scholarly journals Efficient Segmentation and Registration of Retinal Image Using Gumble Probability Distribution and BRISK Feature

2020 ◽  
Vol 37 (5) ◽  
pp. 855-864
Author(s):  
Nagendra Pratap Singh ◽  
Vibhav Prakash Singh
Keyword(s):  
Retinal Image ◽  
Matched Filter ◽  
Computation Time ◽  
Retinal Vessel ◽  
Retinal Images ◽  
Feature Descriptor ◽  
Retinal Diseases ◽  
Vessel Structure ◽  
Feature Based ◽  
Image Pairs

The registration of segmented retinal images is mainly used for the diagnosis of various diseases such as glaucoma, diabetes, and hypertension, etc. These retinal diseases depend on the retinal vessel structure. The fast and accurate registration of segmented retinal images helps to identify the changes in vessels and the diagnosis of the diseases. This paper presents a novel binary robust invariant scalable key point (BRISK) feature-based segmented retinal image registration approach. The BRISK framework is an efficient keypoint detection, description, and matching approach. The proposed approach contains three steps, namely, pre-processing, segmentation using matched filter based Gumbel pdf, and BRISK framework for registration of segmented source and target retinal images. The effectiveness of the proposed approach is demonstrated by evaluating the normalized cross-correlation of image pairs. Based on the experimental analysis, it has been observed that the performance of the proposed approach is better in both aspect, registration performance as well as computation time with respect to SURF and Harris partial intensity invariant feature descriptor based registration.

scholarly journals Feature-Based Retinal Image Registration Using D-Saddle Feature

2017 ◽  
Vol 2017 ◽  
pp. 1-15 ◽  
Author(s):  
Roziana Ramli ◽  
Mohd Yamani Idna Idris ◽  
Khairunnisa Hasikin ◽  
Noor Khairiah A. Karim ◽  
Ainuddin Wahid Abdul Wahab ◽  
...  
Keyword(s):  
Image Registration ◽  
Retinal Image ◽  
Retinal Diseases ◽  
Feature Points ◽  
Registration Accuracy ◽  
Gaussian Pyramid ◽  
Difference Of Gaussian ◽  
Lower Success Rate ◽  
Feature Based ◽  
Image Pairs

Retinal image registration is important to assist diagnosis and monitor retinal diseases, such as diabetic retinopathy and glaucoma. However, registering retinal images for various registration applications requires the detection and distribution of feature points on the low-quality region that consists of vessels of varying contrast and sizes. A recent feature detector known as Saddle detects feature points on vessels that are poorly distributed and densely positioned on strong contrast vessels. Therefore, we propose a multiresolution difference of Gaussian pyramid with Saddle detector (D-Saddle) to detect feature points on the low-quality region that consists of vessels with varying contrast and sizes. D-Saddle is tested on Fundus Image Registration (FIRE) Dataset that consists of 134 retinal image pairs. Experimental results show that D-Saddle successfully registered 43% of retinal image pairs with average registration accuracy of 2.329 pixels while a lower success rate is observed in other four state-of-the-art retinal image registration methods GDB-ICP (28%), Harris-PIIFD (4%), H-M (16%), and Saddle (16%). Furthermore, the registration accuracy of D-Saddle has the weakest correlation (Spearman) with the intensity uniformity metric among all methods. Finally, the paired t-test shows that D-Saddle significantly improved the overall registration accuracy of the original Saddle.

scholarly journals A Two-Stage GAN for High-Resolution Retinal Image Generation and Segmentation

Electronics ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 60
Author(s):  
Paolo Andreini ◽  
Giorgio Ciano ◽  
Simone Bonechi ◽  
Caterina Graziani ◽  
Veronica Lachi ◽  
...  
Keyword(s):  
High Resolution ◽  
Retinal Vessel ◽  
Real Data ◽  
Generative Adversarial Networks ◽  
Retinal Images ◽  
Two Stage ◽  
Generation Task ◽  
Training Samples ◽  
Vessel Structure ◽  
Semantic Label

