视盘和视杯分割在计算机辅助青光眼诊断中的应用综述

青光眼是以视神经损伤、特征性视野损伤为特点的一类眼病,在早期很难诊断,尽早发现可更好地遏制青光眼病症的恶化,降低致盲率。视盘和视杯的比值是评价青光眼诊断中的重要指标之一,视盘和视杯的分割是青光眼诊断的关键步骤。但眼底彩照中的渗出物、不均匀照明区域等特征使其可能出现相似的亮度区域,导致视盘和视杯的分割非常困难。因此本文对现有眼底彩照中视盘和视杯的分割方法进行了总结,并将其分为5大类：水平集法、模态法、能量泛函法、划分法以及基于机器学习的混合法。系统地梳理了各类算法的代表性方法,以及基本思想、理论基础、关键技术、框架流程和优缺点等。同时,概括了适用于青光眼诊断的各种数据集,包括数据集的名称、来源以及详细内容,并总结了在各种数据集中不同视盘和视杯分割结果和诊断青光眼的量化指标及其相关结果。在现有的视盘和视杯分割方法中,许多图像处理和机器学习技术得到广泛应用。通过对该领域研究算法进行综述,清晰直观地总结了各类算法之间的特点及联系,有助于推动视盘和视杯分割在青光眼疾病临床诊断中的应用。可以在很大程度上提高临床医生的工作效率,为临床诊断青光眼提供了重要的理论研究意义和价值。     

视觉显著性的眼底图像视盘检测

目的 青光眼是导致失明的主要疾病之一,视盘区域的形状、大小等参数是青光眼临床诊断的重要指标。然而眼底图像通常亮度低、对比度弱,且眼底结构复杂,各组织以及病灶干扰严重。为解决上述问题,实现视盘的精确检测,提出一种视觉显著性的眼底图像视盘检测方法。方法 首先,依据视盘区域显著的特点,采用一种基于视觉显著性的方法对视盘区域进行定位;其次,采用全卷积神经网络（fully convolutional neural network,FCN）预训练模型提取深度特征,同时计算视盘区域的平均灰度,进而提取颜色特征;最后,将深度特征、视盘区域的颜色特征和背景先验信息融合到单层元胞自动机（single-layer cellular automata,SCA）中迭代演化,实现眼底图像视盘区域的精确检测。结果 在视网膜图像公开数据集DRISHTI-GS、MESSIDOR和DRIONS-DB上对本文算法进行实验验证,平均相似度系数分别为0.965 8、0.961 6和0.971 1;杰卡德系数分别为0.934 1、0.922 4和0.937 6;召回率系数分别为0.964 8、0.958 9和0.967 4;准确度系数分别为0.996 6、0.995 3和0.996 8,在3个数据集上均可精确地检测视盘区域。实验结果表明,本文算法精确度高,鲁棒性强,运算速度快。结论 本文算法能够有效克服眼底图像亮度低、对比度弱及血管、病灶等组织干扰的影响,在多个视网膜图像公开数据集上进行验证均取得了较好的检测结果,具有较强的泛化性,可以实现视盘区域的精确检测。     

一种基于改进Attention U-net的联合视杯视盘分割方法

青光眼是当前世界范围内致盲的主要病因之一,其发病过程没有明显的特征。视杯盘比是青光眼诊断中最主要的评估指标之一,这使得视杯视盘的分割成为了目前青光眼诊断的关键。已有的视杯视盘分割方法大多基于手工提取的特征,低效且精度不高。提出一种名为MAR2U-net的深度神经网络架构用于青光眼视杯视盘的联合分割。它是基于Attention U-net的一种改进架构,通过在Attention U-net的基础之上引入递归残差卷积模块来提取更加深层次的特征,并结合多尺度的输入和多标签的Focal Tversky损失函数来提升模型的联合分割性能。实验结果表明,该方法在REFUGE数据集上的分割效果较已有方法取得了显著提升,为实现大规模的青光眼诊断筛查提供了基础。     

