Three-Dimensional Retinal Microvasculature Restoration in OCT Angiography
Quick Answer
This paper shows that A deep learning algorithm utilizing EfficientNet-B5 enhances OCTA imaging by restoring 3D retinal microvasculature, achieving a PSNR of 26.16 and SSIM of 0.91, significantly improving image quality and microvascular fidelity.
Quick Take
A deep learning algorithm utilizing EfficientNet-B5 enhances OCTA imaging by restoring 3D retinal microvasculature, achieving a PSNR of 26.16 and SSIM of 0.91, significantly improving image quality and microvascular fidelity.
Key Points
- Proposed model uses EfficientNet-B5 for 3D retinal microvasculature restoration.
- Achieved PSNR of 26.16 and SSIM of 0.91, outperforming original OCTA volumes.
- Improved microvascular fidelity by at least 3.8% in 2D and 51.2% in 3D.
- Utilizes three adjacent B-frames to predict a restored middle B-frame.
- Significant performance improvements validated with p < 0.001.
Article Content
From source RSS / original summaryarXiv:2606. 05375v1 Announce Type: new Abstract: Optical coherence tomographic angiography (OCTA) is a powerful technique for imaging retinal microvasculature. However, acquiring reliable quantification of retinal blood flow and areas of retinal nonperfusion is challenging because of imaging artifacts.
Existing methods primarily focus on noise suppression, projection artifact removal, or signal enhancement to improve the image quality of OCTA in cross-sectional or two-dimensional (2D) en face projections, while neglecting the intrinsic three-dimensional vascular architecture. In this study, we propose a deep learning-based algorithm for restoring capillary anatomical vasculature from a single OCTA volume.
The network consists of an EfficientNet-B5 encoder and a decoder incorporating concurrent spatial and channel squeeze-and-excitation modules, connected via skip connections to preserve spatial resolution. Three adjacent B-frames are used as input to predict the restored middle B-frame. We evaluated the performance of the model using the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) against ground truth generated from averaging multiple scans.
The results show that the proposed model significantly (both p < 0. 001) improved image quality compared with the original single OCTA volume, with a PSNR of 26. 16 +/- 1. 26 vs. 22. 23 +/- 0. 78 and an SSIM of 0. 91 +/- 0. 02 vs. 0. 72 +/- 0. 03. The proposed model also significantly (p < 0. 001) improved microvascular fidelity, measured by the Dice coefficient overlap between the model output and ground truth, in both 2D and 3D by at least 3. 8% and 51. 2%, respectively, across several different vascular slabs.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.