Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, 100730, China.
Key Lab of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, 100730, China.
BMC Ophthalmol. 2022 Mar 26;22(1):139. doi: 10.1186/s12886-022-02299-w.
To develop a deep learning-based framework to improve the image quality of optical coherence tomography (OCT) and evaluate its image enhancement effect with the traditional image averaging method from a clinical perspective.
359 normal eyes and 456 eyes with various retinal conditions were included. A deep learning framework with high-resolution representation was developed to achieve image quality enhancement for OCT images. The quantitative comparisons, including expert subjective scores from ophthalmologists and three objective metrics of image quality (structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR) and contrast-to-noise ratio (CNR)), were performed between deep learning method and traditional image averaging.
With the increase of frame count from 1 to 20, our deep learning method always obtained higher SSIM and PSNR values than the image averaging method while importing the same number of frames. When we selected 5 frames as inputs, the local objective assessment with CNR illustrated that the deep learning method had more obvious tissue contrast enhancement than averaging method. The subjective scores of image quality were all highest in our deep learning method, both for normal retinal structure and various retinal lesions. All the objective and subjective indicators had significant statistical differences (P < 0.05).
Compared to traditional image averaging methods, our proposed deep learning enhancement framework can achieve a reasonable trade-off between image quality and scanning times, reducing the number of repeated scans.
开发一种基于深度学习的框架，以改善光学相干断层扫描（OCT）的图像质量，并从临床角度评估其与传统图像平均法的图像增强效果。
纳入 359 只正常眼和 456 只各种视网膜病变眼。开发了具有高分辨率表示的深度学习框架，以实现 OCT 图像的质量增强。对来自眼科专家的定量比较，包括主观评分和三种客观图像质量指标（结构相似性指数测量（SSIM）、峰值信噪比（PSNR）和对比噪声比（CNR））进行了比较，比较了深度学习方法和传统图像平均法。
随着帧数从 1 增加到 20，我们的深度学习方法始终比图像平均法获得更高的 SSIM 和 PSNR 值，同时输入相同数量的帧数。当我们选择 5 帧作为输入时，局部客观评估用 CNR 表明，深度学习方法比平均法具有更明显的组织对比度增强。图像质量的主观评分在我们的深度学习方法中均最高，无论是正常视网膜结构还是各种视网膜病变。所有的客观和主观指标均有显著的统计学差异（P<0.05）。
与传统的图像平均方法相比，我们提出的深度学习增强框架可以在图像质量和扫描次数之间实现合理的权衡，减少重复扫描的次数。
