Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2611.05983

Perturbation-Based Reconstruction of Depth-Resolved OCT Attenuation without Requiring a Fully Decayed Signal Tail

Jinglun Yu·Yaning Wang·Shuwen Wei·Jin U. Kang
View original source ↗Read source document ↗Export metadata ↓

Abstract

Depth-resolved attenuation in optical coherence tomography (OCT) can provide quantitative optical contrast beyond structural imaging. However, conventional reconstruction methods can be biased when the OCT signal does not fully decay within the imaging range or when the distal signal tail is dominated by noise or residual reflections from distal sample or support interfaces. Here, we present a perturbation-based Beer-Lambert framework that combines a zeroth-order exponential estimate with a first-order correction, reducing reliance on the unreliable distal signal tail below the current depth. Numerical A-line simulations, Monte Carlo modeling, multilayer silicone-dye-TiO2 phantoms, and ex vivo bovine retina experiments were used to evaluate the method under finite-depth and heterogeneous imaging conditions. The numerical A-line tests showed reduced depth-dependent error against prescribed attenuation profiles; the Monte Carlo comparisons showed less distal drift relative to model-defined benchmarks, while the phantom profiles were compared with separately acquired single-layer OCT calibration values. In a Monte Carlo component test that withheld vessel-mask and vessel-boundary information from reconstruction and used that information only for post hoc evaluation, the first-order correction recovered 61% of the segmentation-informed target vessel contrast and reduced vessel ROI mean absolute error by 65% relative to the fixed zeroth-order baseline. These results suggest that perturbation-based reconstruction may provide a practical approach for depth-resolved reconstruction of effective OCT attenuation when the fully decayed A-line condition is not satisfied.

Explore related subjects

eess.IVphysics.optics

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jinglun Yu, Yaning Wang, Shuwen Wei, Jin U. Kang. 2026-11-04. Perturbation-Based Reconstruction of Depth-Resolved OCT Attenuation without Requiring a Fully Decayed Signal Tail. https://arxiv.org/abs/2611.05983

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

RPL-UIE: Reference-Guided Prior Learning for Content-Preserving Underwater Image Enhancement

Underwater image enhancement (UIE) aims to recover clear images from observations degraded by wavelength-dependent absorption, scattering, and spatially nonuniform degradation. Although existing generative methods can handle complex degradations, they may still generate visually appealing results while compromising content preservation, thereby degrading downstream visual perception. To improve content preservation, we extract spatial priors characterizing appearance and photometric properties from ground-truth images to provide stable guidance for enhancement. To bridge the gap between training with ground-truth references and inference without references, we propose reference-guided prior learning for underwater image enhancement (RPL-UIE), a two-stage teacher-student framework. The teacher network extracts stable priors from ground-truth images, while the student network takes only degraded images as input and learns to mimic the teacher's prior extraction capability. We further design Residual Prior Refinement Diffusion (RPRD) and Frequency-Aware Prior Residual Calibration (FPRC) to reduce the prior discrepancy between the teacher and student. RPRD progressively predicts corrections in the residual space, while FPRC preserves stable low-frequency residuals and selectively modulates high-frequency details. Experiments on multiple underwater image datasets show that RPL-UIE achieves competitive enhancement performance. For the engineering application of underwater visual perception, downstream object detection and instance segmentation experiments show that RPL-UIE improves visual quality while better preserving object structures and semantic content needed for reliable perception. Tests on real-world data collected by a custom-built remotely operated vehicle (ROV) further demonstrate its effectiveness and practical applicability.

eess.IV↗
arXiv2026

Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter. Lattice vector quantization (LVQ), on the other hand, presents a compelling alternative, which can exploit inter-feature dependencies more effectively while keeping computational efficiency almost the same as scalar quantization. However, traditional LVQ structures are designed/optimized for uniform source distributions, hence nonadaptive and suboptimal for real source distributions of latent code space for Neural image compression tasks. In this paper, we propose a novel learning method to overcome this weakness by designing the rate-distortion optimal lattice vector quantization (OLVQ) codebooks with respect to the sample statistics of the latent features to be compressed. By being able to better fit the LVQ structures to any given latent sample distribution, the proposed OLVQ method improves the rate-distortion performances of the existing quantization schemes in neural image compression significantly, while retaining the amenability of uniform scalar quantization. Code is available at: https://github.com/xzhang9308/OLVQ.

eess.IV↗
arXiv2026

Deep Pseudo-Proximal Map: A Self-Supervised Data-Fitting Agent for Iterative Reconstruction

Iterative algorithms for inverse imaging problems split reconstruction into alternating subproblems, one of which requires evaluating the data-fitting proximal map. In many practical cases, this proximal map has no analytic solution and so must be approximated by an inner loop solver at every iteration, compounding the cost of the outer reconstruction loop. To address this, we propose the pseudo-proximal map (PPM), a reformulation of the data-fitting proximal map as the minimum mean square error estimate of a synthetic probabilistic model. We implement the deep PPM as a self-supervised neural network trained only on sampled Gaussian noise, requiring no ground-truth training images. The deep PPM can be trained for any operator for which the forward model $A$ and its transpose $A^T$ can be evaluated, with provable equivalence to the proximal map when $A$ is linear. We validate the deep PPM on Gaussian deblurring and 4x super-resolution, where the proximal map has an analytic solution, and on X-ray computed tomography (XCT), where no analytic solution exists. Used as the data-fitting agent within an iterative reconstruction method, the deep PPM reproduces the reference reconstruction to within 1% NRMSE for all three operators, and for XCT, it replaces the inner conjugate-gradient loop with a single network evaluation that is 18x faster.

eess.IV↗