HistoSpeckle-Net: Mutual Information-Guided Deep Learning for high-fidelity reconstruction of complex OrganAMNIST images via perturbed Multimode Fibers Article Swipe

MAKE IMPACT

Maqbool, Jawaria , Cheema, M. Imran · YOU? · · 2025 · Open Access ·

Existing deep learning methods in multimode fiber (MMF) imaging often focus on simpler datasets, limiting their applicability to complex, real-world imaging tasks. These models are typically data-intensive, a challenge that becomes more pronounced when dealing with diverse and complex images. In this work, we propose HistoSpeckle-Net, a deep learning architecture designed to reconstruct structurally rich medical images from MMF speckles. To build a clinically relevant dataset, we develop an optical setup that couples laser light through a spatial light modulator (SLM) into an MMF, capturing output speckle patterns corresponding to input OrganAMNIST images. Unlike previous MMF imaging approaches, which have not considered the underlying statistics of speckles and reconstructed images, we introduce a distribution-aware learning strategy. We employ a histogram-based mutual information loss to enhance model robustness and reduce reliance on large datasets. Our model includes a histogram computation unit that estimates smooth marginal and joint histograms for calculating mutual information loss. It also incorporates a unique Three-Scale Feature Refinement Module, which leads to multiscale Structural Similarity Index Measure (SSIM) loss computation. Together, these two loss functions enhance both the structural fidelity and statistical alignment of the reconstructed images. Our experiments on the complex OrganAMNIST dataset demonstrate that HistoSpeckle-Net achieves higher fidelity than baseline models such as U-Net and Pix2Pix. It gives superior performance even with limited training samples and across varying fiber bending conditions. By effectively reconstructing complex anatomical features with reduced data and under fiber perturbations, HistoSpeckle-Net brings MMF imaging closer to practical deployment in real-world clinical environments.

Type

article

Landing Page

http://arxiv.org/abs/2511.20245

PDF

https://arxiv.org/pdf/2511.20245

OA Status

green

OpenAlex ID

https://openalex.org/W7106862066

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W7106862066

Canonical identifier for this work in OpenAlex

Title

HistoSpeckle-Net: Mutual Information-Guided Deep Learning for high-fidelity reconstruction of complex OrganAMNIST images via perturbed Multimode Fibers

Work title

Type

article

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-11-25

Full publication date if available

Authors

Maqbool, Jawaria, Cheema, M. Imran

List of authors in order

Landing page

https://arxiv.org/abs/2511.20245

Publisher landing page

PDF URL

https://arxiv.org/pdf/2511.20245

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2511.20245

Direct OA link when available

Concepts

Computer science, Deep learning, Artificial intelligence, Robustness (evolution), Speckle pattern, Histogram, Fidelity, Multi-mode optical fiber, Computer vision, Iterative reconstruction, Pattern recognition (psychology), Mutual information, Focus (optics), High fidelity, Feature (linguistics), Speckle noise, Computation, Feature learning, Algorithm, Metric (unit), Artificial neural network, Data modeling, Optical flow, Similarity measure, Wasserstein metric, Similarity (geometry), Segmentation, Medical imaging

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Full payload