Dev Chander, M S Sharang, Reddy Manne Shanmukh, Goud Abhilash, Bashar Sarforaz Bin, Richhariya Ashutosh, Chhablani Jay, Vupparaboina Kiran Kumar, Jana Soumya
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:2091-2094. doi: 10.1109/EMBC.2019.8857046.
Various ophthalmic procedures critically depend on high-quality images. For instance, efficiency of teleophthalmology, a framework to bring advanced eye care to remote regions, is determined by the capability of assessing diagnostic quality of ocular fundus photographs (FPs), and rejecting poor-quality ones at the source. In this context, we study algorithmic methods of classifying high- and low-quality FPs. Crucially, diagnostic quality (DQ) - determined by clinically, but not necessarily perceptually, significant structures - is not synonymous with perceptual appeal. Yet, traditional methods handpick features individually (or in small subsets) to meet certain ad hoc perceptual requirements. In contrast, we investigate the efficacy of a comprehensive set of structure-preserving features, systematically generated by a deep scattering network (ScatNet). Specifically, we consider three advanced machine learning classifiers, train each using ScatNet as well as traditional features separately, and demonstrate that the former ensure significantly superior performance for each classifier under multiple criteria including classification accuracy.
各种眼科手术严重依赖高质量的图像。例如，远程眼科作为一种为偏远地区提供先进眼保健的框架，其效率取决于评估眼底照片（FPs）诊断质量的能力，并在源头拒收质量差的照片。在此背景下，我们研究对高质量和低质量FPs进行分类的算法方法。至关重要的是，由临床但不一定是感知上显著的结构所决定的诊断质量（DQ）并不等同于感知吸引力。然而，传统方法是单独（或以小子集的形式）挑选特征以满足某些特定的感知要求。相比之下，我们研究了由深度散射网络（ScatNet）系统生成的一整套结构保留特征的功效。具体而言，我们考虑三种先进的机器学习分类器，分别使用ScatNet以及传统特征对每个分类器进行训练，并证明在包括分类准确率在内的多个标准下，前者能确保每个分类器具有显著更优的性能。
