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.     

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.

     

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。     

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。     

基于YOLO算法的眼底图像视盘定位方法

视盘的各个参数是衡量眼底健康状况和病灶的重要指标,视盘的检测和定位对于观察视盘的形态尤为重要。在以往的视盘定位研究中,主要根据视盘的形状、亮度、眼底血管的走向等特征使用图像处理的方法对眼底图像中视盘进行定位。由于人为因素影响较大,特征提取时间较长,且视盘定位效率低,因此提出一种基于YOLO算法的眼底图像视盘定位方法。利用YOLO算法将眼底图像划分为N×N的格子,每个格子负责检测视盘中心点是否落入该格子中,通过多尺度的方式和残差层融合低级特征对视盘进行定位,得到不同大小的边界框,最后通过非极大抑制的方式筛选出得分最高的边界框。通过在3个公开的眼底图像数据集(DRIVE、DRISHTI-GS1和MESSIDOR)上,对所提出的视盘定位方法进行测试,定位准确率均为100%,实验同时定位出视盘的中心点坐标,与标准中心点的平均欧氏距离分别为22.36 px、2.52 px、21.42 px,验证了该方法的准确性和通用性。     

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.     

基于融合相位特征的视网膜血管分割算法

针对相位一致性特征对血管中心检测不足问题,提出基于融合相位特征的眼底视网膜血管分割算法。首先,预处理原始的视网膜图像;然后,对图像中每个像素构造4D的特征向量（包括Hessian矩阵、Gabor变换、条带选择组合位移滤波响应（B-COSFIRE）滤波、相位特征）;最后,采用支持向量机（SVM）进行像素分类,实现眼底视网膜血管的分割。其中,相位特征是将分别提取的相位一致性特征与Hessian矩阵特征进行小波融合后得到的一种新的融合相位特征。该特征既保留了相位一致性特征良好的血管边缘信息,又克服了相位一致性特征对血管中心检测的不足。在用于血管提取的数字视网膜图像（DRIVE）数据库上测得基于融合相位特征的视网膜血管分割算法的平均准确率（Acc）为0.9574,平均受试者工作曲线面积（AUC）为0.9702;且在单一特征进行像素分类提取血管的实验中,与使用相位一致性特征相比,使用融合相位特征进行像素分类提取血管的Acc由0.9191提高到0.9478,AUC由0.9359提高到0.9578。实验结果表明,融合相位特征比相位一致性特征更适用于基于像素分类的眼底视网膜血管分割算法。     

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.     

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。     

视盘与黄斑同时定位检测的FPGA方法研究

在眼底图像自动分析中,视盘与黄斑的定位是实现利用计算机辅助诊断或筛查糖尿病视网膜病变的先决条件。提出一种实现眼底图像中视盘与黄斑同时定位检测的新方法,使用YOLOv4-tiny算法定位检测,将该算法移植到现场可编程逻辑门阵列（field programmable gate array,FPGA）。与传统方法相比,该方法不仅可以快速准确地同时定位眼底图像中视盘和黄斑的位置,而且也是利用高层综合（high level synthesis,HLS）语言和时分复用技术实现38层中型神经网络的首次尝试。实验采用公认的COCO数据集和Kaggle-Diabetic Retinopathy Detection竞赛中的381幅眼底图像对算法进行训练,将训练后的算法移植到FPGA平台后视盘和黄斑定位的平均正确率（mean average precision,mAP）为96.11%,检测一张图片只需要150.445?ms,在相关领域具有良好的临床应用前景。     

基于L*a*b*色彩空间的视神经边缘自动提取

视神经(Optic nerve)形状、面积和深度等参数是衡量眼底健康状况的重要指标, 其边缘提取是量化这些参数的前提. 为精确识别视神经边缘, 本文提出了一种基于L*a*b*色彩空间眼底图像视神经边缘自动提取算法. 该方法通过L*a*b*色彩空间自适应形态学方法与区域辅助几何活动轮廓模型边缘提取方法, 结合基于交叉网络的视神经自动定位, 实现视神经边缘的自动提取. 采用国际上通用的DRIVE眼底图像库和临床图像进行实验, 验证了该算法的有效性.     

