Development and quantitative assessment of deep learning-based image enhancement for optical coherence tomography

Abstract

Purpose 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. Methods 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. Results 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). Conclusion 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.

Digital image enhancement using Deep learning algorithm in 3D heads-up vitreoretinal surgery

“…Consequently, satisfactory PSNR and SSIM values were measured (34.59 ± 5.34 and 0.88 ± 0.08, respectively), which were similar to or slightly better than those yielded by the deep learning algorithm developed by other authors (Table 1). 3,[22][23][24] The SSIM is a measurement indicator for the human visual system that considers factors such as luminance, contrast, and structure instead of simple objective differences between images. 18,19 In other words, an SSIM value of approximately 1 implies that humans, particularly vitreoretinal surgeons, do not perceive any difference between manually adjusted and optimized surgical images.…”

Synthetic artificial intelligence using generative adversarial network for retinal imaging in detection of age-related macular degeneration

“…To establish that the synthetic images are not just copies of training images, comparison of a subset of synthetic images to training images by the structural similarity index measure (SSIM) in a pairwise manner was conducted ( 26 , 27 ). SSIM is a perceptual metric that measures the perceptual difference between two images based on luminance, contrast, and structure.…”

Deceptive Tricks in Artificial Intelligence: Adversarial Attacks in Ophthalmology

“…In many areas of artificial intelligence, machine learning algorithms based on big data (Wang et al [1] and Ching-Yu et al [2]) and deep learning have facilitated extraordinary progress, with many applications in ophthalmology (Keenan et al [3], Papadopoulos et al [4], Rampasek et al [5], Ishii et al [6], Kermany et al [7], Liu Y. et al [8], Liu T. et al [9], Burlina et al [10], Cen et al [11], Zheng et al [12], Shekar et al [13], and by Zhao et al [14]).…”