Computer-aided retinal vessel segmentation in retinal images: convolutional neural networks

In medicine, diagnosis is as important as treatment. Retinal blood vessels are the most easily visible vessels in the whole body, and therefore, play a key role in the diagnosis of numerous diseases and eye disorders. Systematic and eye diseases cause morphologic variations, such as the growing, narrowing or branching of retinal blood vessels. Imaging-based screening of retinal blood vessels plays an important role in the identification and follow-up of eye diseases. Therefore, automatic retinal vessel segmentation can be used to diagnose and monitor those diseases. Computer-aided algorithms are required for the analysis of progression of eye diseases. This study proposes a hybrid method that provides a combination of pre-processing and data augmentation methods with a deep learning model. Pre-processing was used to solve the irregular clarification problems and to form a contrast between the background and retinal blood vessels. After pre-processing step, a convolutional neural network (CNN) was designed and then trained for the extraction of retinal blood vessels. In the training phase, data augmentation was performed to improve training performance. The CNN was trained and tested in the DRIVE database, which is commonly used in retinal blood vessel segmentation and publicly available for studies in this area. Results showed that the proposed system extracted vessels with a sensitivity of 77.78%, specificity of 97,84%, precision of 84.17% and accuracy of 95.27%.

This study also compared the results to those of previous studies. The comparison showed that the proposed method is an efficient and successful method for extracting retinal blood vessels. Moreover, the pre-processing phases improved the system performance. We believe that the proposed method and results will make contribution to the literature.

     

A quantum mechanics-based algorithm for vessel segmentation in retinal images

Blood vessel segmentation is an important step in retinal image analysis. It is one of the steps required for computer-aided detection of ophthalmic diseases. In this paper, a novel quantum mechanics-based algorithm for retinal vessel segmentation is presented. The algorithm consists of three major steps. The first step is the preprocessing of the images to prepare the images for further processing. The second step is feature extraction where a set of four features is generated at each image pixel. These features are then combined using a nonlinear transformation for dimensionality reduction. The final step is applying a recently proposed quantum mechanics-based framework for image processing. In this step, pixels are mapped to quantum systems that are allowed to evolve from an initial state to a final state governed by Schrödinger’s equation. The evolution is controlled by the Hamiltonian operator which is a function of the extracted features at each pixel. A measurement step is consequently performed to determine whether the pixel belongs to vessel or non-vessel classes. Many functional forms of the Hamiltonian are proposed, and the best performing form was selected. The algorithm is tested on the publicly available DRIVE database. The average results for sensitivity, specificity, and accuracy are 80.29, 97.34, and 95.83 %, respectively. These results are compared to some recently published techniques showing the superior performance of the proposed method. Finally, the implementation of the algorithm on a quantum computer and the challenges facing this implementation are introduced.     

融合深层差异特征的RGB-T巢式语义分割网络

针对现存可见光—红外（RGB-T）图像语义分割模型分割性能不高的问题,提出一种基于深层差异特征互补融合的巢式分割网络。具体来说,网络的编码和解码部分通过多级稠密中间路径相连形成一个嵌套形式的结构,编码器的深浅特征通过多级路径供解码器实现密集的多尺度特征复用,另一方面多模态深层特征通过特征差异性融合策略增强其语义表达能力。实验结果表明,所提网络在MFNet数据集上实现了65.8%的平均准确率和54.7%的平均交并比,与其他先进RGB-T分割模型相比,具有更优越的分割能力。     

融合外观和运动特征的在线目标分割

目的 视频中的目标分割是计算机视觉领域的一个重要课题,有着极大的研究和应用价值。为此提出一种融合外观和运动特征的在线自动式目标分割方法。方法 首先,融合外观和运动特征进行目标点估计,结合上一帧的外观模型估计出当前帧的外观模型。其次,以超像素为节点构建马尔可夫随机场模型,结合外观模型和位置先验把分割问题转化为能量最小化问题,并通过Graph Cut进行优化求解。结果 最后,在两个数据集上与5种标准方法进行了对比分析,同时评估了本文方法的组成成分。本文算法在精度上至少比其他的目标分割算法提升了44.8%,且具有较高的分割效率。结论 本文通过融合外观与运动特征实现在线的目标分割,取得较好的分割结果,且该方法在复杂场景中也具有较好的鲁棒性。     

