Role of Deep Learning in Optical Imaging

Imaging based problem solving approaches have shown an illustrative way of solving problems for various scientific applications, for several decades. With an increased demand for automation, such approaches have shown exponential growth in recent years. In this context, deep learning-based “learned” solutions are widely opted for many applications thus slowly becoming an inevitable alternative tool. It is known that in contrast to the conventional “physics-based” approach, deep learning models are known to be a “data-driven” approach where the outcomes are based on data analysis and interpretation. Thus, the deep learning approaches have applied for several (optical and computational) imaging based scientific problems such as denoising, phase retrieval, hologram reconstruction and histopathology, to name a few. In this talk, I will briefly discuss the role of deep learning networks for imaging-based problem solving applications and will provide the future direction for those approaches.