DeepFilters: Scattering-Aware Pupil Engineering with Learned Digital Filter Reconstruction for Extended Depth of Field Microscopy

TL;DR

DeepFilters is a novel microscopy framework that combines scattering-aware optical design with digital reconstruction to significantly extend the depth of field in biological tissues.

Contribution

It introduces a joint optimization of pupil filters and digital filters using a differentiable model, enabling robust imaging in scattering tissues without retraining.

Findings

Extended PSF from 16 to over 400 microns in clear media

Achieved signal recovery beyond 120 microns in biological tissues

Validated across brain slices and sea urchin embryos

Abstract

Extended depth of field microscopy encodes axial information into a single acquisition through engineered point spread functions, but conventional and deep optics approaches are subject to degradation in scattering tissue. We introduce DeepFilters, a scattering-aware deep optics framework that jointly optimizes a parameterized pupil filter and a digital-filter-based reconstruction network through a calibrated differentiable forward model to achieve broad generalization without retraining. Incorporating empirical scattering kernels, physics-guided regularization, and a hybrid genetic-gradient initialization strategy, DeepFilters extends the PSF from 16 micron to >400 micron in clear media and enables signal recovery beyond 120 micron deep in biological tissues, validated across fixed brain slices and sea urchin embryos.