Molina-Casado José M, Carmona Enrique J, García-Feijoó Julián
Department of Artificial Intelligence, ETS Ingeniería Informática, Universidad Nacional de Educación a Distancia (UNED), C/ Juan del Rosal 16, Madrid 28040, Spain.
Department of Ophthalmology, Faculty of Medicine, Complutense University, Madrid, Spain; Ocular Pathology National Net OFTARED of the Institute of Health Carlos III, Spain; Department of Ophthalmology, Sanitary Research Institute of the San Carlos Clinical Hospital, Madrid, Spain.
Comput Methods Programs Biomed. 2017 Oct;149:55-68. doi: 10.1016/j.cmpb.2017.06.022. Epub 2017 Jul 22.
The anatomical structure detection in retinal images is an open problem. However, most of the works in the related literature are oriented to the detection of each structure individually or assume the previous detection of a structure which is used as a reference. The objective of this paper is to obtain simultaneous detection of the main retinal structures (optic disc, macula, network of vessels and vascular bundle) in a fast and robust way.
We propose a new methodology oriented to accomplish the mentioned objective. It consists of two stages. In an initial stage, a set of operators is applied to the retinal image. Each operator uses intra-structure relational knowledge in order to produce a set of candidate blobs that belongs to the desired structure. In a second stage, a set of tuples is created, each of which contains a different combination of the candidate blobs. Next, filtering operators, using inter-structure relational knowledge, are used in order to find the winner tuple. A method using template matching and mathematical morphology is implemented following the proposed methodology.
A success is achieved if the distance between the automatically detected blob center and the actual structure center is less than or equal to one optic disc radius. The success rates obtained in the different public databases analyzed were: MESSIDOR (99.33%, 98.58%, 97.92%), DIARETDB1 (96.63%, 100%, 97.75%), DRIONS (100%, n/a, 100%) and ONHSD (100%, 98.85%, 97.70%) for optic disc (OD), macula (M) and vascular bundle (VB), respectively. Finally, the overall success rate obtained in this study for each structure was: 99.26% (OD), 98.69% (M) and 98.95% (VB). The average time of processing per image was 4.16 ± 0.72 s.
The main advantage of the use of inter-structure relational knowledge was the reduction of the number of false positives in the detection process. The implemented method is able to simultaneously detect four structures. It is fast, robust and its detection results are competitive in relation to other methods of the recent literature.
视网膜图像中的解剖结构检测是一个开放性问题。然而，相关文献中的大多数工作都是针对每个结构单独进行检测，或者假设之前已经检测到一个结构并将其用作参考。本文的目的是以快速且稳健的方式同时检测主要的视网膜结构（视盘、黄斑、血管网络和血管束）。
我们提出了一种旨在实现上述目标的新方法。它由两个阶段组成。在初始阶段，将一组算子应用于视网膜图像。每个算子利用结构内关系知识来生成一组属于所需结构的候选斑点。在第二阶段，创建一组元组，每个元组包含候选斑点的不同组合。接下来，使用利用结构间关系知识的过滤算子来找到获胜元组。按照所提出的方法实现了一种使用模板匹配和数学形态学的方法。
如果自动检测到的斑点中心与实际结构中心之间的距离小于或等于一个视盘半径，则视为成功。在分析的不同公共数据库中获得的成功率分别为：视盘（OD）在MESSIDOR数据库中为99.33%、98.58%、97.92%，在DIARETDB1数据库中为96.63%、100%、97.75%，在DRIONS数据库中为100%、无数据、100%，在ONHSD数据库中为100%、98.85%、97.70%；黄斑（M）在MESSIDOR数据库中为99.33%、98.58%、97.92%，在DIARETDB1数据库中为96.63%、100%、97.75%，在DRIONS数据库中为100%、无数据、100%，在ONHSD数据库中为100%、98.85%、97.70%；血管束（VB）在MESSIDOR数据库中为99.33%、98.58%、97.92%，在DIARETDB1数据库中为96.63%、100%、97.75%，在DRIONS数据库中为100%、无数据、100%，在ONHSD数据库中为100%、98.85%、97.70%。最后，本研究中每个结构获得的总体成功率分别为：视盘（OD）为99.26%，黄斑（M）为98.69%，血管束（VB）为98.95%。每张图像的平均处理时间为4.16 ± 0.72秒。
使用结构间关系知识的主要优点是减少了检测过程中的误报数量。所实现的方法能够同时检测四种结构。它快速、稳健，其检测结果与近期文献中的其他方法相比具有竞争力。
