Generative modeling for label-free glomerular modeling and classification
Generative modeling for label-free glomerular modeling and classification
复制标题
无标记肾小球建模和分类的生成模型
DOI：
10.1117/12.2548757
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
P. Sarder
中科院分区：
文献类型：
--
作者：
Brendon Lutnick;Brandon G. Ginley;Kuang;Wen Dong;P. Sarder
使用GAN的生成式建模在机器学习文献中获得了吸引力，因为训练不需要标记的数据集。这非常适合生物数据集的应用，在生物数据集中，大型标记数据集通常很难获得，而且成本很高。然而，生成模型没有提供简单的方法来将真实的图像编码成特征集，这是网络可解释性所期望的，并且可能产生潜在的信息图像特征。出于这个原因，我们测试了VAE-GAN架构，用于肾小球结构特征的无标记建模。我们表明，该网络可以生成逼真的合成图像，并用于图像之间的插值。为了证明网络编码的生物相关性，我们通过活检Tervaert类和硬化的存在对编码肾小球的小标记集进行分类，分别获得0.87和0.78的Cohen kappa值。
Generative modeling using GANs has gained traction in machine learning literature, as training does not require labeled datasets. This is perfect for applications in biological datasets, where large labeled datasets are often difficult and expensive to acquire. However, generative models offer no easy way to encode real images into feature-sets, something that is desirable for network explainability and may yield potentially informative image features. For this reason, we test a VAE-GAN architecture for label-free modeling of glomerular structural features. We show that this network can generate realistic looking synthetic images, and be used to interpolate between images. To prove the biological relevance of the network encodings, we classify small-labeled sets of encoded glomeruli by biopsy Tervaert class and for the presence of sclerosis, obtaining a Cohen's kappa values of 0.87 and 0.78 respectfully.
影响因子：
13.6
作者：
Li, Xuezhu;Chuang, Peter Y.;He, John Cijiang
通讯作者：
He, John Cijiang
影响因子：
13.6
作者：
Ginley, Brandon;Lutnick, Brendon;Sarder, Pinaki
通讯作者：
Sarder, Pinaki