多相主动轮廓模型的眼底图像杯盘分割

目的 视盘及视杯的检测对于分析眼底图像和视网膜视神经疾病计算机辅助诊断来说十分重要,利用医学眼底图像中视盘和视杯呈现椭圆形状这一特征,提出了椭圆约束下的多相主动轮廓模型,实现视盘视杯的同时精确分割。方法 该算法根据视盘视杯在灰度图像中具有不同的区域亮度,建立多相主动轮廓模型,然后将椭圆形约束内嵌于该模型中。通过对该模型的能量泛函进行求解,得到椭圆参数的演化方程。分割时首先设定两条椭圆形初始曲线,根据演化方程,驱动曲线分别向视盘和视杯方向进行移动。当轮廓线到达视盘、视杯边缘时,曲线停止演化。结果 在不同医学眼底图像中对算法进行验证,对算法抗噪性、不同初始曲线选取等进行了实验,并与多种算法进行了对比。实验结果表明,本文模型能够同时分割出视盘及视杯,与其他模型的分割结果相比,本文算法的分割结果更加准确。结论 本文算法可以精确分割医学眼底图像中的视盘和视杯,该算法不需要预处理,具有较强的鲁棒性和抗噪性。     

基于医学影像分割方法的多模态语料库构建

电子文本病历语料库可提供相关医学影像的定性诊断结果,但缺乏直观影像和文本标注信息,不利于有效管理医学数据和医科学生自主学习相关医学知识.针对此问题,文中提出基于深度水平集算法的医学影像分割方法,对医学影像进行自动分割,给出感兴趣区域的轮廓结果及相关定量指标,并结合自然语言处理方法实现电子病历文本的标注,增强影像与文本病历多模态语料库的信息表征能力.在青光眼影像数据上的实验表明,文中方法可精准分割眼底图像中视盘和视杯,有效构建具有直观影像标记与对应病历文本的多模态语料库.     

Retinal optic disc localization using convergence tracking of blood vessels

Optic disc localization is of great diagnostic value related to retinal diseases, such as glaucoma and diabetic retinopathy. However, the detection process is quite challenging because positions of optic discs vary from image to image, and moreover, pathological changes, like hard exudates or neovascularization, may alter optic disc appearance. In this paper, we propose a robust approach to accurately detect the optic disc region and locate the optic disc center in color retinal images. The proposed technique employs a kernelized least-squares classifier to decide the area that contains optic disc. Then connected-component labeling and lumination information are used together to find the convergence of blood vessels, which is thought to be optic disc center. The proposed method has been evaluated over two datasets: the Digital Retinal Images for Vessel Extraction (DRIVE), and the Non-fluorescein Images for Vessel Extraction (NIVE) datasets. Experimental results have shown that our method outperforms existing methods, achieving a competitive accuracy (97.52 %) and efficiency (1.1577s).     

Segmentation of optic disc in retinal images using an improved gradient vector flow algorithm

Image segmentation plays an important role in the analysis of retinal images as the extraction of the optic disk provides important cues for accurate diagnosis of various retinopathic diseases. In recent years, gradient vector flow (GVF) based algorithms have been used successfully to successfully segment a variety of medical imagery. However, due to the compromise of internal and external energy forces within the resulting partial differential equations, these methods can lead to less accurate segmentation results in certain cases. In this paper, we propose the use of a new mean shift-based GVF segmentation algorithm that drives the internal/external energies towards the correct direction. The proposed method incorporates a mean shift operation within the standard GVF cost function to arrive at a more accurate segmentation. Experimental results on a large dataset of retinal images demonstrate that the presented method optimally detects the border of the optic disc.     

双层水平集描述眼底图像视杯视盘分割

目的 青光眼是一种可导致视力严重减弱甚至失明的高发眼部疾病。在眼底图像中,视杯和视盘的检测是青光眼临床诊断的重要步骤之一。然而,眼底图像普遍是灰度不均匀的,眼底结构复杂,不同结构之间的灰度重叠较多,受到血管和病变的干扰较为严重。这些都给视盘与视杯的分割带来很大挑战。因此,为了更准确地提取眼底图像中的视杯和视盘区域,提出一种基于双层水平集描述的眼底图像视杯视盘分割方法。方法 通过水平集函数的不同层级分别表示视杯轮廓和视盘轮廓,依据视杯与视盘间的位置关系建立距离约束,应用图像的局部信息驱动活动轮廓演化,克服图像的灰度不均匀性。根据视杯与视盘的几何形状特征,引入视杯与视盘形状的先验信息约束活动轮廓的演化,从而实现视杯与视盘的准确分割。结果 本文使用印度Aravind眼科医院提供的具有视杯和视盘真实轮廓注释的CDRISHTI-GS1数据集对本文方法进行实验验证。该数据集主要用来验证视杯及视盘分割方法的鲁棒性和有效性。本文方法在数据集上对视杯和视盘区域进行分割,取得了67.52%的视杯平均重叠率,81.04%的视盘平均重叠率,0.719的视杯F1分数和0.845的视盘F1分数,结果优于基于COSFIRE（combination of shifted filter responses）滤波模型的视杯视盘分割方法、基于先验形状约束的多相Chan-Vese（C-V）模型和基于聚类融合的水平集方法。结论 实验结果表明,本文方法能够有效克服眼底图像灰度不均匀、血管及病变区域的干扰等影响,更为准确地提取视杯与视盘区域。     

