DeepPD: Joint Phase and Object Estimation from Phase Diversity with Neural Calibration of a Deformable Mirror

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schneider, Magdalena C., Johnson, Courtney, Allier, Cedric, Heinrich, Larissa, Adjavon, Diane, Husic, Joren, La Rivière, Patrick, Saalfeld, Stephan, Shroff, Hari
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910915061874688
author Schneider, Magdalena C.
Johnson, Courtney
Allier, Cedric
Heinrich, Larissa
Adjavon, Diane
Husic, Joren
La Rivière, Patrick
Saalfeld, Stephan
Shroff, Hari
author_facet Schneider, Magdalena C.
Johnson, Courtney
Allier, Cedric
Heinrich, Larissa
Adjavon, Diane
Husic, Joren
La Rivière, Patrick
Saalfeld, Stephan
Shroff, Hari
contents Sample-induced aberrations and optical imperfections limit the resolution of fluorescence microscopy. Phase diversity is a powerful technique that leverages complementary phase information in sequentially acquired images with deliberately introduced aberrations--the phase diversities--to enable phase and object reconstruction and restore diffraction-limited resolution. These phase diversities are typically introduced into the optical path via a deformable mirror. Existing phase-diversity-based methods are limited to Zernike modes, require large numbers of diversity images, or depend on accurate mirror calibration--which are all suboptimal. We present DeepPD, a deep learning-based framework that combines neural representations of the object and wavefront with a learned model of the deformable mirror to jointly estimate both object and phase from only five images. DeepPD improves robustness and reconstruction quality over previous approaches, even under severe aberrations. We demonstrate its performance on calibration targets and biological samples, including immunolabeled myosin in fixed PtK2 cells.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14157
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepPD: Joint Phase and Object Estimation from Phase Diversity with Neural Calibration of a Deformable Mirror
Schneider, Magdalena C.
Johnson, Courtney
Allier, Cedric
Heinrich, Larissa
Adjavon, Diane
Husic, Joren
La Rivière, Patrick
Saalfeld, Stephan
Shroff, Hari
Optics
Machine Learning
Sample-induced aberrations and optical imperfections limit the resolution of fluorescence microscopy. Phase diversity is a powerful technique that leverages complementary phase information in sequentially acquired images with deliberately introduced aberrations--the phase diversities--to enable phase and object reconstruction and restore diffraction-limited resolution. These phase diversities are typically introduced into the optical path via a deformable mirror. Existing phase-diversity-based methods are limited to Zernike modes, require large numbers of diversity images, or depend on accurate mirror calibration--which are all suboptimal. We present DeepPD, a deep learning-based framework that combines neural representations of the object and wavefront with a learned model of the deformable mirror to jointly estimate both object and phase from only five images. DeepPD improves robustness and reconstruction quality over previous approaches, even under severe aberrations. We demonstrate its performance on calibration targets and biological samples, including immunolabeled myosin in fixed PtK2 cells.
title DeepPD: Joint Phase and Object Estimation from Phase Diversity with Neural Calibration of a Deformable Mirror
topic Optics
Machine Learning
url https://arxiv.org/abs/2504.14157