Model-free estimation of the Cramér-Rao bound for deep-learning microscopy in complex media

Abstract

Artificial neural networks have become important tools to harness the complexity of disordered or random photonic systems. Recent applications include the recovery of information from light that has been scrambled during propagation through a complex scattering medium, especially in the challenging case where the deterministic input-output transmission matrix cannot be measured. This naturally raises the question of what the limit is that information theory imposes on this recovery process, and whether neural networks can actually reach this limit. To answer these questions, we introduce a model-free approach to calculate the Cramér-Rao bound, which sets the ultimate precision limit at which artificial neural networks can operate. As an example, we apply this approach in a proof-of-principle experiment using laser light propagating through a disordered medium, evidencing that a convolutional network approaches the ultimate precision limit in the challenging task of localizing a reflective target hidden behind a dynamically-fluctuating scattering medium. The model-free method introduced here is generally applicable to benchmark the performance of any deep-learning microscope, to drive algorithmic developments and to push the precision of metrology and imaging techniques to their ultimate limit.

References in corpus (24)

• Advances in Quantum Metrology
• Measuring the Transmission Matrix in Optics : An Approach to the Study and Control of Light Propagation in Disordered Media
• Non-invasive real-time imaging through scattering layers and around corners via speckle correlations
• Image Transmission Through an Opaque Material
• Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media
• Transmission of natural scene images through a multimode fibre
• Sparsity-based single-shot sub-wavelength coherent diffractive imaging
• Roadmap on Wavefront Shaping and deep imaging in complex media
• An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
• Efficient and accurate inversion of multiple scattering with deep learning
• Controlling light propagation in multimode fibers for imaging, spectroscopy and beyond
• Light scattering control in transmission and reflection with neural networks
• Image transmission through a flexible multimode fiber by deep learning
• Deep learning in biomedical optics
• Maximum information states for coherent scattering measurements
• All-optical image classification through unknown random diffusers using a single-pixel diffractive network
• Tracking moving objects through scattering media via speckle correlations
• Displacement-agnostic coherent imaging through scatter with an interpretable deep neural network
• Robust Position Sensing with Wave Fingerprints in Dynamic Complex Environments
• Fundamental bounds on the precision of classical phase microscopes
• Influence of the local scattering environment on the localization precision of single particles
• Subwavelength position sensing using nonlinear feedback and wave chaos
• Correlations between reflected and transmitted intensity patterns emerging from opaque disordered media
• Optimizing illumination for precise multi-parameter estimations in coherent diffractive imaging