CellINR: Implicitly Overcoming Photo-induced Artifacts in 4D Live Fluorescence Microscopy

TL;DR

CellINR is a novel neural representation framework that effectively removes photo-induced artifacts in 4D live fluorescence microscopy, enhancing image quality and structural continuity for biological research.

Contribution

The paper introduces CellINR, a case-specific implicit neural approach that outperforms existing methods in artifact removal and structural reconstruction in 4D microscopy.

Findings

Significantly better artifact removal compared to existing techniques.

Provides the first paired 4D live cell imaging dataset for evaluation.

Enables high-accuracy cellular structure reconstruction.

Abstract

4D live fluorescence microscopy is often compromised by prolonged high intensity illumination which induces photobleaching and phototoxic effects that generate photo-induced artifacts and severely impair image continuity and detail recovery. To address this challenge, we propose the CellINR framework, a case-specific optimization approach based on implicit neural representation. The method employs blind convolution and structure amplification strategies to map 3D spatial coordinates into the high frequency domain, enabling precise modeling and high-accuracy reconstruction of cellular structures while effectively distinguishing true signals from artifacts. Experimental results demonstrate that CellINR significantly outperforms existing techniques in artifact removal and restoration of structural continuity, and for the first time, a paired 4D live cell imaging dataset is provided for evaluating reconstruction performance, thereby offering a solid foundation for subsequent quantitative analyses and biological research. The code and dataset will be public.