深度生成模型合成高分辨率年龄相关性黄斑变性视网膜图像的评价
两名视网膜专科医生在真实与合成图像上的AMD诊断准确率相近,且无法区分真实与合成图像;在合成数据上训练的深度卷积神经网络(DCNN)诊断性能接近真实数据训练者。
要点
- 视网膜专科医生在真实与合成眼底图像上的AMD诊断准确率相似。
- 专科医生难以区分真实与合成图像,准确率接近随机水平。
- 合成数据训练的DCNN诊断性能接近真实数据训练,提示可用于训练人与机器。
核心结论
- 深度学习合成的眼底图像对 retinal specialists 而言具有真实感,且基于合成数据训练的DCNN诊断性能接近真实图像,生成式技术有望用于培训医生和机器。
主要发现
- 视网膜专科医生1诊断可转诊与不可转诊AMD的准确率在真实图像为84.54%(误差范围4.06%),合成图像为84.12%(误差范围4.16%);专科医生2分别为89.47%(误差范围3.45%)与89.19%(误差范围3.54%)。
- 专科医生区分真实与合成图像的准确率分别为59.50%(误差范围3.93%)和53.67%(误差范围3.99%)。
- 真实数据训练的DCNN曲线下面积为0.9706(误差范围0.0029),合成数据训练的DCNN为0.9235(误差范围0.0045)。
关键数值与推荐
- 视网膜专科医生1真实图像诊断准确率84.54%(误差范围4.06%) vs 合成图像84.12%(误差范围4.16%)。
- 视网膜专科医生2真实图像诊断准确率89.47%(误差范围3.45%) vs 合成图像89.19%(误差范围3.54%)。
- 区分真实与合成图像准确率:专科医生1为59.50%(误差范围3.93%),专科医生2为53.67%(误差范围3.99%)。
- DCNN曲线下面积:真实数据0.9706(误差范围0.0029),合成数据0.9235(误差范围0.0045)。
临床怎么用
- 合成眼底图像可用于医学教育中学生、住院医师和视网膜专科医生的培训,并可作为补充数据训练深度学习诊断模型,尤其适用于稀有眼病或缺乏大规模专家分级图像的数据集。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
IMPORTANCE: Deep learning (DL) used for discriminative tasks in ophthalmology, such as diagnosing diabetic retinopathy or age-related macular degeneration (AMD), requires large image data sets graded by human experts to train deep convolutional neural networks (DCNNs). In contrast, generative DL techniques could synthesize large new data sets of artificial retina images with different stages of AMD. Such images could enhance existing data sets of common and rare ophthalmic diseases without concern for personally identifying information to assist medical education of students, residents, and retinal specialists, as well as for training new DL diagnostic models for which extensive data sets from large clinical trials of expertly graded images may not exist. OBJECTIVE: To develop DL techniques for synthesizing high-resolution realistic fundus images serving as proxy data sets for use by retinal specialists and DL machines. DESIGN, SETTING, AND PARTICIPANTS: Generative adversarial networks were trained on 133 821 color fundus images from 4613 study participants from the Age-Related Eye Disease Study (AREDS), generating synthetic fundus images with and without AMD. We compared retinal specialists' ability to diagnose AMD on both real and synthetic images, asking them to assess image gradability and testing their ability to discern real from synthetic images. The performance of AMD diagnostic DCNNs (referable vs not referable AMD) trained on either all-real vs all-synthetic data sets was compared. MAIN OUTCOMES AND MEASURES: Accuracy of 2 retinal specialists (T.Y.A.L. and K.D.P.) for diagnosing and distinguishing AMD on real vs synthetic images and diagnostic performance (area under the curve) of DL algorithms trained on synthetic vs real images. RESULTS: The diagnostic accuracy of 2 retinal specialists on real vs synthetic images was similar. The accuracy of diagnosis as referable vs nonreferable AMD compared with certified human graders for retinal specialist 1 was 84.54% (error margin, 4.06%) on real images vs 84.12% (error margin, 4.16%) on synthetic images and for retinal specialist 2 was 89.47% (error margin, 3.45%) on real images vs 89.19% (error margin, 3.54%) on synthetic images. Retinal specialists could not distinguish real from synthetic images, with an accuracy of 59.50% (error margin, 3.93%) for retinal specialist 1 and 53.67% (error margin, 3.99%) for retinal specialist 2. The DCNNs trained on real data showed an area under the curve of 0.9706 (error margin, 0.0029), and those trained on synthetic data showed an area under the curve of 0.9235 (error margin, 0.0045). CONCLUSIONS AND RELEVANCE: Deep learning-synthesized images appeared to be realistic to retinal specialists, and DCNNs achieved diagnostic performance on synthetic data close to that for real images, suggesting that DL generative techniques hold promise for training humans and machines.
引用
- Burlina PM, Joshi N, Pacheco KD, et al. Assessment of Deep Generative Models for High-Resolution Synthetic Retinal Image Generation of Age-Related Macular Degeneration. JAMA Ophthalmol. 2019. PMID: 30629091. doi:10.1001/jamaophthalmol.2018.6156
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。