■提供一种用于从彩色眼底照片合成荧光素血管造影(FA)图像的自动化系统,以避免与荧光素染料相关的风险,并将其未来应用扩展到资源有限的航天中的航天相关神经眼综合征(SANS)检测。
■开发和验证一种新的条件生成对抗网络(GAN),该网络对糖尿病视网膜病变和对照病例的FA和彩色眼底图像进行了有限量的训练。
■独特患者的彩色眼底和FA配对图像是从公开可用的研究中收集的。
■对FA4SANS-GAN进行了训练,以使用2个多尺度发生器和2个贴片-GAN鉴别器从彩色眼底照片生成FA图像。通过增强来自17名独特患者的图像,将八百五十张彩色眼底和FA图像用于训练。在从14名独特患者收集的56张荧光素图像上评估该模型。此外,它与在同一数据集上训练的其他3个GAN体系结构进行了比较。此外,当引入人工创建的生物标记时,我们测试了模型对采集噪声和保留结构信息的鲁棒性。
■对于GAN合成,度量Fréchet初始距离(FID)和内核初始距离(KID)。此外,基于Welcht检验的两个单侧检验(TOST),用于测量统计显著性。
■在测试FA图像上,FA4SANS-GAN的平均FID为39.8(标准偏差,9.9),这优于Gangio模型的平均值43.2(标准偏差,13.7),Pix2PixHD的平均值为57.3(标准偏差,11.5)和Pix2Pix的平均值为67.5(标准偏差,11.7).同样,对于孩子来说,FA4SANS-GAN实现的平均值为0.00278(标准偏差,0.00167),优于其他3款车型的平均KID为0.00303(标准偏差,0.00216),0.00609(标准偏差,0.00238),0.00784(标准偏差,0.00218)。对于TOST测量,与GANgio(P=0.006);与Pix2PixHD(P<0.00001);与Pix2Pix(P<0.00001)相比,FA4SANS-GAN被证明具有统计学意义。
■我们的研究表明,FA4SANS-GAN对于2个GAN合成指标具有统计学意义。此外,它对采集噪声具有鲁棒性,与其他3个GAN体系结构相比,可以保留清晰的生物标记。该模型的部署在国际空间站中对于检测SANS至关重要。
■作者对本文讨论的任何材料都没有专有或商业利益。
UNASSIGNED: To provide an automated system for synthesizing fluorescein angiography (FA) images from color fundus photographs for averting risks associated with fluorescein dye and extend its future application to spaceflight associated neuro-ocular syndrome (SANS) detection in spaceflight where resources are limited.
UNASSIGNED: Development and validation of a novel conditional generative adversarial network (GAN) trained on limited amount of FA and color fundus images with diabetic retinopathy and control cases.
UNASSIGNED: Color fundus and FA paired images for unique patients were collected from a publicly available study.
UNASSIGNED: FA4SANS-GAN was trained to generate FA images from color fundus photographs using 2 multiscale generators coupled with 2 patch-GAN discriminators. Eight hundred fifty color fundus and FA images were utilized for training by augmenting images from 17 unique patients. The model was evaluated on 56 fluorescein images collected from 14 unique patients. In addition, it was compared with 3 other GAN architectures trained on the same data set. Furthermore, we test the robustness of the models against acquisition noise and retaining structural information when introduced to artificially created biological markers.
UNASSIGNED: For GAN synthesis, metric Fréchet Inception Distance (FID) and Kernel Inception Distance (KID). Also, two 1-sided tests (TOST) based on Welch\'s t test for measuring statistical significance.
UNASSIGNED: On test FA images, mean FID for FA4SANS-GAN was 39.8 (standard deviation, 9.9), which is better than GANgio model\'s mean of 43.2 (standard deviation, 13.7), Pix2PixHD\'s mean of 57.3 (standard deviation, 11.5) and Pix2Pix\'s mean of 67.5 (standard deviation, 11.7). Similarly for KID, FA4SANS-GAN achieved mean of 0.00278 (standard deviation, 0.00167) which is better than other 3 model\'s mean KID of 0.00303 (standard deviation, 0.00216), 0.00609 (standard deviation, 0.00238), 0.00784 (standard deviation, 0.00218). For TOST measurement, FA4SANS-GAN was proven to be statistically significant versus GANgio (P = 0.006); versus Pix2PixHD (P < 0.00001); and versus Pix2Pix (P < 0.00001).
UNASSIGNED: Our study has shown FA4SANS-GAN to be statistically significant for 2 GAN synthesis metrics. Moreover, it is robust against acquisition noise, and can retain clear biological markers compared with the other 3 GAN architectures. This deployment of this model can be crucial in the International Space Station for detecting SANS.
UNASSIGNED: The authors have no proprietary or commercial interest in any materials discussed in this article.