Content uploaded by Ali Allam
Author content
All content in this area was uploaded by Ali Allam on Nov 01, 2017
Content may be subject to copyright.
A preview of the PDF is not available
Automatic Detection of Landmarks and Abnormalities in Eye Fundus Images
Diabetic retinopathy is an eye related complication of diabetes mellitus caused due to damage to the retinal blood vessels, resulting in micro-aneurysms, hemorrhages and exudates. DR is asymptomatic, necessitating the development of an automated screening system. Exudates appear in the later stages of diabetic retinopathy and their presence would classify the disease as moderate or severe. In developing countries, where access to training data is limited, there is a greater need for analytical methods than machine learning techniques. The proposed method uses the orientation scores of the retinal image to detect exudates. The 2D orientation score framework, proposed by Duits et al., inspired by the visual system of mammals, is a mapping which assigns the position and orientation angle of each pixel to a complex scalar and has been so far used to detect vasculature tree on the retina. This paper proposes the use of orientation scores to form an orientation enhanced image, from which a binary mask of exudates can be obtained by intensity thresholding. It achieves a sensitivity of 86.2% and a specificity of 85% on images of DIARETDB1 database.
This paper provides a novel approach for the problem of detecting the yellowish lesions in the eye fundus images, such as hard and soft exudates, in a fully-automated manner. To solve this problem of segmenting exudates automatically, the fundus image was first converted into the L*a*b* color space to decouple the chromaticity information of the image. Next, the fundus image was partitioned into five disjoint clusters based on this information via the unsupervised k-means algorithm. Among the clustered images, the one having the brightest average intensity was chosen to be the best cluster containing all the bright yellowish pixels. Using this cluster, a threshold value was estimated via statistic-based metrics and subsequently applied to remove any non-bright clustered pixels and preserve only the relatively bright ones within the image. Finally, the optic disc was eliminated from the thresholded image, leaving out only the bright abnormalities. This approach was evaluated over a total of 1419 images retrieved from three heterogeneous datasets: DIARETDB0, DIARETDB1 and MESSIDOR. The proposed segmentation algorithm was fully-automated, non-customized, simple and straightforward, regardless of the heterogeneity of the datasets. The proposed system correctly detected the bright abnormalities achieving an average sensitivity and specificity of 85.08% and 56.77%, respectively.
Retinal microaneurysms (MAs) are the earliest clinically observable lesions of diabetic retinopathy. Reliable automated MAs detection is thus critical for early diagnosis of diabetic retinopathy. This paper proposes a novel method for the automated MAs detection in color fundus images based on gradient vector analysis and class imbalance classification, which is composed of two stages, i.e. candidate MAs extraction and classification. In the first stage, a candidate MAs extraction algorithm is devised by analyzing the gradient field of the image, in which a multi-scale log condition number map is computed based on the gradient vectors for vessel removal, and then the candidate MAs are localized according to the second order directional derivatives computed in different directions. Due to the complexity of fundus image, besides a small number of true MAs, there are also a large amount of non-MAs in the extracted candidates. Classifying the true MAs and the non-MAs is an extremely class imbalanced classification problem. Therefore, in the second stage, several types of features including geometry, contrast, intensity, edge, texture, region descriptors and other features are extracted from the candidate MAs and a class imbalance classifier, i.e., RUSBoost, is trained for the MAs classification. With the Retinopathy Online Challenge (ROC) criterion, the proposed method achieves an average sensitivity of 0.433 at 1/8, 1/4, 1/2, 1, 2, 4 and 8 false positives per image on the ROC database, which is comparable with the state-of-the-art approaches, and 0.321 on the DiaRetDB1 V2.1 database, which outperforms the state-of-the-art approaches.
This book provides a modern, self-contained introduction to digital image processing. We designed this book to be used both by learners desiring a firm foundation on which to build as well as practitioners in search of detailed analysis and transparent implementations of the most important techniques. This is the third
English edition of the original German-language book, which has been widely used by
* Scientists and engineers who use image processing as a tool and wish to develop a deeper understanding and create custom solutions to imaging problems in their field;
* IT professionals in search of a self-study course featuring easily adaptable code and completely worked out examples, enabling them to be productive right away;
* Faculty and students desiring an example-rich introductory textbook suitable for an advanced undergraduate or graduate level course that features exercises, projects, and examples that have been honed during quite some years of experience teaching this material.
While we concentrate on practical applications and concrete implementations, we do so without glossing over the important formal details and mathematics necessary for a deeper understanding of the algorithms.
