Retinal Image Preprocessing Research Articles

CGSX Ensemble: An Integrative Machine Learning and Deep Learning Approach for Improved Diabetic Retinopathy Classification

This research proposes an integrated approach for automated diabetic retinopathy (DR) diagnosis, leveraging a combination of machine learning and deep learning techniques to extract features and perform classification tasks effectively. Through preprocessing of retinal images to enhance features and mitigate noise, two distinct methodologies are employed: machine learning feature extraction, targeting texture features like Gray-Level Co-occurrence Matrix (GLCM) and Gray-Level Run Length Matrix (GLRLM), and deep learning feature extraction, utilizing pre-trained convolutional neural networks (CNNs) such as VGG, ResNet, or Inception. Following feature extraction, various classifiers, including Support Vector Machines (SVM), Random Forests, and Gradient Boosting Machines, are trained on the extracted features for DR classification. Alternatively, deep learning classifiers like CNNs or recurrent neural networks (RNNs) may be trained directly on the extracted features or on raw images. This comprehensive framework shows promising potential to improve the accuracy and efficiency of diabetic retinopathy (DR) diagnosis, enabling timely intervention and management of this vision-threatening condition.

Retinal image preprocessing techniques: Acquisition and cleaning perspective

AbstractImage preprocessing is a method to transform raw image data into clean image data. The objective of preprocessing is to improve the image data by suppressing undesired distortions. Enhancement of some image features which are relevant for further processing of image and analysis task is also done in preprocessing. Screening and diagnosis of various eye diseases like diabetic retinopathy, Choroidal Neovascularization(CNV), DRUSEN, etc. are possible using digital retinal images. This paper aims to provide a better understanding and knowledge of the computer algorithms used for retinal image preprocessing. In this paper, various image preprocessing techniques are incorporated such as color correction, color space selection, noise reduction, and contrast enhancement on retinal images. Retinal blood vessels are better seen in Green color space instead of Red or Blue color space. Noise reduction through Block matching and 3D(BM3D) techniques show a significant result as compared to Total Variation Filter (TVF) and Bilateral Filter (BLF). Contrast enhancement through Contrast Limited Adaptive Histogram Equalization (CLAHE) outperforms Global Equalization (GE) or Adaptive Histogram Equalization (AHE). Evaluation parameters such as Mean square error, Peak Signal Noise ratio, Structured similarity index measures, and Normalized root mean square error values for BM3D noise filtering are 0.0029, 25.3370, 0.6839 and 0.0998 respectively which shows that BM3D outperforms the others.

A Retinal Lesion Detection of Diabetic Retinopathy

Diabetic retinopathy (DR) is the most common cause of vision loss among people with diabetes and leading to the cause of blindness. Microaneurysms (MAs) are primary lesion of Diabetic retinopathy, so their detection can give time to prevent further vision loss. Hemorrhages (HMs) and exudates (EXs) are the other type of lesions occurs during Diabetic retinopathy. The Retinal lesion detection consists of retinal image preprocessing, Optic disc detection and removal, Blood vessel segmentation, Candidate Lesion detection, Feature extraction, Classification and post processing . Publicly available DiaretDB1 dataset is used for performance evaluation.

Improved retinal fundus image quality with hybrid image filter and enhanced contrast limited adaptive histogram equalization

Retinal fundus image preprocessing has contributed extensively to medical image analysis and retrieval of appropriate images. The acquired retinal images are usually messy and come from different sources. They need to be standardized and cleaned up. Retinal image preprocessing enables the improvement of retinal image quality and enhances the image features that are required for processing. The success of the retinal image diagnosis for early prediction of Diabetic Retinopathy (DR) depends on the reliability of preprocessing. The automatic preprocessing of color retinal fundus images without affecting the image quality is still challenging. Retinal images often have issues such as low contrast intensity, uneven light intensity, blurring, noise disturbances, sensor system that lack of focus, low contrast, irregular shapes with high variability, object movement, ill-defined boundaries, heterogeneous pixel intensities and the annotation of medical images to support diagnosis. In this work, issues such as noisy/ill in defined boundaries, uneven light intensity, low contrast, and blurring of images in the retinal fundus images are addressed with the proposed method. The results of the proposed method are reliable, contrast enhanced, edge preserved preprocessed images for given color input images.

