Hyperspectral Dual-Comb Compressive Imaging for Minimally-Invasive Video-Rate Endomicroscopy

TL;DR

This paper introduces a novel hyperspectral dual-comb compressive imaging technique that enables real-time, high-resolution endomicroscopy using minimal hardware, combining optical frequency combs, ghost imaging, and deep learning for rapid image reconstruction.

Contribution

It presents a new integrated approach that combines dual-comb interferometry, compressive ghost imaging, and transformer-based deep learning for minimally invasive, high-speed endomicroscopy.

Findings

Achieves video-rate imaging with high fidelity.

Eliminates the need for spatial and spectral scanning.

Outperforms classical ghost imaging in speed and accuracy.

Abstract

Endoscopic imaging is essential for real-time visualization of internal organs, yet conventional systems remain bulky, complex, and expensive due to their reliance on large, multi-element optical components. This limits their accessibility to delicate or constrained anatomical regions. Achieving real-time, high-resolution endomicroscopy using compact, low-cost hardware at the hundred-micron scale remains an unsolved challenge. Optical fibers offer a promising route toward miniaturization by providing sub-millimeter-scale imaging channels; however, existing fiber-based methods typically rely on raster scanning or multicore bundles, which limit the resolution and imaging speed. In this work, we overcome these limitations by integrating dual-comb interferometry with compressive ghost imaging and advanced computational reconstruction. Our technique, hyperspectral dual-comb compressive imaging, utilizes optical frequency combs to generate wavelength-multiplexed speckle patterns that are delivered through a single-core fiber and detected by a single-pixel photodetector. This parallel speckle illumination and detection enable snapshot compression and acquisition of image information using zero-dimensional hardware, completely eliminating the need for both spatial and spectral scanning. To decode these highly compressed signals, we develop a transformer-based deep learning model capable of rapid, high-fidelity image reconstruction at extremely low sampling ratios. This approach significantly outperforms classical ghost imaging methods in both speed and accuracy, achieving video-rate imaging with a dramatically simplified optical front-end. Our results represent a major advance toward minimally invasive, cost-effective endomicroscopy and provide a generalizable platform for optical sensing in applications where hardware constraints are critical.