A new convolutional neural network model for peripapillary atrophy area segmentation from retinal fundus images

Peripapillary atrophy (PPA) is a clinical finding, which reflects the atrophy of retina layer and retinal pigment epithelium. The size of PPA area is a useful medical indicator, as it is highly associated with many diseases such as glaucoma and myopia. Therefore, separating the PPA area from retinal images, which is called PPA area segmentation, is very important. It is a challenging task, because PPA areas are irregular and non-uniform, and their contours are blurry and change gradually. To solve these issues, we transform the PPA area segmentation task into a task of segmenting another two areas with relatively regular and uniform shapes, and then propose a novel multi-task fully convolutional network (MFCN) model to jointly extract them from retinal images. Meanwhile, we take edge continuity of the target area into consideration. To evaluate the performance of the proposed model, we conduct experiments on images with PPA areas labelled by experts and achieve an average precision of 0.8928, outperforming the state-of-the-art models. To demonstrate the application of PPA segmentation in medical research, we apply PPA related features based on the segmented PPA area on differentiating glaucomatous and physiologic large cup cases. Experiment conducted on real datasets confirms the effectiveness of using these features for glaucoma diagnosis.     

Multilayered thresholding-based blood vessel segmentation for screening of diabetic retinopathy

Diabetic retinopathy screening involves assessment of the retina with attention to a series of indicative features, i.e., blood vessels, optic disk and macula etc. The detection of changes in blood vessel structure and flow due to either vessel narrowing, complete occlusions or neovascularization is of great importance. Blood vessel segmentation is the basic foundation while developing retinal screening systems since vessels serve as one of the main retinal landmark features. This article presents an automated method for enhancement and segmentation of blood vessels in retinal images. We present a method that uses 2-D Gabor wavelet for vessel enhancement due to their ability to enhance directional structures and a new multilayered thresholding technique for accurate vessel segmentation. The strength of proposed segmentation technique is that it performs well for large variations in illumination and even for capturing the thinnest vessels. The system is tested on publicly available retinal images databases of manually labeled images, i.e., DRIVE and STARE. The proposed method for blood vessel segmentation achieves an average accuracy of 94.85% and an average area under the receiver operating characteristic curve of 0.9669. We compare our method with recently published methods and experimental results show that proposed method gives better results.     

Automatic segmentation of optic disc in retinal fundus images using semi-supervised deep learning

Diseases of the eye require manual segmentation and examination of the optic disc by ophthalmologists. Though, image segmentation using deep learning techniques is achieving remarkable results, it leverages on large-scale labeled datasets. But, in the field of medical imaging, it is challenging to acquire large labeled datasets. Hence, this article proposes a novel deep learning model to automatically segment the optic disc in retinal fundus images by using the concepts of semi-supervised learning and transfer learning. Initially, a convolutional autoencoder (CAE) is trained to automatically learn features from a large number of unlabeled fundus images available from the Kaggle’s diabetic retinopathy (DR) dataset. The autoencoder (AE) learns the features from the unlabeled images by reconstructing the input images and becomes a pre-trained network (model). After this, the pre-trained autoencoder network is converted into a segmentation network. Later, using transfer learning, the segmentation network is trained with retinal fundus images along with their corresponding optic disc ground truth images from the DRISHTI GS1 and RIM-ONE datasets. The trained segmentation network is then tested on retinal fundus images from the test set of DRISHTI GS1 and RIM-ONE datasets. The experimental results show that the proposed method performs on par with the state-of-the-art methods achieving a 0.967 and 0.902 dice score coefficient on the test set of the DRISHTI GS1 and RIM-ONE datasets respectively. The proposed method also shows that transfer learning and semi-supervised learning overcomes the barrier imposed by the large labeled dataset. The proposed segmentation model can be used in automatic retinal image processing systems for diagnosing diseases of the eye.