Pre-processing of Retinal Images for Removal of Outliers

Early diagnosis of diseases related with retina such as glaucoma is of utmost importance in current scenario as it is the second most prevailing cause of irreversible blindness over the world and is expected to increase further in near future. It is commonly diagnosed using retinal images which are acquired by digital fundus cameras. But the acquired images may be prone to certain outliers that create hindrance in diagnosis of glaucoma by tempering the accuracy. These outliers include retinal vessels, low contrast of images and uneven illumination that deteriorates the performance of disc and cup segmentation which are the key indicators to diagnose glaucoma. Thus, pre-processing of retinal images to remove outliers plays a significant role in diagnosis. This paper presents an approach for pre-processing the retinal fundus image followed by its comparison with state of the art. Based on the experimental analysis the performance of the proposed approach is found to be better than the state of the art based on the analysis using metrics such as peak signal to ratio, mean square error and structural similarity index. Further, the proposed approach has been compared with state of the art using metrics such as Jaccard index and dice similarity on the basis of segmentation outcomes on different pre-processing approaches.

Pre-processing of retinal images acquired from digital fundus cameras for improved performance of diagnostic tools in biomedical engineering

Early diagnosis of abnormality related to retina such as glaucoma is of utmost significance as it is the common cause of permanent blindness across the world and is predicted to rise further in near future. It is usually diagnosed using fundus images acquired from digital fundus cameras. But the images acquired are prone to some noises that create alternations in outputs of diagnosis by tempering the accuracy. These noises include vessels in the retina, lower contrast of images and irregular illumination that depreciates the performance of cup and disc segmentation which are crucial to diagnose glaucoma. Thus, removal of outliers to pre-process retinal images plays an important role in diagnostics. This manuscript presents a hybrid technique for removal of outliers from retinal images. The suggested approach can be embedded in digital cameras to filter out the outliers and improve the performance of diagnostic tools.

Detection and Segmentation of Retinal Lesions in Retcam 3 Images Based on Active Contours Driven by Statistical Local Features

Clinical retinal image analysis is an import aspect of clinical diagnosis in ophthalmology. Retinopathy of Prematurity (ROP) represents one of the most severe retinal disorders in prematurely born infants. One of the ROP clinical signs is the presence of retinal lesions endangering the vision system. Unfortunately, the stage and progress of these findings is often only subjectively estimated. A procedure such as this is undoubtedly linked to subjective inaccuracies depending on the experience of the ophthalmologist. In our study, a fully autonomous segmentation algorithm to model retinal lesions found using RetCam 3 is proposed. The proposed method used a combination of retinal image preprocessing and active contours for retinal lesion segmentation. Based on this procedure, a binary model of retinal lesions that allowed retinal lesions to be classified from a retinal image background was obtained. Another important aspect of the model was feature extraction. These features reliably and automatically described the development stage of an individual lesion. A complex procedure such as this has significant implications for ophthalmic clinical practice in substituting manual clinical procedures and improving the accuracy of routine clinical decisions.

Stroke Prognosis through Retinal Image Analysis

Many eye diseases as well as systemic diseases usually used to manifest in the retina. The innovations in the field of retinal imaging have paved the way to the development of tools for assisting physicians in stroke prognosis. Stroke is one of the leading causes of adult disability in most of the developing countries. Diagnosis of stroke during the initial stage is crucial for timely prevention and cure. Retinal imaging provides a non invasive technique of predicting the possibility of stroke. This research work focuses on the prediction of retinal ischemia from retinal fundus images and thereby predicting the occurance of stroke. Preprocessing of retinal images is done by retinex processing and morphological operations are done to remove noisy background. Branching points are detected and various features like major axis length, mean diameter, orientation, eccentricity, fractal dimension and tortuosity for the branching blood vessels are computed. This has been compared for various diseases like diabetic retinopathy, hypertensive retinopathy and retinal ischemia against a set of healthy retinal images. Classification has been implemented by Artificial Neural Networks which gives an accuracy of 89 % and the results proved to be promising.

Reduction of False Microaneurysms in Retinal Fundus Images using Fuzzy C-Means Clustering in terms NLM Anisotropic Filter

The identification of MAs is an important phase in the research and grading of suffering from diabetes retinopathy. We present clustering strategy to identify the microaneurysms from the optic disk and cup in the retinal fundus pictures. Fuzzy C-Means (FCM) Clustering is used for clustering the information in which the information factors are grouped with different account level. The first and major phase is preprocessing function, in which the optic cup and disk of the feedback picture is being turned. Originally the optic hard disk is turned in some position and the range between the information factors is calculated and a group is established in accordance with the centroid. For retrieving micro aneurysms in all retinal images in our previous work we used SVM Classification filter in Fuzzy C-Means Clustering. In this paper we propose an effective filtering technique for micro aneurysms detection in retinal image preprocessing. Instead of SVM Filtering technique we used NLM in terms of Anisotropic Filter to process retinal images. Tested on the various simulated retina data repositories combining rotation and scaling, the developed method presents good results and shows robustness to rotations and scale changes.

