Inverse 3D Microscopy Rendering for Cell Shape Inference with Active Mesh

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ichbiah, Sacha, Sinha, Anshuman, Delbary, Fabrice, Turlier, Hervé
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916873963044864
author Ichbiah, Sacha
Sinha, Anshuman
Delbary, Fabrice
Turlier, Hervé
author_facet Ichbiah, Sacha
Sinha, Anshuman
Delbary, Fabrice
Turlier, Hervé
contents Traditional methods for biological shape inference, such as deep learning (DL) and active contour models, face important limitations in 3D. DL approaches require large annotated datasets, which are often impractical to obtain, while active contour methods depend on carefully tuned heuristics for intensity attraction and shape regularization. We introduce deltaMic, a novel differentiable 3D renderer for fluorescence microscopy that formulates shape inference as an inverse problem. By leveraging differentiable convolutions, deltaMic simulates the image formation process, integrating a parameterized point spread function (PSF) with a triangle mesh-based representation of biological structures. Unlike DL- or contour-based segmentation, deltaMic directly optimizes both shape and optical parameters to align synthetic and real microscopy images, removing the need for large datasets or sample-specific fine-tuning. To ensure scalability, we implement a GPU-accelerated Fourier transform for triangle meshes along with narrow-band spectral filtering. We show that deltaMic accurately reconstructs cell geometries from both synthetic and diverse experimental 3D microscopy data, while remaining robust to noise and initialization. This establishes a new physics-informed framework for biophysical image analysis and inverse modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2303_10440
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Inverse 3D Microscopy Rendering for Cell Shape Inference with Active Mesh
Ichbiah, Sacha
Sinha, Anshuman
Delbary, Fabrice
Turlier, Hervé
Biological Physics
Quantitative Methods
68U10
I.4.6; I.4.7; I.4.8; I.3.3; I.3.5; I.3.7
Traditional methods for biological shape inference, such as deep learning (DL) and active contour models, face important limitations in 3D. DL approaches require large annotated datasets, which are often impractical to obtain, while active contour methods depend on carefully tuned heuristics for intensity attraction and shape regularization. We introduce deltaMic, a novel differentiable 3D renderer for fluorescence microscopy that formulates shape inference as an inverse problem. By leveraging differentiable convolutions, deltaMic simulates the image formation process, integrating a parameterized point spread function (PSF) with a triangle mesh-based representation of biological structures. Unlike DL- or contour-based segmentation, deltaMic directly optimizes both shape and optical parameters to align synthetic and real microscopy images, removing the need for large datasets or sample-specific fine-tuning. To ensure scalability, we implement a GPU-accelerated Fourier transform for triangle meshes along with narrow-band spectral filtering. We show that deltaMic accurately reconstructs cell geometries from both synthetic and diverse experimental 3D microscopy data, while remaining robust to noise and initialization. This establishes a new physics-informed framework for biophysical image analysis and inverse modeling.
title Inverse 3D Microscopy Rendering for Cell Shape Inference with Active Mesh
topic Biological Physics
Quantitative Methods
68U10
I.4.6; I.4.7; I.4.8; I.3.3; I.3.5; I.3.7
url https://arxiv.org/abs/2303.10440