Toward a severity index for ROP: An unsupervised approach.
Toward a severity index for ROP: An unsupervised approach.
复制标题
制定 ROP 严重程度指数：一种无监督方法。
DOI：
10.1109/embc.2016.7590948
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Erdogmus,Deniz
中科院分区：
文献类型：
--
作者：
PengTian;Ataer-Cansizoglu,Esra;Kalpathy-Cramer,Jayashree;Ostmo,Susan;Jonas,Karyn;Chan,RVPaul;Campbell,JPeter;Chiang,MichaelF;Erdogmus,Deniz
早产儿视网膜病变（ROP）是一种影响低出生体重儿的疾病，是儿童失明的主要原因。虽然准确的诊断是重要的，有一个高变异性的专家决定，主要是由于主观阈值。现有的工作集中在ROP的自动诊断。在这项研究中，我们构建了一个连续的严重程度指数作为替代离散分类。我们遵循无监督的方法进行非线性降维。每个图像由其特征的概率分布表示，而不是提取图像特征的若干统计数据。分布之间的距离然后在流形学习方法中用作样本之间的距离。实验是在104幅广角视网膜图像的数据集上进行的。结果是有希望的，他们反映了离散分类的挑战。
Retinopathy of prematurity (ROP) is a disease affecting low birth-weight infants and is the major cause of childhood blindness. Although accurate diagnosis is important, there is a high variability among expert decisions mostly due to subjective thresholds. Existing work focused on automated diagnosis of ROP. In this study, we construct a continuous severity index as an alternative to discrete classification. We follow an unsupervised approach by performing nonlinear dimensionality reduction. Instead of extracting several statistics of image features, each image is represented by the probability distribution of its features. The distance between distributions are then used in manifold learning methods as the distance between samples. The experiments are carried out on a dataset of 104 wide-angle retinal images. The results are promising and they reflect the challenges of the discrete classification.