     

Automated segmentation of optic disc region on retinal fundus photographs: Comparison of contour modeling and pixel classification methods

The automatic determination of the optic disc area in retinal fundus images can be useful for calculation of the cup-to-disc (CD) ratio in the glaucoma screening. We compared three different methods that employed active contour model (ACM), fuzzy c-mean (FCM) clustering, and artificial neural network (ANN) for the segmentation of the optic disc regions. The results of these methods were evaluated using new databases that included the images captured by different camera systems. The average measures of overlap between the disc regions determined by an ophthalmologist and by using the ACM (0.88 and 0.87 for two test datasets) and ANN (0.88 and 0.89) methods were slightly higher than that by using FCM (0.86 and 0.86) method. These results on the unknown datasets were comparable with those of the resubstitution test; this indicates the generalizability of these methods. The differences in the vertical diameters, which are often used for CD ratio calculation, determined by the proposed methods and based on the ophthalmologist's outlines were even smaller than those in the case of the measure of overlap. The proposed methods can be useful for automatic determination of CD ratios.     

A novel optic disc detection scheme on retinal images

Robust and effective optic disc detection is a necessary processing component in automatic retinal screening systems. In this paper, optic disc localization is achieved by a novel illumination correction operation, and contour segmentation is completed by a supervised gradient vector flow snake (SGVF snake) model. Conventional GVF snake is not sufficient to segment contour due to vessel occlusion and fuzzy disc boundaries. In view of this reason, the SGVF snake is extended in each time of deformation iteration, so that the contour points can be classified and updated according to their corresponding feature information. The classification relies on the feature vector extraction and the statistical information generated from training images. This approach is evaluated by means of two publicly available databases, Digital Retinal Images for Vessel Extraction (DRIVE) database and Structured Analysis of the Retina (STARE) database, of color retinal images. The experimental results show that the overall performance is with 95% correct optic disc localization from the two databases and 91% disc boundaries are correctly segmented by the SGVF snake algorithm.     

Simple methods for segmentation and measurement of diabetic retinopathy lesions in retinal fundus images

Diabetic retinopathy (DR) is one of the most important complications of diabetes mellitus, which causes serious damages in the retina, consequently visual loss and sometimes blindness if necessary medical treatment is not applied on time. One of the difficulties in this illness is that the patient with diabetes mellitus requires a continuous screening for early detection. So far, numerous methods have been proposed by researchers to automate the detection process of DR in retinal fundus images. In this paper, we developed an alternative simple approach to detect DR. This method was built on the inverse segmentation method, which we suggested before to detect Age Related Macular Degeneration (ARMDs). Background image approach along with inverse segmentation is employed to measure and follow up the degenerations in retinal fundus images. Direct segmentation techniques generate unsatisfactory results in some cases. This is because of the fact that the texture of unhealthy areas such as DR is not homogenous. The inverse method is proposed to exploit the homogeneity of healthy areas rather than dealing with varying structure of unhealthy areas for segmenting bright lesions (hard exudates and cotton wool spots). On the other hand, the background image, dividing the retinal image into high and low intensity areas, is exploited in segmentation of hard exudates and cotton wool spots, and microaneurysms (MAs) and hemorrhages (HEMs), separately. Therefore, a complete segmentation system is developed for segmenting DR, including hard exudates, cotton wool spots, MAs, and HEMs. This application is able to measure total changes across the whole retinal image. Hence, retinal images that belong to the same patients are examined in order to monitor the trend of the illness. To make a comparison with other methods, a Na?ve Bayes method is applied for segmentation of DR. The performance of the system, tested on different data sets including various qualities of retinal fundus images, is over 95% in detection of the optic disc (OD), and 90% in segmentation of the DR.     

基于PCLSM的M-S模型的视乳头杯盘分割

基于分段常数水平集方法的M—S模型能解决二值M—S模型及其相应的C—V模型不适合包含多个目标（或多相）的图像分割的问题。采用该方法研究青光眼视乳头图像杯盘分割难题,并在此基础上进行杯盘重建。实验表明,该方法能够正确分割不同青光眼病人的视乳头图像。与多层分割方法相比,该方法能同时获得视杯和视盘的形态。     

Combining algorithms for automatic detection of optic disc and macula in fundus images

This paper proposes an efficient combination of algorithms for the automated localization of the optic disc and macula in retinal fundus images. There is in fact no reason to assume that a single algorithm would be optimal. An ensemble of algorithms based on different principles can be more accurate than any of its individual members if the individual algorithms are doing better than random guessing. We aim to obtain an improved optic disc and macula detector by combining the prediction of multiple algorithms, benefiting from their strength and compensating their weaknesses. The location with maximum number of detectors’ outputs is formally the hotspot and is used to find the optic disc or macula center. An assessment of the performance of integrated system and detectors working separately is also presented. Our proposed combination of detectors achieved overall highest performance in detecting optic disc and fovea closest to the manually center chosen by the retinal specialist.     

