Multi-frame Restoration for High-rate Lissajous Confocal Laser Endomicroscopy

TL;DR

This paper introduces a benchmark and a novel recurrent framework called MIRA for high-rate Lissajous confocal laser endomicroscopy, improving image restoration quality while maintaining clinical efficiency.

Contribution

The work presents the first benchmark dataset for high-rate Lissajous CLE and proposes MIRA, a lightweight recurrent model that effectively restores high-speed imaging data.

Findings

MIRA outperforms baseline methods in restoration quality.

MIRA maintains computational efficiency suitable for clinical use.

The benchmark dataset enables future research in high-rate CLE restoration.

Abstract

Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high speed in vivo optical biopsy for handheld scenarios. However, Lissajous scanning traces a resonant trajectory and samples only the visited pixels per frame; at high frame rates, many pixels remain unvisited, creating structured holes. In this work, we introduce the first benchmark for high-rate Lissajous CLE, consisting of low-quality video clips paired with high-quality reference images. The reference images are wide-FOV mosaics obtained by stitching stabilized, slow-scan frames of the same tissue, enabling temporally aligned supervision. Using this dataset, we propose MIRA, a lightweight recurrent framework for Lissajous CLE restoration that iteratively aggregates temporal context through feature reuse and displacement alignment. Our experiments demonstrate that MIRA outperforms both lightweight and high-complexity baselines in restoration quality while maintaining a favorable computational efficiency suitable for clinical deployment.