In this paper, we use Generative Adversarial Networks (GANs) to synthesize high-quality retinal images along with the corresponding semantic label-maps, instead of real images during training of a segmentation network. Different from other previous proposals, we employ a two-step approach: first, a progressively growing GAN is trained to generate the semantic label-maps, which describes the blood vessel structure (i.e., the vasculature); second, an image-to-image translation approach is used to obtain realistic retinal images from the generated vasculature. The adoption of a two-stage process simplifies the generation task, so that the network training requires fewer images with consequent lower memory usage. Moreover, learning is effective, and with only a handful of training samples, our approach generates realistic high-resolution images, which can be successfully used to enlarge small available datasets. Comparable results were obtained by employing only synthetic images in place of real data during training. The practical viability of the proposed approach was demonstrated on two well-established benchmark sets for retinal vessel segmentation—both containing a very small number of training samples—obtaining better performance with respect to state-of-the-art techniques.

scholarly journals RFARN: Retinal vessel segmentation based on reverse fusion attention residual network

PLoS ONE ◽  
2021 ◽  
Vol 16 (12) ◽  
pp. e0257256
Author(s):  
Wenhuan Liu ◽  
Yun Jiang ◽  
Jingyao Zhang ◽  
Zeqi Ma
Keyword(s):  
Retinal Image ◽  
Complex Structure ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Fundus Images ◽  
Residual Network ◽  
Global Features ◽  
Spatial Dimensions ◽  
Vessel Structure ◽  
Retinal Vessel Segmentation

Accurate segmentation of retinal vessels is critical to the mechanism, diagnosis, and treatment of many ocular pathologies. Due to the poor contrast and inhomogeneous background of fundus imaging and the complex structure of retinal fundus images, this makes accurate segmentation of blood vessels from retinal images still challenging. In this paper, we propose an effective framework for retinal vascular segmentation, which is innovative mainly in the retinal image pre-processing stage and segmentation stage. First, we perform image enhancement on three publicly available fundus datasets based on the multiscale retinex with color restoration (MSRCR) method, which effectively suppresses noise and highlights the vessel structure creating a good basis for the segmentation phase. The processed fundus images are then fed into an effective Reverse Fusion Attention Residual Network (RFARN) for training to achieve more accurate retinal vessel segmentation. In the RFARN, we use Reverse Channel Attention Module (RCAM) and Reverse Spatial Attention Module (RSAM) to highlight the shallow details of the channel and spatial dimensions. And RCAM and RSAM are used to achieve effective fusion of deep local features with shallow global features to ensure the continuity and integrity of the segmented vessels. In the experimental results for the DRIVE, STARE and CHASE datasets, the evaluation metrics were 0.9712, 0.9822 and 0.9780 for accuracy (Acc), 0.8788, 0.8874 and 0.8352 for sensitivity (Se), 0.9803, 0.9891 and 0.9890 for specificity (Sp), area under the ROC curve(AUC) was 0.9910, 0.9952 and 0.9904, and the F1-Score was 0.8453, 0.8707 and 0.8185. In comparison with existing retinal image segmentation methods, e.g. UNet, R2UNet, DUNet, HAnet, Sine-Net, FANet, etc., our method in three fundus datasets achieved better vessel segmentation performance and results.

scholarly journals Retinal Image Enhancement Based on Contrast, Luminosity Adjustment and MSC

2019 ◽  
Vol 8 (2S11) ◽  
pp. 2572-2574
Keyword(s):  
Image Enhancement ◽  
Sparse Coding ◽  
Retinal Vessel ◽  
Poor Quality ◽  
The Other ◽  
Retinal Images ◽  
Retinal Diseases ◽  
Medical Studies ◽  
Basic Quality

Retinal images have been widely used by ophthalmologists for detecting the retinal diseases before-hand and diagnosing them suitably. Old age macular degeneration, diabetic retinopathy and glaucoma are some examples of these diseases. However, poor quality of the image due to inadvertent circumstances limits the ability of the ophthalmologists to study the image. This paper hereby proposes an algorithm that is used to obtain clearer images by performing contrast and luminosity adjustment that enhances the basic quality of the clicked image. Following this, Multi-dictionary Sparse Coding (MSC) is carried out on the image to obtain the retinal vessel structures and miniscule details. Amount of Image enhancement is calculated by measuring the improvement after each stage of operation on the image. The image's quality is found to be much better compared to the other methods and thus can be suggested to the ophthalmologists for conducting the further medical studies conveniently.

scholarly journals Ultra low bitrate retinal image compression using integer lifting scheme and subband encoder

