Diabetic retinopathy detection and stage classification in eye fundus images using active deep learning

Multimedia Tools and Applications - Retinal fundus image analysis (RFIA) for diabetic retinopathy (DR) screening can be used to reduce the risk of blindness among diabetic patients. The RFIA...     

Eye movement analysis system using fundus images

This paper describes a precise eye movement analysis system that incorporates an infra-red television (fundus) camera and utilizes image processing techniques. Using this method, we can measure vertical and horizontal eye position and target position as a function of time.This system uses a two level hierarchical searching method to detect the papilla quickly. The first level gives a rough estimate of papillary position by detecting the papillary area with a mask operation (differential-like operation). The second level detects papillary position precisely by a correlation method.Finally, the paper describes experimental results of measuring eye movement in horizontal and vertical directions.     

Hard exudate detection in retinal fundus images using supervised learning

Neural Computing and Applications - The patients with diabetes have a chance to develop diabetic retinopathy (DR) which affects to the eyes. DR can cause blindness if the patients do not control...     

A personal identification system using retinal vasculature in retinal fundus images

The characteristics of human body such as fingerprint, face, hand palm and iris are measured, recorded and identified by performing comparison using biometric devices. Even though it has not seen widespread acceptance yet, retinal identification based on retinal vasculatures in retina provides the most secure and accurate authentication means among biometric systems. Using retinal images taken from individuals, retinal identification is employed in environments such as nuclear research centers and facilities, weapon factories, where extremely high security measures are needed. The superiority of this method stems from the fact that retina is unique to every human being and it would not be changed during human life. Adversely, other identification approaches such as fingerprint, face, palm and iris recognition, are all vulnerable in that those characteristics can be corrupted via plastic surgeries and other changes. In this study we propose an alternate personal identification system based on retinal vascular network in retinal images, which tolerates scale, rotation and translation in comparison. In order to accurately identify a person our new approach first segments vessel structure and then employ similarity measurement along with the tolerations. The developed system, tested on about four hundred images, presents over 95% of success which is quite promising.     

Texture based on geostatistic for glaucoma diagnosis from fundus eye image

Multimedia Tools and Applications - Glaucoma is an ocular disorder that can permanently damage patient vision. Initially, it reduces the visual field, and may cause blindness. Effective methods for...     

Artery/vein classification using reflection features in retina fundus images

Automatic artery/vein (A/V) classification is one of the important topics in retinal image analysis. It allows the researchers to investigate the association between biomarkers and disease progression on a huge amount of data for arteries and veins separately. Recent proposed methods, which employ contextual information of vessels to achieve better A/V classification accuracy, still rely on the performance of pixel-wise classification, which has received limited attention in recent years. In this paper, we show that these classification methods can be markedly improved. We propose a new normalization technique for extracting four new features which are associated with the lightness reflection of vessels. The accuracy of a linear discriminate analysis classifier is used to validate these features. Accuracy rates of 85.1, 86.9 and 90.6% were obtained on three datasets using only local information. Based on the introduced features, the advanced graph-based methods will achieve a better performance on A/V classification.     

Automatic detection and characterisation of retinal vessel tree bifurcations and crossovers in eye fundus images

Analysis of retinal vessel tree characteristics is an important task in medical diagnosis, specially in cases of diseases like vessel occlusion, hypertension or diabetes. The detection and classification of feature points in the arteriovenous eye tree will increase the information about the structure allowing its use for medical diagnosis. In this work a method for detection and classification of retinal vessel tree feature points is presented. The method applies and combines imaging techniques such as filters or morphologic operations to obtain an adequate structure for the detection. Classification is performed by analysing the feature points environment. Detection and classification of feature points is validated using the VARIA database. Experimental results are compared to previous approaches showing a much higher specificity in the characterisation of feature points while slightly increasing the sensitivity. These results provide a more reliable methodology for retinal structure analysis.     

Examining the variation of vascular structure in digital fundus images using textural pattern

One of the most significant retinal abnormality in which an individual loses the vision is diabetic retinopathy (DR). The appropriate way to treat this disease would be easier if it is detected at an earlier stage. The study on the vasculature extracted from illumination correction on the fundus image brings the presence of diabetic retinopathy. This preprocessing involves three steps. Initially illumination and reflectance estimation is done and then illumination correction is employed and finally the clipped histogram equalization is done to preserve the brightness of the image so that the information on the retinal image may not get saturated. Here, k-means segmentation process has been done and the local binary pattern (LBP) has been calculated. The selected feature vectors are then classified by using an echo state neural network (ESNN). The proposed method has been tested on publically available database DIARETDB1 that contained 89 DR fundus images in total. The result of detecting and classifying the pathology based on vasculature study on these images yielded sensitivity of 86.46%, specificity of 80.47%, and accuracy of 96.92%.     

