用深度学习从单次OCTA扫描恢复视网膜微血管三维结构
Three-Dimensional Retinal Microvasculature Restoration in OCT Angiography
- 基于EfficientNet-B5与双注意力模块的网络，通过三帧预测中间帧实现三维血管修复
- PSNR提升至26.16（原22.23），SSIM达0.91（原0.72），血管重合度提升51.2%
- 特别适合眼科医生分析视网膜缺血区域，提升影像诊断精度
光学相干断层扫描血管成像（OCTA）是成像视网膜微血管的重要技术，但受成像伪影影响，难以可靠量化血流和无灌注区。现有方法多聚焦于噪声抑制、投影伪影去除或信号增强，仅改善横断面或二维层面的图像质量，忽视了血管的内在三维结构。本研究提出一种基于深度学习的算法，从单个OCTA体数据中恢复毛细血管解剖结构。网络采用EfficientNet-B5编码器与包含并行空间-通道挤压激励模块的解码器，通过跳跃连接保持空间分辨率。以三个相邻B帧作为输入，预测中间帧。使用多次扫描平均生成的真值进行评估，结果表明，相比原始单次OCTA体积，该模型显著（均p < 0.001）提升图像质量，PSNR为26.16 ± 1.26（原22.23 ± 0.78），SSIM为0.91 ± 0.02（原0.72 ± 0.03）。模型还显著（p < 0.001）提升了微血管保真度，2D与3D层面的Dice系数分别提高至少3.8%与51.2%，覆盖多个不同血管板层。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。