期刊
NEUROCOMPUTING
卷 396, 期 -, 页码 465-476出版社
ELSEVIER
DOI: 10.1016/j.neucom.2018.07.102
关键词
Deep learning; Classification; Explanations; Diabetic retinopathy; Model interpretation
资金
- URV [2017PFR-URV-B2-60]
- Spanish research projects (Instituto de Salud Carlos III) [PI15/01150, PI12/01535]
- Fondos Feder from EU
In this paper we present a diabetic retinopathy deep learning interpretable classifier. On one hand, it classifies retina images into different levels of severity with good performance. On the other hand, this classifier is able of explaining the classification results by assigning a score for each point in the hidden and input spaces. These scores indicate the pixel contribution to the final classification. To obtain these scores, we propose a new pixel-wise score propagation model that for every neuron, divides the observed output score into two components. With this method, the generated visual maps can be easily interpreted by an ophthalmologist in order to find the underlying statistical regularities that help to the diagnosis of this eye disease. (C) 2019 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据