MicroDiffuse3D: A Foundation Model for 3D Microscopy Imaging Restoration

2026-05-08

AI Summary

Three-dimensional chemical imaging is hindered by slow acquisition speeds and low signal-to-noise ratios, making high-quality volumetric reconstruction at high throughput challenging. This work proposes MicroDiffuse3D—the first pre-trained diffusion foundation model tailored for 3D microscopic image restoration—which leverages a large-scale 3D diffusion architecture to unify diverse tasks including super-resolution, joint degradation restoration, and denoising under low signal-to-noise conditions. Evaluated under 16× sparse sampling, the method substantially outperforms strong existing baselines, achieving a 10.58% improvement in segmentation quality and a 15.59% gain in line-profile consistency, thereby enabling efficient and generalizable high-fidelity 3D structural reconstruction in high-throughput settings.

Abstract

Chemical imaging enables label-free visualization of cells, tissues and living systems while providing direct biochemical information that is difficult to obtain with conventional fluorescence microscopy. Despite its promise in applications ranging from intraoperative diagnosis to drug-response analysis, its broader use remains limited by slow data acquisition, particularly for three-dimensional imaging. Here we present MicroDiffuse3D, a pretrained foundation model for 3D microscopy image restoration that recovers high-quality volumetric structure from degraded low-resolution measurements acquired at substantially higher throughput. We evaluated MicroDiffuse3D across three challenging restoration settings, including 3D super-resolution under 16-fold volumetric sparsity, joint degradation in resolution and noise, and 3D denoising in the low signal-to-noise ratio (SNR) regime, where the model delivered clear gains over strong baselines. Under the sparse 3D super-resolution setting, MicroDiffuse3D produced clearer continuity across depth with fewer artifacts and improved segmentation quality by 10.58% and line-profile concordance by 15.59%. Together, our results establish pretrained 3D restoration as a broadly applicable strategy for overcoming the throughput and SNR limitations in volumetric chemical imaging, enabling high-resolution analysis at scales and speeds that were previously difficult to achieve.

Problem

• 3D microscopy
• image restoration
• chemical imaging
• throughput limitation
• low signal-to-noise ratio

Innovation

• 3D microscopy restoration
• foundation model
• super-resolution
• denoising
• chemical imaging