OCTN: Neural OCT Representations for Robot-Guided Precision Intervention

Ravi Prakash; Ryan P. McNabb; Patrick J. Codd; Shan Lin

cs.ROSep 6, 2026

OCTN: Neural OCT Representations for Robot-Guided Precision Intervention

Authors: Ravi Prakash, Ryan P. McNabb, Patrick J. Codd, Shan Lin

Organizations: Duke University, Durham, NC 27705 USA · Arizona State University, Phoenix, AZ 85287 USA

Abstract

Optical coherence tomography (OCT) offers compact, contactless, micron-scale imaging suitable for intraoperative guidance, but native OCT volumes are discretely sampled, anisotropic, and currently inefficient for downstream geometric reasoning and robot integration. We present OCTN (pronounced "octane"), an implicit neural representation framework that converts volumetric OCT scans into a continuous, differentiable, and spatially faithful tissue-intensity field. OCTN uses a two-stage hybrid training strategy that combines supervision from acquired voxels with inter-slice interpolations, preserving B-scan fidelity while improving continuity in sparsely sampled regions. For versatility, we first show that OCTN enables fast volumetric reasoning by storing the learned tissue representation natively on the GPU, supporting intensity-based spatial queries with up to 43x speedup over conventional CPU processing. We then demonstrate OCTN-enabled OCT-guided robotic laser surgery where the continuous tissue representation supports implicit surface discovery and surface-constrained path planning via multiple optimization strategies, including Newton- and SGD-based optimization. Next, OCTN enables reconstruction of dense volumetric structure from sparsely acquired B-scans, while reducing acquisition time by 4x and preserving clinically relevant structures. Across the newly generated Duke TissueOCT dataset and public OCT datasets, OCTN achieves robust, high-fidelity reconstruction with PSNR > 30 dB and training time < 10 s, while preserving surface consistency within 10 $μ$ m Chamfer distance relative to baseline reconstruction. The TissueOCT dataset and code are publicly available at raprakashvi.github.io/octn

Figures & tables

Fig. 1: System overview. a) OCTN maps discrete, anisotropic OCT voxels to a continuous tissue-intensity field using on-grid samples and off-grid inter-slice supervision. Its multiresolution hash-grid and MLP enable fast training, arbitrary spatial queries, and $4\times$ sparse acquisition. b) OCTN supports smooth, surface-aware robotic laser path planning. c) OCTN balances sparse C-scan reconstruction, image fidelity, fast 3D querying, and surface constraints. d) Its GPU-native representation enables threshold-based tissue queries with up to $43\times$ faster spatial reasoning.

Fig. 2: OCTN Framework and sparse reconstruction . a ) OCTN converts an anisotropically sampled OCT C-scan, $V_{\mathrm{Original}}$ , into a continuous neural volumetric representation. Volume is mapped to a canonical coordinate domain $[-1,1]^{3}$ , and an INR $f_{\theta}(x,y,z)\rightarrow I$ is trained using a two-stage strategy. Stage I combines acquired discrete voxels with interpolated inter-slice in ratio ( $\alpha$ ) to encourage off-grid continuity, while Stage II performs discrete-only refinement. The learned field can be queried at arbitrary resolution, enabling dense surface extraction and continuous volume rendering. b ) Sparse reconstruction protocol shown for $SF=2$ . The subsampled training volume, $V_{\mathrm{Train}}$ , is used to train OCTN, and held-out B-scans form $V_{\mathrm{GT}}$ for evaluation. OCTN predictions, $V_{\mathrm{Pred}}$ , are compared with ground truth and with trilinear interpolation (baseline) to quantify reconstruction quality at unobserved slice locations.

Tissue	Volumes
Porcine muscle, high SNR	5
Porcine muscle, low SNR	11
Chicken breast	12
Bovine tissue	11
Porcine muscle with dye	7
Total	46

TABLE I: Duke TissueOCT sample distribution.

Fig. 3: Intensity-based volumetric query. a) Baseline and OCTN tissue volumes across intensity ranges, with better agreement under reduced speckle. b) End-to-end runtime shows $2\times$ – $3\times$ OCTN speedup. c) Query-only runtime shows larger gains at higher voxel counts.

Fig. 4: OCTN-enabled path planning. a) Porcine tissue MIP with a $\mathbf{3\,mm\times 3\,mm}$ raster pattern; waypoints are colored by surface depth. b) Tissue surface with optimized raster paths. SGD enforces smoothness and reduces jerk, unlike Baseline and Newton. Methods are compared by c) path generation time, d) surface-hit rate within $5\%$ of target $\tau$ , and e) depth smoothness energy $\Sigma(\Delta^{2}y_{i})^{2}$ ( $\mathbf{mm^{2}}$ ).

