UASSIGNED:由于数据集的自然类别不平衡,在基于医学图像的人工智能中,罕见疾病诊断具有挑战性。导致预测模型有偏差。遗传性视网膜疾病(IRD)是一个特别面临这一问题的研究领域。这项研究调查了合成数据在使用生成对抗网络(GAN)改善人工智能对IRD的诊断中的适用性。
UNASSIGNED:使用深度学习对基因标记的眼底自发荧光(FAF)IRD图像进行诊断研究。
UNASSIGNED:Moorfields眼科医院(MEH)的15.692张FAF图像数据集来自1800名患者,这些患者的基因诊断为36个IRD基因中的1个。
UNASSIGNED:在IRD数据集上训练StyleGAN2模型以生成512×512分辨率图像。使用不同的合成增强数据集训练卷积神经网络进行分类,包括真实的IRD图像以及1800和3600合成图像,和一个完全重新平衡的数据集。我们还只使用合成数据进行实验。将所有模型与仅在真实数据上训练的基线卷积神经网络进行比较。
UNASSIGNED:我们使用视觉图灵测试对来自MEH的4位眼科医生进行了综合数据质量评估。使用特征空间可视化比较了合成图像和真实图像,相似性分析来检测记忆图像,和盲/无参考图像空间质量评估(BRISQUE)得分,用于无参考的质量评估。使用受试者工作特征曲线下面积(AUROC)和Cohen'sKappa(κ)在保留的测试集上确定卷积神经网络诊断性能。
UNASSIGNED:从视觉图灵测试获得63%的平均真实识别率和47%的假识别率。因此,相当比例的合成图像被临床专家归类为真实的。相似性分析表明,合成图像不是真实图像的副本,表明复制的真实图像,这意味着GAN能够概括。然而,BRISQUE评分分析表明,合成图像的整体质量明显低于真实图像(P<0.05)。将重新平衡模型(RB)与基线(R)进行比较,平均AUROC和κ没有发现显著变化(R-AUROC=0.86[0.85-88],RB-AUROC=0.88[0.86-0.89],R-k=0.51[0.49-0.53],和RB-k=0.52[0.50-0.54])。合成数据训练模型(S)实现了与基线相似的性能(S-AUROC=0.86[0.85-87],S-k=0.48[0.46-0.50])。
UNASSIGNED:合成生成逼真的IRDFAF图像是可行的。合成数据增强不会改善分类性能。然而,仅合成数据就能提供与真实数据相似的性能,因此,作为真实数据的代理可能很有用。财务披露:专有或商业披露可以在参考文献之后找到。
UNASSIGNED: Rare disease diagnosis is challenging in medical image-based artificial intelligence due to a natural class imbalance in datasets, leading to biased prediction models. Inherited retinal diseases (IRDs) are a research domain that particularly faces this issue. This study investigates the applicability of synthetic data in improving artificial intelligence-enabled diagnosis of IRDs using generative adversarial networks (GANs).
UNASSIGNED: Diagnostic study of gene-labeled fundus autofluorescence (FAF) IRD images using deep learning.
UNASSIGNED: Moorfields Eye Hospital (MEH) dataset of 15 692 FAF images obtained from 1800 patients with confirmed genetic diagnosis of 1 of 36 IRD genes.
UNASSIGNED: A StyleGAN2 model is trained on the IRD dataset to generate 512 × 512 resolution images. Convolutional neural networks are trained for classification using different synthetically augmented datasets, including real IRD images plus 1800 and 3600 synthetic images, and a fully rebalanced dataset. We also perform an experiment with only synthetic data. All models are compared against a baseline convolutional neural network trained only on real data.
UNASSIGNED: We evaluated synthetic data quality using a Visual Turing Test conducted with 4 ophthalmologists from MEH. Synthetic and real images were compared using feature space visualization, similarity analysis to detect memorized images, and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score for no-reference-based quality evaluation. Convolutional neural network diagnostic performance was determined on a held-out test set using the area under the receiver operating characteristic curve (AUROC) and Cohen\'s Kappa (κ).
UNASSIGNED: An average true recognition rate of 63% and fake recognition rate of 47% was obtained from the Visual Turing Test. Thus, a considerable proportion of the synthetic images were classified as real by clinical experts. Similarity analysis showed that the synthetic images were not copies of the real images, indicating that copied real images, meaning the GAN was able to generalize. However, BRISQUE score analysis indicated that synthetic images were of significantly lower quality overall than real images (P < 0.05). Comparing the rebalanced model (RB) with the baseline (R), no significant change in the average AUROC and κ was found (R-AUROC = 0.86[0.85-88], RB-AUROC = 0.88[0.86-0.89], R-k = 0.51[0.49-0.53], and RB-k = 0.52[0.50-0.54]). The synthetic data trained model (S) achieved similar performance as the baseline (S-AUROC = 0.86[0.85-87], S-k = 0.48[0.46-0.50]).
UNASSIGNED: Synthetic generation of realistic IRD FAF images is feasible. Synthetic data augmentation does not deliver improvements in classification performance. However, synthetic data alone deliver a similar performance as real data, and hence may be useful as a proxy to real data. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references.