Pladema Institute, UNCPBA, Gral. Pinto 399, Tandil, Argentina; Consejo Nacional de Investigaciones Científicas y Técnicas, CONICET, Argentina.
Scientific Institute of Public Health (WIV-ISP), Brussels, Belgium; Federal Agency for Medicines and Health Products (FAMHP), Brussels, Belgium.
Comput Methods Programs Biomed. 2018 Jan;153:115-127. doi: 10.1016/j.cmpb.2017.10.017. Epub 2017 Oct 14.
Diabetic retinopathy (DR) is one of the leading causes of preventable blindness in the world. Its earliest sign are red lesions, a general term that groups both microaneurysms (MAs) and hemorrhages (HEs). In daily clinical practice, these lesions are manually detected by physicians using fundus photographs. However, this task is tedious and time consuming, and requires an intensive effort due to the small size of the lesions and their lack of contrast. Computer-assisted diagnosis of DR based on red lesion detection is being actively explored due to its improvement effects both in clinicians consistency and accuracy. Moreover, it provides comprehensive feedback that is easy to assess by the physicians. Several methods for detecting red lesions have been proposed in the literature, most of them based on characterizing lesion candidates using hand crafted features, and classifying them into true or false positive detections. Deep learning based approaches, by contrast, are scarce in this domain due to the high expense of annotating the lesions manually.
In this paper we propose a novel method for red lesion detection based on combining both deep learned and domain knowledge. Features learned by a convolutional neural network (CNN) are augmented by incorporating hand crafted features. Such ensemble vector of descriptors is used afterwards to identify true lesion candidates using a Random Forest classifier.
We empirically observed that combining both sources of information significantly improve results with respect to using each approach separately. Furthermore, our method reported the highest performance on a per-lesion basis on DIARETDB1 and e-ophtha, and for screening and need for referral on MESSIDOR compared to a second human expert.
Results highlight the fact that integrating manually engineered approaches with deep learned features is relevant to improve results when the networks are trained from lesion-level annotated data. An open source implementation of our system is publicly available at https://github.com/ignaciorlando/red-lesion-detection.
糖尿病视网膜病变（DR）是全球可预防致盲的主要原因之一。其最早的征象是红色病变，这是一个通用术语，包括微动脉瘤（MA）和出血（HE）。在日常临床实践中，这些病变由医生使用眼底照片手动检测。然而，由于病变的体积小且对比度低，因此这项任务既繁琐又耗时，需要大量的精力。基于红色病变检测的 DR 计算机辅助诊断由于其在提高临床医生的一致性和准确性方面的改善效果而受到积极探索。此外，它提供了易于医生评估的全面反馈。文献中已经提出了几种用于检测红色病变的方法，其中大多数方法都是基于使用手工制作的特征来描述病变候选物，并将其分类为真阳性或假阳性检测。相比之下，由于手动标注病变的费用很高，基于深度学习的方法在该领域还很少见。
在本文中，我们提出了一种基于结合深度学习和领域知识的新的红色病变检测方法。卷积神经网络（CNN）学习的特征通过合并手工制作的特征来扩充。随后，使用这种集成描述符向量使用随机森林分类器来识别真正的病变候选物。
我们通过实验观察到，与分别使用每种方法相比，结合两种信息源可显著提高结果。此外，与第二名人类专家相比，我们的方法在 DIARETDB1 和 e-ophtha 上基于病变的性能最高，在 MESSIDOR 上的筛查和转诊需求最高。
结果强调了这样一个事实，即当网络从病变级别的标注数据中进行训练时，将手动设计的方法与深度学习特征相结合对于提高结果是相关的。我们系统的开源实现可在 https://github.com/ignaciorlando/red-lesion-detection 上获得。