2021 ◽  
Vol 24 (1) ◽  
pp. 295
Author(s):  
Yassine Habchi ◽  
Ameur Fethi Aimer ◽  
Mohammed Beladgham ◽  
Riyadh Bouddou
Keyword(s):  
Retinal Image ◽  
Processing Time ◽  
Lifting Scheme ◽  
Large Data ◽  
Set Partitioning ◽  
Retinal Images ◽  
Retinal Diseases ◽  
Important Indicator ◽  
Hierarchical Trees ◽  
Difficult Cases

Recently, ophthalmic clinics have seen many complaints related to retinal diseases. The degree of clarity of the blood vessels (BV) in the eye can be an important indicator of some diseases affecting the retina such as diabetic retinopathy. To diagnose it, we need to intervene more than a medical team, especially in some difficult cases, through the exchange of medical images obtained by photography. This method has contributed significantly to the production of large data that can quickly saturate transmission, storage systems and increase processing time, so the need to compress images efficiently without modifying the content before transmission represents a major challenge. This paper provides an effective method for compressing color retinal images (CRI), which relies on the use of an integer lifting scheme (ILS) based on cohen daubechies-feaveau wavelet (CDFW9/7) and the set partitioning in hierarchical trees (SPIHT) to encode large coefficients. The obtained results demonstrate that the suggested method reduce algorithmic complexity, improve the retinal image quality and achieves high objective parameters values for ultra-low bitrate compared to the conventional methods.

scholarly journals Mathematical Morphology based Retinal Image Blood Vessels Segmentation

2019 ◽  
Vol 8 (12) ◽  
pp. 2914-2920
Keyword(s):  
Blood Vessels ◽  
Mathematical Morphology ◽  
Retinal Image ◽  
Retinal Vessel ◽  
Morphological Processing ◽  
Evaluation Metrics ◽  
Health Study ◽  
Retinal Images ◽  
Suggested Approach ◽  
Sensitivity Specificity

It is necessary to verify the state of blood vessel network in the retina for diagnosing various issues associated with eyes. In this research paper, an involuntary retinal vessel segmentation using mathematical morphology is proposed. The contrast of the retinal images is enhanced by contrast limited adaptive histogram equalisation technique. Ten blood vessels of the enhanced retinal image are detected using morphological processing. The hysteresis thresholding is applied on the blood vessels detected image to remove the unwanted back ground detail. Finally the properly segmented binary image of the retinal vessel is obtained using post processing process. Results of the presented method are verified by using most widely used for benchmarking retinal image databases such as, Child Heart and Health Study in England (CHASE_DB1) and Digital Retinal Images for Vessel Extraction (DRIVE) database by computing the evaluation metrics such as sensitivity, specificity, accuracy and precision. The better evaluation metrics achieved for the DRIVE dataset are 0.7493, 0.9687, 0.9524 and 0.6590, and the worst values are 0.6621, 0.9411, 0.9137 and 0.5491. The best evaluation metrics values for the CHASE_DB1 dataset are 0.5058, 0.8947, 0.9382 and 0.8856, and the worst values are 0.5639, 0.9581, 0.9137 and 0.7110. The investigational results show that the suggested approach provides the excellent accuracy in comparison with other approaches

scholarly journals Cloud Detection Based on High Resolution Stereo Pairs of the Geostationary Meteosat Images

2020 ◽  
Vol 12 (3) ◽  
pp. 371 ◽  
Author(s):  
Sahar Dehnavi ◽  
Yasser Maghsoudi ◽  
Klemen Zakšek ◽  
Mohammad Javad Valadan Zoej ◽  
Gunther Seckmeyer ◽  
...  
Keyword(s):  
High Resolution ◽  
Matched Filter ◽  
Stereo Pair ◽  
Cloud Detection ◽  
Operating Characteristics ◽  
Detection Techniques ◽  
Infrared Imager ◽  
Detection Approach ◽  
Considerable Impact ◽  
Image Pairs