Hybrid feature vector based detection of Glaucoma

This paper focus on the investigation of the potential in retinal image analysis for the detection of Glaucoma. The computer-based analysis of the parameter involves the use of image processing algorithms for pre-processing, localization and segmentation of the region of interest (ROI), feature extraction from ROI, and classification. The initial step in computer based detection system includes the enhancing scheme for improving the contrast of the fundus image from the three databases, Drishti-GS1, FAU and RIMONE. The optic disc region has been localized from the enhanced image. Structural deformation of the optic disc region, one of the primary indicators of the glaucoma demands more accuracy in segmentation process. As a solution to this problem, non-morphological features are extracted from the enhanced optic disc region. The non-morphological features from spatial domain include Local Binary Pattern, Histogram of Oriented Gradient and Fractal features. The significant feature extracted from the spatial domain are selected using Sequential Floating Forward Selection method and are then fed into the Support Vector Machine, Naive Bayes and Logistic Regression classifiers. Performance of the classifier is analyzed by computing the accuracy, sensitivity, specificity and positive prediction value. The performance of the classifier is also validated using the receiver operating characteristics plot. The hybrid feature from the spatial domain contributes to increase the efficiency of classification.

     

视网膜图像中的黄斑中心检测

目的 在眼底图像分析中,准确的黄斑中心定位对于糖尿病性视网膜病变的计算机辅助诊断系统具有重要的意义。然而,由于光照不均匀、计算量大及病变的干扰给黄斑中心定位带来了巨大的挑战。因此,为了实现更为准确且高效的黄斑中心检测,提出一种基于血管投影和数学形态学的黄斑中心检测方法。方法 首先,基于数学形态学,提出一种自动的血管检测方法。其次,利用视盘区域的血管分布实现视盘中心的自动定位。再次,根据视盘和黄斑的解剖学结构先验信息,提取感兴趣区域。最后,在感兴趣区域内,通过数学形态学和特征提取定位黄斑中心。结果 本文提出的方法在两个标准的糖尿病视网膜病变数据库DIARETDB0和DIARETDB1上分别取得了96.92%和96.63%的成功率,且总成功率达到96.35%。此外,平均的执行时间分别为8.236 s和8.912 s。结论 实验结果表明,本文方法能快速和准确地定位黄斑中心且其性能明显地优于现有的黄斑中心检测方法。     

融合残差上下文编码和路径增强的视杯视盘分割

目的 从眼底图像中分割视盘和视杯对于眼部疾病智能诊断来说是一项重要工作,U-Net及变体模型已经广泛应用在视杯盘分割任务中。由于连续的卷积与池化操作容易引起空间信息损失,导致视盘和视杯分割精度差且效率低。提出了融合残差上下文编码和路径增强的深度学习网络RCPA-Net,提升了分割结果的准确性与连续性。方法 采用限制对比度自适应直方图均衡方法处理输入图像,增强对比度并丰富图像信息。特征编码模块以ResNet34(residual neural network)为骨干网络,通过引入残差递归与注意力机制使模型更关注感兴趣区域,采用残差空洞卷积模块捕获更深层次的语义特征信息,使用路径增强模块在浅层特征中获得精确的定位信息来增强整个特征层次。本文还提出了一种新的多标签损失函数用于提高视盘视杯与背景区域的像素比例并生成最终的分割图。结果 在4个数据集上与多种分割方法进行比较,在ORIGA(online retinal fundus image database for glaucoma analysis)数据集中,本文方法对视盘分割的JC(Jaccard)指数为0.939 1,F-measure为...     

带尺寸约束的弱监督眼底图像视盘分割

目的 医学图像的像素级标注工作需要耗费大量的人力。针对这一问题，本文以医学图像中典型的眼底图像视盘分割为例，提出了一种带尺寸约束的弱监督眼底图像视盘分割算法。方法 对传统卷积神经网络框架进行改进，根据视盘的结构特点设计新的卷积融合层，能够更好地提升分割性能。为了进一步提高视盘分割精度，本文对卷积神经网络的输出进行了尺寸约束，同时用一种新的损失函数对尺寸约束进行优化，所提的损失公式可以用标准随机梯度下降方法来优化。结果 在RIM-ONE视盘数据集上展开实验，并与经典的全监督视盘分割方法进行比较。实验结果表明，本文算法在只使用图像级标签的情况下，平均准确识别率（mAcc）、平均精度（mPre）和平均交并比（mIoU）分别能达到0.852、0.831、0.827。结论 本文算法不需要专家进行像素级标注就能够实现视盘的准确分割，只使用图像级标注就能够得到像素级标注的分割精度。缓解了医学图像中像素级标注难度大的问题。