A comparative evaluation of diabetic retinal vascular structures using edge detection techniques

Diabetic retinopathy (DR) is a major cause of loss of vision in diabetes which occurs due to vascular changes in the retina. Automated image processing has the potential to assist in the early detection of diabetes, by detecting changes in blood vessel patterns in the retina. Accurate extraction of retinal blood vessels is an important task in computer aided diagnosis of DR. The edge detection technique has been greatly benefited in interpreting the information contents in the retinal blood vessel. The pre-processing of retinal image may help in detecting the early stage of symptoms in DR. In this article we have detected the abnormalities in retinal blood vessels by Sobel and Canny edge detector and the results are compared in terms of different image parameters and histogram error. The Canny operator is found to have higher peak signal-to-noise ratio (PSNR) and normalised cross-correlation (NK) with less value of mean square error (MSE), average difference (AD), and structural content (SC). The histogram error is also found to be less in the Canny operator (0.0015) than the Sobel operator (0.014). Thus, we may conclude that the Canny operator is more accurate in detecting even tiny blood vessels compared to Sobel operator in diabetic retinal image.

Retinal Image Preprocessing: Background and Noise Segmentation

Retinal Image Preprocessing: Background and Noise Segmentation

Retinal Image Preprocessing: Background and Noise Segmentation

Medical imaging is very popular research area these days and includes computer aided diagnosis of different diseases by taking digital images as input. Digital retinal images are used for the screening and diagnosis of diabetic retinopathy, an eye disease. An automated system for the diagnosis of diabetic retinopathy should highlight all signs of disease present in the image and in order to improve the accuracy of the system, the retinal image quality must be improved. In this article, we present a method to improve the quality of input retinal image and we consider this method as a preprocessing step in automated diagnosis of diabetic retinopathy. The preprocessing consists of background estimation and noise removal from retinal image by applying coarse and fine segmentation. We perform extensive results to check the validity of proposed preprocessing technique using standard fundus image database.

Retinal Image Preprocessing: Background and Noise Segmentation

Retinal images are used for the automated screening and diagnosis of diabetic retinopathy. The retinal image quality must be improved for the detection of features and abnormalities and for this purpose preprocessing of retinal images is vital. In this paper, we present a novel automated approach for preprocessing of colored retinal images. The proposed technique improves the quality of input retinal image by separating the background and noisy area from the overall image. It contains coarse segmentation and fine segmentation. Standard retinal images databases Diaretdb0, Diaretdb1, DRIVE and STARE are used to test the validation of our preprocessing technique. The experimental results show the validity of proposed preprocessing technique. DOI: http://dx.doi.org/10.11591/telkomnika.v10i3.615

Automated Detection of Dark and Bright Lesions in Retinal Images for Early Detection of Diabetic Retinopathy

There is an ever-increasing interest in the development of automatic medical diagnosis systems due to the advancement in computing technology and also to improve the service by medical community. The knowledge about health and disease is required for reliable and accurate medical diagnosis. Diabetic Retinopathy (DR) is one of the most common causes of blindness and it can be prevented if detected and treated early. DR has different signs and the most distinctive are microaneurysm and haemorrhage which are dark lesions and hard exudates and cotton wool spots which are bright lesions. Location and structure of blood vessels and optic disk play important role in accurate detection and classification of dark and bright lesions for early detection of DR. In this article, we propose a computer aided system for the early detection of DR. The article presents algorithms for retinal image preprocessing, blood vessel enhancement and segmentation and optic disk localization and detection which eventually lead to detection of different DR lesions using proposed hybrid fuzzy classifier. The developed methods are tested on four different publicly available databases. The presented methods are compared with recently published methods and the results show that presented methods outperform all others.

The preprocessing of retinal images for the detection of fluorescein leakage

Images of the human retina are routinely used in clinical practice for the diagnosis and management of eye disease. Increased permeability of retinal blood vessels, which is a clinically significant feature, can be visualized with a process known as fluorescein angiography as leakage of fluorescence dye into the surrounding tissues. Analyses of such images can be quantified but significant degradation of images due to uneven illumination or occluded optical pathways is often incurred during image capture. We describe a procedure to restore fluorescein angiographic retinal images so that quantitative computation can be reliably performed. Analysis of the image acquisition system reveals that captured images are composed of two functions, one describing the true underlying image and the other the degradation incurred. These two functions are independent of one another and it is possible to estimate the degradation from an isolated captured image and restore it appropriately. Any leakage of fluorescein dye is then detected by analysing the restored angiographic sequence over time and finding areas of the image that do not have the usual decrease in fluorescence intensity.