Kim Ye Eun, Lee Eun Ji, Yoon Jung Suk, Kwak Jiyoon, Kim Hyunjoong
Department of Statistics and Data Science, Yonsei University, Seoul 03722, Republic of Korea.
Department of Ophthalmology, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea.
Diagnostics (Basel). 2025 Jan 24;15(3):277. doi: 10.3390/diagnostics15030277.
Variations in image clarity across different OCT devices, along with the inconsistent delineation of RNFL boundaries, pose a challenge to achieving consistent diagnoses for glaucoma. Recently, deep learning methods such as GANs for image transformation have been gaining attention. This paper introduces deep learning methods to transform low-clarity images from one OCT device into high-clarity images from another, concurrently estimating the retinal nerve fiber layer (RNFL) segmentation lines in the enhanced images. We applied two deep learning methods, pix2pix and cycle-GAN, and provided a comparison of their performance by evaluating the similarity between the generated and actual images, as well as comparing the generated RNFL boundary delineation with the actual boundaries. The image conversion performance was compared based on two criteria: Fréchet Inception Distance (FID) and curve dissimilarity. In the comparison of FID values, the cycle-GAN method showed significantly lower values than the pix2pix method (-value < 0.001). In terms of curve similarity, the cycle-GAN method also demonstrated higher similarity to the actual curves compared to both manually annotated curves and the pix2pix method (-value < 0.001). We demonstrated that the cycle-GAN method produces more consistent and precise outcomes in the converted images compared to the pix2pix method. The resulting segmented lines showed a high degree of similarity to those manually annotated by clinical experts in high-clarity images, surpassing the boundary accuracy observed in the original low-clarity scans.
不同光学相干断层扫描（OCT）设备的图像清晰度存在差异，再加上视网膜神经纤维层（RNFL）边界的划分不一致，这对青光眼的一致性诊断构成了挑战。最近，诸如用于图像转换的生成对抗网络（GAN）等深度学习方法受到了关注。本文介绍了深度学习方法，将来自一种OCT设备的低清晰度图像转换为来自另一种设备的高清晰度图像，同时估计增强图像中的视网膜神经纤维层（RNFL）分割线。我们应用了两种深度学习方法，pix2pix和循环GAN，并通过评估生成图像与实际图像之间的相似度，以及将生成的RNFL边界划分与实际边界进行比较，对它们的性能进行了比较。基于两个标准比较了图像转换性能：弗雷歇因距离（FID）和曲线差异。在FID值的比较中，循环GAN方法显示出的值明显低于pix2pix方法（p值<0.001）。在曲线相似度方面，与手动标注曲线和pix2pix方法相比，循环GAN方法也显示出与实际曲线更高的相似度（p值<0.001）。我们证明，与pix2pix方法相比，循环GAN方法在转换后的图像中产生的结果更一致、更精确。生成的分割线与高清晰度图像中临床专家手动标注的分割线高度相似，超过了原始低清晰度扫描中观察到的边界精度。