Band	Chamfer (mm) $\downarrow$	Hausdorff (mm) $\downarrow$
$[0.2,0.4)$	$0.0423$	$1.572$
$[0.4,0.6)$	$0.0264$	$1.451$
$[0.6,1.0]$	$0.0158$	$0.963$

TABLE II: Volumetric query accuracy across OCT intensity bands.

Fig. 5: Sparse volume reconstruction. a) Qualitative B-scan comparison across $SF$ for OCTN and interpolation. Red boxes and white arrows mark interpolation-induced surface artifacts visible in $8\times$ and beyond. b) Global PSNR at native resolution $\left[256,512,512\right]$ . c) Held-out B-scan performance reported as mean $\pm 1\sigma$ over each volume. d) Chamfer distance (CD) quantifies reconstruction quality and spatial-feature preservation.

Dataset	Index	Global	ROI	ROI	$\boldsymbol{\Delta}$ ROI	$\mathbf{SNR_{GT}}$ $\uparrow$	$\mathbf{SNR_{Pred}}$ $\uparrow$	EPI $\sim 1$
		PSNR $\uparrow$ / SSIM $\uparrow$		PSNR $\uparrow$ / SSIM $\uparrow$	PSNR $\uparrow$ / SSIM $\uparrow$	(dB)	(dB)
Srinivasan	24	44.64 / 0.996	R1	44.81 / 0.997	+0.17 / +0.001	9.42	9.41	0.998
			R2	43.39 / 0.992	-1.25 / -0.004	3.32	3.32	0.977
			R3	43.60 / 0.999	-1.04 / +0.003	6.62	6.62	0.992
Harvard	100	45.05 / 0.995	R1	45.24 / 0.997	+0.19 / +0.002	4.87	4.86	0.990
			R2	46.09 / 0.999	+1.04 / +0.004	8.47	8.48	1.000

TABLE III: Global and local reconstruction performance across representative datasets.

\Delta m=m_{\mathrm{ROI}}-m_{\mathrm{global}}

Fig. 6: B-scan reconstruction : OCTN performance over Srinivasan [ 35 ] , Harvard GDP [ 36 ] , Noor Eye [ 37 ] , and variants of proposed TissueOCT data. For local metric estimation, regions marked as noise are shown in red, and signal in white, with results in Table III .

Fig. 7: OCTN performance across datasets. a) Training loss and PSNR, showing two-stage training reaches $>30$ dB PSNR within seconds. PSNR is computed on 16 uniformly spaced B-scans from 10 random volumes. b) Global PSNR and SSIM distributions. c) Speckle-noise reduction improves PSNR and SSIM as seen in TissueOCT (left) and Srinivasan (right) volumes.

Fig. 8: Porcine tissue ablation demonstration. a) RATS robotic laser platform integrating OCT and a laser scalpel. b) En face MIP of porcine with target region marked in red. c) Post-ablation tissue showing localized coagulation and discoloration, with corresponding d) thermal image. e) Smoothness comparison, showing SGD achieves the lowest smoothness energy in the physical experiment.

Strategy	$\boldsymbol{\alpha}$	Volume PSNR/SSIM $\uparrow$	128.5 PSNR/SSIM $\uparrow$
Discrete only	$0.00$	$35.26{\pm}1.44$ / $\mathbf{0.87{\pm}0.03}$	$22.86{\pm}3.19$ / $0.506{\pm}0.192$
OCTN, proposed	$\mathbf{0.20}$	$\mathbf{35.35{\pm}2.87}$ / $0.83{\pm}0.06$	$27.19{\pm}3.12$ / $0.667{\pm}0.160$
Low-interp.	$0.40$	$34.93{\pm}3.30$ / $0.81{\pm}0.08$	$28.04{\pm}3.00$ / $0.698{\pm}0.144$
Moderate-interp.	$0.60$	$34.32{\pm}3.50$ / $0.79{\pm}0.09$	$28.55{\pm}2.89$ / $0.713{\pm}0.134$
High-interp.	$0.80$	$33.62{\pm}3.48$ / $0.80{\pm}0.03$	$\mathbf{28.79{\pm}2.85}$ / $\mathbf{0.723{\pm}0.128}$
Interp. only	$1.00$	$32.74{\pm}3.34$ / $0.75{\pm}0.10$	$28.20{\pm}2.63$ / $0.716{\pm}0.120$

TABLE IV: Ablation of OCTN two-stage training on TissueOCT. Metrics are reported for the full volume and fractional B-scan 128.5.