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.

     

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。     

Glaucoma visual field quantification with eye tracker

Glaucoma is a group of diseases that manifest as atrophy and depression of the optic papilla, visual field defects, and vision loss, representing one of the three leading causes of blindness worldwide. Traditional visual field examinations – an important diagnostic tool for glaucoma – present various challenges including patients’ inability to maintain fixed vision, delays in detecting vision loss, passive position detection, difficulty in detection, and limitations in reflecting physiological visual field damage. Early diagnosis and intervention are crucial for improving patients’ condition and enhancing their later-life abilities and life quality. Herein, we proposed two vision field detection systems to overcome these limitations. First, we establish a dynamic visual field detection system to reduce the complexity of traditional detection experiments and to enhance their operability. Instead of fixating on a central point, subjects are only required to search for the target in the picture. We analyze the heat map and trajectory map of visual attention for visual interpretation, and the analysis of experimental data reveals that the average finding time of subjects in the experimental task varies. In response to the scenario where visual field defects are not detected by the dynamic visual field detection system, we have developed a static visual field detection system based on the former. The system obtains eye movement data and automatically generates a map of the extent of the physiological blind spot without any action required from the patient. The experiment results provide evidence for the effectiveness of the static visual field detection system in detecting the physiological blind spot. Given the well-established association between glaucoma and an enlarged physiological blind spot, the use of an eye tracker to assess the extent of the subject’s blind spot represents an easy-to-use and reliable method for preliminary glaucoma screening.     

基于SIFT特征的眼底图像自动拼接

针对眼底图像对比度低、不同视场的图像间存在几何畸变等特点,提出一种基于SIFT特征的眼底图像自动拼接算法。该算法分别提取待拼接眼底图像的SIFT特征点,并用向量进行描述,确定两幅图像特征点的匹配关系,使用MLESAC算法去除误匹配点对,提出对特征点对提纯的距离-斜率相似测度方法,计算匹配点之间的透视变换矩阵,最后进行图像配准和拼接。对实际眼底照相机获取的多幅图像拼接结果表明,该算法具有很好的鲁棒性和稳健性,可以实现眼底图像的高精度自动拼接。     

A computer method of understanding ocular fundus images

We have studied some fundamental problems towards the understanding of color ocular fundus images which are used in the mass diagnosis of adult diseases such as hypertension and diabetes.These problems are: the extraction of blood vessels from the retinal background; the recognition of arteries and veins; the detection and analysis of peculiar regions such as hemorrhages, exudates, optic discs and arterio-venous crossings.We propose a computer method for each of these problems and show some experimental results.     

语义融合眼底图像动静脉分类方法

目的 眼底图像中的动静脉分类是许多系统性疾病风险评估的基础步骤。基于传统机器学习的方法操作复杂,且往往依赖于血管提取的结果,不能实现端到端的动静脉分类,而深度语义分割技术的发展使得端到端的动静脉分类成为可能。本文结合深度学习强大的特征提取能力,以提升动静脉分类精度为目的,提出了一种基于语义融合的动静脉分割模型SFU-Net（semantic fusion based U-Net）。方法 针对动静脉分类任务的特殊性,本文采用多标签学习的策略来处理该问题,以降低优化难度。针对动静脉特征的高度相似性,本文以DenseNet-121作为SFU-Net的特征提取器,并提出了语义融合模块以增强特征的判别能力。语义融合模块包含特征融合和通道注意力机制两个操作：1）融合不同尺度的语义特征从而得到更具有判别能力的特征;2）自动筛选出对目标任务更加重要的特征,从而提升性能。针对眼底图像中血管与背景像素之间分布不均衡的问题,本文以focal loss作为目标函数,在解决类别不均衡问题的同时重点优化困难样本。结果 实验结果表明,本文方法的动静脉分类的性能优于现有绝大多数方法。本文方法在DRIVE（digital retinal images for vessel extraction）数据集上的灵敏性（sensitivity）与目前最优方法相比仅有0.61%的差距,特异性（specificity）、准确率（accuracy）和平衡准确率（balanced-accuracy）与目前最优方法相比分别提高了4.25%,2.68%和1.82%;在WIDE数据集上的准确率与目前最优方法相比提升了6.18%。结论 语义融合模块能够有效利用多尺度特征并自动做出特征选择,从而提升性能。本文提出的SFU-Net在动静脉分类任务中表现优异,性能超越了现有绝大多数方法。     

