cs.LGAug 16, 2026

In Defense of OCTA: The Reconstruction-Utility Gap in OCT-to-OCTA Synthesis

Authors: Michael Chertok, Alon Tiosano, Orly Gal-Or, Lior Kramarski, Einav Baharav Shlezinger, Irit Bahar, Lior Wolf

Organizations: MarkerLeap, Raanana, Israel · Rabin Medical Center, Petah Tikva, Israel · Tel Aviv University, Tel Aviv, Israel

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Optical coherence tomography angiography (OCTA) images retinal blood flow, giving capillary-perfusion and foveal-avascular-zone biomarkers that grade diabetic-retinopathy ischemia. Because OCTA hardware is less common than structural OCT, recent work synthesizes it from OCT, reporting strong reconstruction (3D PSNR > 31 dB, SSIM > 0.9). We ask not whether the synthetic image looks similar, but whether it supports the measurements OCTA is acquired for. A frozen real-OCTA segmenter, applied as a probe to two synthesizers (XOCT, TransPro), shows downstream Dice falling with structural fineness: large vessels survive (0.862 -> 0.831) while the fine capillary network collapses (0.798 -> 0.635, five times the large-vessel loss; paired Wilcoxon p < 1e-3), TransPro worse throughout. A matched-blur control shows this detail is fabricated, not blurred. Retrained on a private Spectralis dataset, neither synthesizer reproduces the neovascular lesion (qualitative, n=3). Reconstruction fidelity is not clinical utility; we establish downstream-task fidelity as the evaluation OCT-to-OCTA synthesis needs.

Figures & tables

 3D PSNR3D SSIMproj-full PSNRproj-full SSIM
XOCT (reported)31.260.90521.460.568
XOCT (ours)31.170.90321.530.567
TransPro (ours)29.540.88020.780.532
Table 1: We reproduce XOCT’s published OCTA-500 6 mm reconstruction (70-eye test split) to within 0.10.1 dB PSNR and 0.0030.003 SSIM, and train a second synthesizer, TransPro, to XOCT-comparable reconstruction (within ∼\sim 11 – 1.61.6 dB PSNR). Both run faithfully before we probe them, so a downstream gap reflects fidelity, not undertraining. proj = en-face projection.
Figure 1: Two synthesizers erode the diagnostic microvasculature at high pixel fidelity (OCTA-500 held-out eye, diabetic retinopathy). Rows: XOCT and TransPro. Columns: real full-retina en-face, synthetic full-retina, real deep OPL–BM slab (outer plexiform layer to Bruch’s membrane), synthetic deep OPL–BM. Both reproduce the large arcade vessels, which drives high PSNR/SSIM, but the synthetic full-retina enlarges and over-regularizes the foveal avascular zone (FAZ, the capillary-free foveal center read for ischemia; cyan marker) into a round dark void and degrades the fine perifoveal capillaries. In the deep OPL–BM slab, both real and synthetic are dominated by projection tails (decorrelation shadows cast by superficial vessels [ 16 ] ); the synthesizer reproduces this projected skeleton but not distinct deep-layer detail. The metrics reward the large vessels the models get right and are blind to the capillaries and FAZ they erase.
Segmentation targetReal (matched)XOCT synth (drop)TransPro synth (drop)
Large vessel0.8620.831 (0.031)0.761 (0.101)
Foveal avascular zone0.7640.678 (0.086)0.609 (0.155)
Capillary0.7980.635 ( 0.163 )0.591 ( 0.206 )
Table 2: Downstream segmentation Dice on synthetic vs matched-recipe real OCTA (50 held-out eyes; Dice drop in parentheses). Both synthesizers collapse monotonically with structural fineness at matched reconstruction PSNR: XOCT preserves large vessels (drop 0.0310.031 ) while destroying capillaries ( 5×5\times ), whereas TransPro degrades even large vessels (drop 0.1010.101 ) and is more uniformly bad. Higher is better; the matched-real large-vessel score ( 0.8620.862 ) is close to the device’s provided projections ( 0.8730.873 ). All gaps are significant (paired Wilcoxon signed-rank, p<10−3p<10^{-3} ); the XOCT capillary-gap 95%95\% CI is [0.156,0.170][0.156,0.170] .
 Sharpness ( σ\sigma , px)Capillary Dicevs. real
Real OCTA0 (native)0.798–
XOCT synthetic0.4 (= real)0.635−20%-20\%
TransPro synthetic0.4 (= real)0.591−26%-26\%
Real blurred to XOCT’s Dice1.00.635( 2.5×2.5\times more blur)
Real blurred to TransPro’s Dice1.20.591( 3.0×3.0\times more blur)
Table 3: Matched-blur control (capillary target). Both synthesizers are as sharp as real OCTA: their radial power spectrum matches real OCTA blurred by only σ=0.4\sigma=0.4 px. Yet at that matched resolution the synthetic loses 20–26% of the capillary Dice, a gap resolution cannot explain; real OCTA must be blurred to σ≈1.0\sigma\approx 1.0 – 1.21.2 px ( 2.52.5 – 3×3\times the synthetic’s own blur) before it segments as badly. The collapse is structural fabrication, not lost resolution.
Figure 2: Neither synthesizer reproduces the neovascular lesion ( SpectralisMNV ). Columns: real OCTA, XOCT retrained on SpectralisMNV, TransPro retrained on the same data. Top row: full-retina en-face; bottom row: the outer-retinal avascular-complex slab (OPL–BM), normally vessel-free and thus the slab read for macular neovascularization (MNV). On the full retina both reproduce the arcade vessels but leave a dark macular void; in the avascular complex the real carries a discrete branching neovascular network (sea-fan / medusa morphology) that both synthesizers miss, rendering only the projected superficial vessels. One representative eye of n=3n{=}3 graded; illustrative, not a detection metric.

Explore similar work

CardsList

  1. Three-Dimensional Retinal Microvasculature Restoration in OCT Angiography

    Jun 3, 2026Yukun Guo, Min Gao, Tristan T. Hormel +3Medical Imaging3D Medical Imaging

    Casey Eye Institute, Oregon Health & Science University, Portland, OR 97239, USA · Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA

  2. Propagating Structural Guidance: Synthesizing Fluorescein Angiography from Fundus Images and Sparse OCT Scans

    Jun 15, 2026Tengfei Ma, Ruiqi Wu, Chenran Zhang +6Medical ImagingCross-Modal Alignment

    School of Computer Science and Engineering, Southeast University, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Nanjing, China · Tianyuan Honors School, Nanjing Medical University, China +2

  3. Cross-Modal Fusion of OCT and OCT angiography enface for Improved Diagnostics of Diabetic Retinopathy

    Jul 4, 2026Rashadul Hasan Badhon, Atalie Carina Thompson, Jennifer I. Lim +2Diabetic Retinopathy GradingOptical Coherence Tomography