Dataset	Method	PSNR $\uparrow$	SSIM $\uparrow$
Srinivasan [ 35 ]	CuNeRF	$12.98\pm 0.96$	$0.38\pm 0.09$
	OCTN	$\mathbf{41.99\pm 5.33}$	$\mathbf{0.97\pm 0.025}$
Harvard GDP [ 36 ]	CuNeRF	$24.70\pm 0.78$	$0.48\pm 0.06$
	OCTN	$\mathbf{44.55\pm 1.23}$	$\mathbf{0.99\pm 0.01}$
Noor Eye [ 37 ]	CuNeRF	$19.62\pm 1.95$	$0.30\pm 0.038$
	OCTN	$\mathbf{45.95\pm 1.27}$	$\mathbf{0.99\pm 0.00}$

TABLE V: Comparison of OCTN and CuNeRF [ 23 ] (

n=3

\sim 171

s/2.5k steps versus

\sim 394

min/250k steps.

Explore similar work

Representation learning from OCT images
May 4, 2026Hedi Tabia, Désiré Sidibé, Nawres Khlifa +6Medical Imaging Medical Imaging Foundation Models
IBISC Univ. Evry Université Paris-Saclay · University of Tunis El Manar · ESIEE Paris - Université Gustave Eiffel +2
Label-Free Deep-Tissue Peripheral Nerve Detection with a Handheld Multimodal OCT Probe and NerveDetNet
Aug 13, 2026Yihan Wang, Ruilin You, Shaobai Li +4Medical Imaging Medical Image Segmentation
Wyant College of Optical Sciences, University of Arizona, Tucson, Arizona 85721, USA · Department of Oral & Maxillofacial Surgery, University of Pennsylvania School of Dental Medicine, Philadelphia, PA 19104, USA
6D Robotic OCT Scanning of Curved Tissue Surfaces
Mar 23, 2026Suresh Guttikonda, Maximilian Neidhardt, Vidas Raudonis +1Hand-Eye Calibration Optical Coherence Tomography
Institute of Medical Technology and Intelligent Sys., Hamburg University of Technology, Germany · Interdisciplinary Competence Center for Interface Research, Hamburg, Germany · SustAInLivWork Center of Excellence, Kaunas, Lithuania +1

May 4, 2026J/K move · Enter open · S save

Representation learning from OCT images

Hedi Tabia, Désiré Sidibé, Nawres Khlifa, Ahmed Tabia+5

IBISC Univ. Evry Université Paris-Saclay · University of Tunis El Manar · ESIEE Paris - Université Gustave Eiffel+2

Medical Imaging Medical Imaging Foundation Models Optical Coherence Tomography 3D Representation Learning Medical Image Representation Learning Self-Supervised Visual Representation Learning+1

Open paper AskPDF arXiv

Optical Coherence Tomography (OCT) has become one of the most used imaging modality in ophthalmology. It provides high-resolution, non-invasive visualization of retinal microarchitecture. The automated analysis of OCT images through representation learning has emerged as a central research frontier. This has mainly been driven by the clinical need to process large acquisition volumes. The objective is to reduce the reliance on expert annotation, and improve diagnostic consistency across devices and populations. This survey provides a comprehensive and structured review of representation learning methods for retinal OCT image analysis. It covers the period from early deep learning approaches to the most recent developments in foundation models and vision-language systems. We organize the literature along a principled taxonomy of learning paradigms, encompassing supervised learning with CNN-based and transformer-based architectures, self-supervised and semi-supervised methods, generative approaches, as well as 3D volumetric modeling, multimodal representation learning, and large-scale pretrained foundation models. For each paradigm, we analyze the core methodological contributions, identify persistent limitations, and trace the connections between successive approaches. We further provide a structured overview of publicly available OCT datasets, discuss evaluation protocol considerations, and present a unified problem formulation that situates each learning paradigm within a common mathematical framework. Building on this analysis, we identify and discuss the most pressing open research directions emerging in the literature. This includes volumetric foundation model pretraining, uncertainty-aware representation learning, federated and privacy-preserving training, fairness and bias mitigation, concept-based interpretability,...

Abstract

Explore similar work

Representation learning from OCT images

Label-Free Deep-Tissue Peripheral Nerve Detection with a Handheld Multimodal OCT Probe and NerveDetNet

6D Robotic OCT Scanning of Curved Tissue Surfaces