...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Medical image analysis >DR vertical bar GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images
【24h】

DR vertical bar GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images

机译：垂直条毕业生：眼底图像中的不确定感知深度学习的糖尿病视网膜病变分级

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Diabetic retinopathy (DR) grading is crucial in determining the adequate treatment and follow up of patient, but the screening process can be tiresome and prone to errors. Deep learning approaches have shown promising performance as computer-aided diagnosis (CAD) systems, but their black-box behaviour hinders clinical application. We propose DR vertical bar GRADUATE, a novel deep learning-based DR grading CAD system that supports its decision by providing a medically interpretable explanation and an estimation of how uncertain that prediction is, allowing the ophthalmologist to measure how much that decision should be trusted. We designed DR vertical bar GRADUATE taking into account the ordinal nature of the DR grading problem. A novel Gaussian-sampling approach built upon a Multiple Instance Learning framework allow DR vertical bar GRADUATE to infer an image grade associated with an explanation map and a prediction uncertainty while being trained only with image-wise labels. DR vertical bar GRADUATE was trained on the Kaggle DR detection training set and evaluated across multiple datasets. In DR grading, a quadratic-weighted Cohen's kappa (kappa) between 0.71 and 0.84 was achieved in five different datasets. We show that high kappa values occur for images with low prediction uncertainty, thus indicating that this uncertainty is a valid measure of the predictions' quality. Further, bad quality images are generally associated with higher uncertainties, showing that images not suitable for diagnosis indeed lead to less trustworthy predictions. Additionally, tests on unfamiliar medical image data types suggest that DR vertical bar GRADUATE allows outlier detection. The attention maps generally highlight regions of interest for diagnosis. These results show the great potential of DR vertical bar GRADUATE as a second-opinion system in DR severity grading. (C) 2020 Elsevier B.V. All rights reserved.
机译：糖尿病视网膜病变（DR）分级对于确定足够的治疗和跟进患者来说至关重要，但筛查过程可以令人厌倦并且容易出错。深入学习方法表现出希望的表现为计算机辅助诊断（CAD）系统，但它们的黑盒行为阻碍了临床应用。我们提出垂直条毕业，这是一种新的深层学习的DR分级CAD系统，通过提供医学上解释的解释和估计预测是多么不确定，允许眼科医生测量应当信任多少决定的估计来支持其决定。考虑到DR分级问题的序数性质，我们设计了DR垂直条毕业生。建立在多实例学习框架上的新颖的高斯采样方法允许DR垂直条毕毕业以​​推断与解释图相关联的图像等级和仅使用图像明智标签培训的同时培训的预测不确定性。 DR垂直栏毕业生训练在Kaggle DR检测训练集上，并在多个数据集中进行评估。在DR分级中，在五个不同的数据集中实现了0.71和0.84之间的二次加权科恩的Kappa（Kappa）。我们表明，具有低预测不确定性的图像的高kappa值，从而表明这种不确定性是预测质量的有效衡量标准。此外，质量上的质量图像通常与更高的不确定性相关，表明不适合诊断的图像确实导致不值得信赖的预测。此外，对不熟悉的医学图像数据类型的测试表明DR垂直栏毕业过程允许异常检测。注意图通常突出显示诊断的感兴趣区域。这些结果表明DR垂直条毕业生作为DR严重程度分级的第二种意见系统的巨大潜力。 （c）2020 Elsevier B.V.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号