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。     

基于自适应多尺度模板匹配的视盘检测方法

针对视盘检测易受光照和弱对比度影响的问题,提出了一种全新的视盘检测方法用于有效地定位和分割视盘.首先,采用预处理技术校正不均匀的光照和提高弱的对比度.然后,利用交替序列滤波和区域极大值技术提取一系列的视盘关键点.再次,利用提出的自适应多尺度模板匹配方法,计算每一个视盘关键点的相关系数,并将最大相关系数值所对应的关键点视为视盘中心.最后,基于获得的视盘中心,提取包含该中心位置的感兴趣区域,并在此基础上,利用Canny边缘检测算子和霍夫变换技术,实现视盘边缘的有效估计.该算法在DRIVE、DIRATEDB0、DIRATEDB1和ROC四个公共数据库上进行了测试,实验结果表明,提出算法的性能明显地优于现有方法.     

A Unique Discrete Wavelet & Deterministic Walk-Based Glaucoma Classification Approach Using Image-Specific Enhanced Retinal Images

Glaucoma is a group of ocular atrophy diseases that cause progressive vision loss by affecting the optic nerve. Because of its asymptomatic nature, glaucoma has become the leading cause of human blindness worldwide. In this paper, a novel computer-aided diagnosis (CAD) approach for glaucomatous retinal image classification has been introduced. It extracts graph-based texture features from structurally improved fundus images using discrete wavelet-transformation (DWT) and deterministic tree-walk (DTW) procedures. Retinal images are considered from both public repositories and eye hospitals. Images are enhanced with image-specific luminance and gradient transitions for both contrast and texture improvement. The enhanced images are mapped into undirected graphs using DTW trajectories formed by the image’s wavelet coefficients. Graph-based features are extracted from these graphs to capture image texture patterns. Machine learning (ML) classifiers use these features to label retinal images. This approach has attained an accuracy range of 93.5% to 100%, 82.1% to 99.3%, 95.4% to 100%, 83.3% to 96.6%, 77.7% to 88.8%, and 91.4% to 100% on the ACRIMA, ORIGA, RIM-ONE, Drishti, HRF, and HOSPITAL datasets, respectively. The major strength of this approach is texture pattern identification using various topological graphs. It has achieved optimal performance with SVM and RF classifiers using biorthogonal DWT combinations on both public and patients’ fundus datasets. The classification performance of the DWT-DTW approach is on par with the contemporary state-of-the-art methods, which can be helpful for ophthalmologists in glaucoma screening.     

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.     

Systematic image processing for diagnosing brain tumors: A Type-II fuzzy expert system approach

This paper presents a systematic Type-II fuzzy expert system for diagnosing the human brain tumors (Astrocytoma tumors) using T₁-weighted Magnetic Resonance Images with contrast. The proposed Type-II fuzzy image processing method has four distinct modules: Pre-processing, Segmentation, Feature Extraction, and Approximate Reasoning. We develop a fuzzy rule base by aggregating the existing filtering methods for Pre-processing step. For Segmentation step, we extend the Possibilistic C-Mean (PCM) method by using the Type-II fuzzy concepts, Mahalanobis distance, and Kwon validity index. Feature Extraction is done by Thresholding method. Finally, we develop a Type-II Approximate Reasoning method to recognize the tumor grade in brain MRI. The proposed Type-II expert system has been tested and validated to show its accuracy in the real world. The results show that the proposed system is superior in recognizing the brain tumor and its grade than Type-I fuzzy expert systems.     

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。     

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.

     

Mean shift based gradient vector flow for image segmentation

In recent years, gradient vector flow (GVF) based algorithms have been successfully used to segment a variety of 2-D and 3-D imagery. However, due to the compromise of internal and external energy forces within the resulting partial differential equations, these methods may lead to biased segmentation results. In this paper, we propose MSGVF, a mean shift based GVF segmentation algorithm that can successfully locate the correct borders. MSGVF is developed so that when the contour reaches equilibrium, the various forces resulting from the different energy terms are balanced. In addition, the smoothness constraint of image pixels is kept so that over- or under-segmentation can be reduced. Experimental results on publicly accessible datasets of dermoscopic and optic disc images demonstrate that the proposed method effectively detects the borders of the objects of interest.