# End-to-end reconstruction of OCT optical properties and speckle-reduced structural intensity via physics-based learning

arXiv: https://arxiv.org/abs/2602.02721 · HTML: https://mlsanity.com/paper/2602.02721/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 7 of 7)

- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [The Neural Networks Based Needle Detection for Medical Retinal Surgery](https://mlsanity.com/paper/2302.05034/) (2023)
- [Reimagining partial thickness keratoplasty: An eye mountable robot for autonomous big bubble needle insertion](https://mlsanity.com/paper/2410.14577/) (2024)
- [Topology-based deep-learning segmentation method for deep anterior lamellar keratoplasty (DALK) surgical guidance using M-mode OCT data](https://mlsanity.com/paper/2501.04735/) (2025)
- [Kalman filter/deep-learning hybrid automatic boundary tracking of optical coherence tomography data for deep anterior lamellar keratoplasty (DALK)](https://mlsanity.com/paper/2501.15311/) (2025)
- [Super-Resolution Optical Coherence Tomography Using Diffusion Model-Based Plug-and-Play Priors](https://mlsanity.com/paper/2505.14916/) (2025)
- [PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior](https://mlsanity.com/paper/2512.18367/) (2025)

## Abstract (arXiv)

Inverse scattering in optical coherence tomography (OCT) seeks to recover both structural images and intrinsic tissue optical properties, including refractive index, scattering coefficient, and anisotropy. This inverse problem is challenging due to attenuation, speckle noise, and strong coupling among parameters. We propose a regularized end-to-end deep learning framework that jointly reconstructs optical parameter maps and speckle-reduced OCT structural intensity for layer visualization. Trained with Monte Carlo-simulated ground truth, our network incorporates a physics-based OCT forward model that generates predicted signals from the estimated parameters, providing physics-consistent supervision for parameter recovery and artifact suppression. Experiments on the synthetic corneal OCT dataset demonstrate robust optical map recovery under noise, improved resolution, and enhanced structural fidelity. This approach enables quantitative multi-parameter tissue characterization and highlights the benefit of combining physics-informed modeling with deep learning for computational OCT.