Experimental insights into data augmentation techniques for deep learning-based multimode fiber imaging: limitations and success

TL;DR

This study investigates data augmentation techniques for deep learning-based multimode fiber imaging, revealing limitations of standard methods and proposing a physics-based augmentation that improves reconstruction quality under data scarcity.

Contribution

It provides the first systematic evaluation of augmentation methods in MMF imaging and introduces a novel physics-based augmentation approach that preserves light-fiber interaction physics.

Findings

Standard augmentations often fail or worsen results due to complex speckle physics.

Conditional GAN-based synthetic speckle generation does not improve reconstruction.

Physics-based augmentation increases SSIM by up to 17%.

Abstract

Multimode fiber~(MMF) imaging using deep learning has high potential to produce compact, minimally invasive endoscopic systems. Nevertheless, it relies on large, diverse real-world medical data, whose availability is limited by privacy concerns and practical challenges. Although data augmentation has been extensively studied in various other deep learning tasks, it has not been systematically explored for MMF imaging. This work provides the first in-depth experimental and computational study on the efficacy and limitations of augmentation techniques in this field. We demonstrate that standard image transformations and conditional generative adversarial-based synthetic speckle generation fail to improve, or even deteriorate, reconstruction quality, as they neglect the complex modal interference and dispersion that results in speckle formation. To address this, we introduce a physical data augmentation method in which only organ images are digitally transformed, while their corresponding speckles are experimentally acquired via fiber. This approach preserves the physics of light-fiber interaction and enhances the reconstruction structural similarity index measure~(SSIM) by up to 17\%, forming a viable system for reliable MMF imaging under limited data conditions.