融合灰度和梯度信息的彩色细胞图像自动分割

为了开发血及骨髓涂片中白细胞自动分类及计算机辅助诊断系统,提出了一种融合灰度空间、彩色信息和数学形态学形态梯度信息的血细胞图像自动分割算法,以完成对白细胞（胞核和胞浆）的分割。在灰度空间,通过改进的迭代阈值分割算法,对白细胞的胞核进行了精确的定位和检出。通过彩色空间变换,有效地利用了图像中血细胞胞浆的颜色信息及先验知识,并且为了抑制过度分割,充分利用梯度信息,合理地对白细胞的胞核和胞浆进行了标记。在灰度梯度图像上提取血细胞的轮廓,并分别赋予不同的标记,表明数学形态梯度算法较传统的边缘检测算子具有更好的边缘提取能力。结果表明,胞核和胞浆的分割正确率分别为95.5％和92.6％,验证了该算法对彩色白细胞图像分割的有效性。     

Boosting sensitivity of a retinal vessel segmentation algorithm

Pattern Analysis and Applications - The correlation between retinal vessel structural changes and the progression of diseases such as diabetes, hypertension, and cardiovascular problems has been...     

Minimising retinal vessel artefacts in optical coherence tomography images

Optical coherence tomography (OCT) is commonly used to investigate the layers of the retina including retinal nerve fiber layer (RNFL) and retinal pigment epithelium (RPE). OCT images are altered by vessels on the retinal surface producing artefacts. We propose a new approach to compensate for these artefacts and enhance quality of OCT images. A total of 28 (20 normal and 8 glaucoma subjects) OCT images were obtained using Spectralis (Heidelberg, Germany). Shadows were detected along the image and compensated by the A-Scan intensity difference from surrounding non-affected areas. Images were then segmented and the area and thickness of RNFL and RPE were measured and compared. 10 subjects were tested twice to determine the effect of this on reproducibility of measurements. Shadow-suppressed images reflected the profile of the retinal layers more closely when assessed qualitatively, minimising distortion. The segmentation of RNFL and RPE thickness demonstrated a mean change of 2.4% ± 1 and 6% ± 1 from the original images. Much larger changes were observed in areas with vessels. Reproducibility of RNFL thickness was improved, specifically in the higher density vessel location, i.e. inferior and superior. Therefore, OCT images can be enhanced by an image processing procedure. Vessel artefacts may cause errors in assessment of RNFL thickness and are a source of variability, which has clinical implications for diseases such as glaucoma where subtle changes in RNFL need to be monitored accurately over time.     

基于Gabor小波的视网膜血管自动提取研究

针对视网膜血管网络灰度分布特征和区域结构特征,提出了一种基于Gabor小波的视网膜血管提取方法。采用Gabor滤波预处理以增强血管,用改进的自适应二值化方法对增强后的视网膜图像进行二值化处理,根据视网膜血管具有区域连通性的特征,并用形态学方法分割出最终的血管。为验证方法的有效性,对Hoover眼底图像库进行实验,结果表明该方法在细小血管的提取以及连续性、有效性方面都优于Hoover算法。     

基于核模糊C均值的眼底视网膜血管分割算法

针对眼底视网膜图像对比度差、背景不一致的问题,提出了一种基于核模糊C均值的眼底视网膜血管分割算法。首先采用二维高斯匹配滤波预处理以增强血管,然后采用核模糊C均值算法对增强眼底图像进行分割,并根据血管与各类隶属度的关系自动合并聚类图像得到最终的血管图像。实验结果表明,该算法分割结果令人满意。     

Automatic retinal layer segmentation in SD-OCT images with CSC guided by spatial characteristics

Multimedia Tools and Applications - Segmentation of retinal layers with central serious chorioretinopathy (CSC) in Spectral Domain Optical Coherence Tomography (SD-OCT) images is significant for...     

