsity-promoting cost function relies on a non-convex penalty - Cauchy-based or Minimax Concave Penalty (MCP) - which makes the problem particularly challenging. We propose an efficient algorithm for minimizing the function based on the forward-backward splitting strategy which guarantees at each iteration the existence and uniqueness of the proximal point. Comparisons with standard convex L1-based reconstructions show the better performance of non-convex models, especially in view of further OCT image analysis