In preparing this text, we started from the premise that simply creating a recipe book of imaging solutions would not provide the deeper understanding needed to apply these techniques to novel problems, so instead our solutions are developed stepwise from three different perspectives: in mathematical form, as abstract pseudocode algorithms, and as complete Java programs. We use a common notation to intertwine all three perspectives - providing multiple, but intimately linked, views of problems and their solution.
Background and objective:
Diabetic retinopathy is one of the leading disabling chronic diseases and one of the leading causes of preventable blindness in developed world. Early diagnosis of diabetic retinopathy enables timely treatment and in order to achieve it a major effort will have to be invested into automated population screening programs. Detection of exudates in color fundus photographs is very important for early diagnosis of diabetic retinopathy.
Methods:
We use deep convolutional neural networks for exudate detection. In order to incorporate high level anatomical knowledge about potential exudate locations, output of the convolutional neural network is combined with the output of the optic disc detection and vessel detection procedures.
Results:
In the validation step using a manually segmented image database we obtain a maximum F1 measure of 0.78.
Conclusions:
As manually segmenting and counting exudate areas is a tedious task, having a reliable automated output, such as automated segmentation using convolutional neural networks in combination with other landmark detectors, is an important step in creating automated screening programs for early detection of diabetic retinopathy.
The automatic exudate segmentation in colour retinal fundus images is an important task in computer aided diagnosis and screening systems for diabetic retinopathy. In this paper, we present a location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images, which includes three stages: anatomic structure removal, exudate location and exudate segmentation. In anatomic structure removal stage, matched filters based main vessels segmentation method and a saliency based optic disk segmentation method are proposed. The main vessel and optic disk are then removed to eliminate the adverse affects that they bring to the second stage. In the location stage, we learn a random forest classifier to classify patches into two classes: exudate patches and exudate-free patches, in which the histograms of completed local binary patterns are extracted to describe the texture structures of the patches. Finally, the local variance, the size prior about the exudate regions and the local contrast prior are used to segment the exudate regions out from patches which are classified as exudate patches in the location stage. We evaluate our method both at exudate-level and image-level. For exudate-level evaluation, we test our method on e-ophtha EX dataset, which provides pixel level annotation from the specialists. The experimental results show that our method achieves 76% in sensitivity and 75% in positive prediction value(PPV), which both outperform the state of the art methods significantly. For image-level evaluation, we test our method on DiaRetDB1, and achieve competitive performance compared to the state of the art methods.
Glaucoma\'s irreversibility, lacking of glaucoma specialists and patient unawareness demand for an economic and effective glaucoma diagnosis system for screening. In this study we explore feature selection (FS) technologies to identify the most essential parameters for automatic glaucoma diagnosis.
Methods: We compose feature space from heterogeneous data sources, i.e., retinal image and eye screening data. A feature selection framework is proposed by exploring multiple feature ranking schemes and a wide range of supervised learners. The optimal feature set is derived automatically from the performance curve smoothed by measurement score regression.
Results: Under the proposed framework, the optimal feature set obtained using mRMR (minimum Redundancy Maximum Relevance) scheme contains only 1/4 of the original features. The classifiers trained upon the optimal feature set are more efficient with better performance in terms of Accuracy and F-score. A detailed investigation on the features in the optimal set indicates that they can be the essential parameters for glaucoma mass screening and image segmentation.
Conclusions: An intelligent Computer-aid-diagnosis (CAD) model is constructed for automatic disease diagnosis. The effectiveness of the model is demonstrated in our glaucoma study based on heterogeneous data sets. The effort not only improves the discriminative power, but also facilitates a better understanding of CAD process and may ease the data collection in glaucoma mass screening.
Methods:
Candidate objects are first located by applying a dark object filtering process. Their cross-section profiles along multiple directions are processed through singular spectrum analysis. The correlation coefficient between each processed profile and a typical microaneurysm profile is measured and used as a scale factor to adjust the shape of the candidate profile. This is to increase the difference in their profiles between true microaneurysms and other non-microaneurysm candidates. A set of statistical features of those profiles is then extracted for a K-Nearest Neighbour classifier.
Results:
Experiments show that by applying this process, microaneurysms can be separated well from the retinal background, the most common interfering objects and artefacts.
Conclusion:
The results have demonstrated the robustness of the approach when testing on large scale datasets with clinically acceptable sensitivity and specificity.
Significance:
The approach proposed in the evaluated system has great potential when used in an automated diabetic retinopathy screening tool or for large scale eye epidemiology studies.