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。     

Retinal vessel segmentation employing ANN technique by Gabor and moment invariants-based features

Diabetic retinopathy (DR) is the major ophthalmic pathological cause for loss of eye sight due to changes in blood vessel structure. The retinal blood vessel morphology helps to identify the successive stages of a number of sight threatening diseases and thereby paves a way to classify its severity. This paper presents an automated retinal vessel segmentation technique using neural network, which can be used in computer analysis of retinal images, e.g., in automated screening for diabetic retinopathy. Furthermore, the algorithm proposed in this paper can be used for the analysis of vascular structures of the human retina. Changes in retinal vasculature are one of the main symptoms of diseases like hypertension and diabetes mellitus. Since the size of typical retinal vessel is only a few pixels wide, it is critical to obtain precise measurements of vascular width using automated retinal image analysis. This method segments each image pixel as vessel or nonvessel, which in turn, used for automatic recognition of the vasculature in retinal images. Retinal blood vessels are identified by means of a multilayer perceptron neural network, for which the inputs are derived from the Gabor and moment invariants-based features. Back propagation algorithm, which provides an efficient technique to change the weights in a feed forward network is utilized in our method. The performance of our technique is evaluated and tested on publicly available DRIVE database and we have obtained illustrative vessel segmentation results for those images.     

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.

     

基于微粒群算法的视网膜血管自动提取方法

针对视网膜血管网络灰度分布特征与结构特征,提出了将灰度-梯度共生矩阵最大熵与微粒群算法相结合的视网膜血管提取方法。采用Gabor滤波以增强血管图像,获取增强后视网膜图像的灰度-梯度共生矩阵,利用微粒群算法并结合灰度-梯度共生矩阵的最大熵方法进行阈值化处理,对图像进行二值化处理后根据视网膜血管具有区域连通性的特征,采用形态学方法分割出最终的血管。实验结果表明,该方法能有效地提取视网膜血管网络。     

A saliency and Gaussian net model for retinal vessel segmentation

Frontiers of Information Technology & Electronic Engineering - Retinal vessel segmentation is a significant problem in the analysis of fundus images. A novel deep learning structure called the...     

Ant Colony Optimization-based method for optic cup segmentation in retinal images

An accurate detection of the cup region in retinal images is necessary to obtain relevant measurements for glaucoma detection. In this work, we present an Ant Colony Optimization-based method for optic cup segmentation in retinal fundus images. The artificial agents will construct their solutions influenced by a heuristic that combines the intensity gradient of the optic disc area and the curvature of the vessels. On their own, the exploration capabilities of the agents are limited; however, by sharing the experience of the entire colony, they are capable of obtaining accurate cup segmentations, even in images with a weak or non-obvious pallor. This method has been tested with the RIM-ONE dataset, yielding an average overlapping error of 24.3% of the cup segmentation and an area under the curve (AUC) of 0.7957 using the cup to disc ratio for glaucoma assessment.     

融合时空多特征表示的无监督视频分割算法

针对视频分割的难点在于分割目标的无规则运动、快速变换的背景、目标外观的任意变化与形变等,提出了一种基于时空多特征表示的无监督视频分割算法,通过融合像素级、超像素级以及显著性三类特征设计由细粒度到粗粒度的稳健特征表示。首先,采用超像素分割对视频序列进行处理以提高运算效率,并设计图割算法进行快速求解;其次,利用光流法对相邻帧信息进行匹配,并通过K-D树算法实现最近邻搜索以引入各超像素的非局部时空颜色特征,从而增强分割的鲁棒性;然后,对采用超像素计算得到的分割结果,设计混合高斯模型进行完善;最后,引入图像的显著性特征,协同超像素分割与混合高斯模型的分割结果,设计投票获得更加准确的视频分割结果。实验结果表明,所提算法是一种稳健且有效的分割算法,其结果优于当前大部分无监督视频分割算法及部分半监督视频分割算法。