Computerised approaches for the detection of diabetic retinopathy using retinal fundus images: a survey

Eye-related disease such as diabetic retinopathy (DR) is a medical ailment in which the retina of the human eye is smashed because of damage to the tiny retinal blood vessels in the retina. Ophthalmologists identify DR based on various features such as the blood vessels, textures and pathologies. With the rapid development of methods of analysis of biomedical images and advanced computing techniques, image processing-based software for the detection of eye disease has been widely used as an important tool by ophthalmologists. In particular, computer vision-based methods are growing rapidly in the field of medical images analysis and are appropriate to advance ophthalmology. These tools depend entirely on visual analysis to identify abnormalities in Retinal Fundus images. During the past two decades, exciting improvement in the development of DR detection computerised systems has been observed. This paper reviews the development of analysing retinal images for the detection of DR in three aspects: automatic algorithms (classification or pixel to pixel methods), detection methods of pathologies from retinal fundus images, and extraction of blood vessels of retinal fundus image algorithms for the detection of DR. The paper presents a detailed explanation of each problem with respect to retinal images. The current techniques that are used to analyse retinal images and DR detection issues are also discussed in detail and recommendations are made for some future directions.     

An improved vessel extraction scheme from retinal fundus images

Vessel extraction from retinal fundus images is essential for the diagnosis of different opthalmologic diseases like glaucoma, diabetic retinopathy and hypertension. It is a challenging task due to presence of several noises embedded with thin vessels. In this article, we have proposed an improved vessel extraction scheme from retinal fundus images. First, mathematical morphological operation is performed on each planes of the RGB image to remove the vessels for obtaining noise in the image. Next, the original RGB and vessel removed RGB image are transformed into negative gray scale image. These negative gray scale images are subtracted and finally binarized (BW₁) by leveling the image. It still contains some granular noise which is removed based on the area of connected component. Further, previously detected vessels are replaced in the gray-scale image with mean value of the gray-scale image and then the gray-scale image is enhanced to obtain the thin vessels. Next, the enhanced image is binarized and thin vessels are obtained (BW₂). Finally, the thin vessel image (BW₂) is merged with the previously obtained binary image (BW₁) and finally we obtain the vessel extracted image. To analyze the performance of our proposed method we have experimented on publicly available DRIVE dataset. We have observed that our algorithm have provides satisfactory performance with the sensitivity, specificity and accuracy of 0.7260, 0.9802 and 0.9563 respectively which is better than the most of the recent works.

     

Reliable detection of eye features and eyes in color facial images using ternary eye-verifier

Eye detection plays an important role in applications related to face recognition. The position of eyes can be used as a reliable reference for other facial feature detection. This paper presents a novel approach for the precise and reliable detection of eyes by introducing a ternary eye-verifier. Initially, the face region is detected by combining color information and the Haar-like feature detector. The face region is then binarized and filtered with circular filters to detect eye candidates at the peaks in the filtered response. Each eye candidate is fed into a ternary eye-verifier that includes a proposed eye feature extractor based on K-means clustering with compensation for variety in iris color. The eye template in the eye-verifier is constructed based on both the knowledge of eye geometry and the detected eye features. The template matching is made by the ternary Hamming distance. Experiments over a collection of FERET face database and house-made face database with different head poses confirm that the proposed method achieves precise and reliable detection of eyes from color facial images with variation in illumination, pose, eye gazing direction, and race.     

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。     

基于眼底图像不同彩色通道的出血特征提取

针对眼底出血图像中出血形态各异、干扰目标多的特性,为提高出血检测精度,同时降低非出血目标引起的干扰,提出了一种基于眼底图像三个彩色通道的出血特征提取方法。该方法利用眼底出血图像在不同彩色通道的表现特性,统计和分析相关性状的像素值特性,并依据出血部分的统计特性设定提取阈值提取出血;使用多尺度顶帽变换和血管密度特征定位血管和黄斑;最后利用不用图像间的逻辑关系针对性去除血管、黄斑干扰,实现了出血区域的自动提取和干扰目标的排除。仿真结果表明,所提方法能够相对完整和准确地提取眼底图像出血目标,且时间效率高。