Due to the considerable impact of clouds on the energy balance in the atmosphere and on the earth surface, they are of great importance for various applications in meteorology or remote sensing. An important aspect of the cloud research studies is the detection of cloudy pixels from the processing of satellite images. In this research, we investigated a stereographic method on a new set of Meteosat images, namely the combination of the high resolution visible (HRV) channel of the Meteosat-8 Indian Ocean Data Coverage (IODC) as a stereo pair with the HRV channel of the Meteosat Second Generation (MSG) Meteosat-10 image at 0° E. In addition, an approach based on the outputs from stereo analysis was proposed to detect cloudy pixels. This approach is introduced with a 2D-scatterplot based on the parallax value and the minimum intersection distance. The mentioned scatterplot was applied to determine/detect cloudy pixels in various image subsets with different amounts of cloud cover. Apart from the general advantage of the applied stereography method, which only depends on geometric relationships, the cloud detection results are also improved because: (1) The stereo pair is the HRV bands of the Spinning Enhanced Visible and InfraRed Imager (SEVIRI) sensor, with the highest spatial resolution available from the Meteosat geostationary platform; and (2) the time difference between the image pairs is nearly 5 s, which improves the matching results and also decreases the effect of cloud movements. In order to prove this improvement, the results of this stereo-based approach were compared with three different reflectance-based target detection techniques, including the adaptive coherent estimator (ACE), constrained energy minimization (CEM), and matched filter (MF). The comparison of the receiver operating characteristics (ROC) detection curves and the area under these curves (AUC) showed better detection results with the proposed method. The AUC value was 0.79, 0.90, 0.90, and 0.93 respectively for ACE, CEM, MF, and the proposed stereo-based detection approach. The results of this research shall enable a more realistic modelling of down-welling solar irradiance in the future.

scholarly journals Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases

2021 ◽  
Vol 11 (5) ◽  
pp. 321
Author(s):  
Kyoung Min Kim ◽  
Tae-Young Heo ◽  
Aesul Kim ◽  
Joohee Kim ◽  
Kyu Jin Han ◽  
...  
Keyword(s):  
Network Models ◽  
Retinal Disease ◽  
Age Related Macular Degeneration ◽  
Diagnostic Tools ◽  
Retinal Images ◽  
Dense Layer ◽  
Retinal Diseases ◽  
Fundus Image ◽  
Neural Network Models ◽  
Age Related

Artificial intelligence (AI)-based diagnostic tools have been accepted in ophthalmology. The use of retinal images, such as fundus photographs, is a promising approach for the development of AI-based diagnostic platforms. Retinal pathologies usually occur in a broad spectrum of eye diseases, including neovascular or dry age-related macular degeneration, epiretinal membrane, rhegmatogenous retinal detachment, retinitis pigmentosa, macular hole, retinal vein occlusions, and diabetic retinopathy. Here, we report a fundus image-based AI model for differential diagnosis of retinal diseases. We classified retinal images with three convolutional neural network models: ResNet50, VGG19, and Inception v3. Furthermore, the performance of several dense (fully connected) layers was compared. The prediction accuracy for diagnosis of nine classes of eight retinal diseases and normal control was 87.42% in the ResNet50 model, which added a dense layer with 128 nodes. Furthermore, our AI tool augments ophthalmologist’s performance in the diagnosis of retinal disease. These results suggested that the fundus image-based AI tool is applicable for the medical diagnosis process of retinal diseases.

Feature-Based Registration of Retinal Images

1987 ◽  
Vol 6 (3) ◽  
pp. 272-278 ◽  
Author(s):  
Eli Peli ◽  
Reed A. Augliere ◽  
George T. Timberlake
Keyword(s):  
Retinal Images ◽  
Feature Based

scholarly journals Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Xing Hu ◽  
Shiqiang Hu ◽  
Xiaoyu Zhang ◽  
Huanlong Zhang ◽  
Lingkun Luo
Keyword(s):  
Anomaly Detection ◽  
Nearest Neighbor ◽  
Computation Time ◽  
Compact Representation ◽  
Feature Descriptor ◽  
Neighbor Distance ◽  
Low Level ◽  
Feature Descriptors ◽  
Nearest Neighbor Distance ◽  
Crowded Scenes

We propose a novel local nearest neighbor distance (LNND) descriptor for anomaly detection in crowded scenes. Comparing with the commonly used low-level feature descriptors in previous works, LNND descriptor has two major advantages. First, LNND descriptor efficiently incorporates spatial and temporal contextual information around the video event that is important for detecting anomalous interaction among multiple events, while most existing feature descriptors only contain the information of single event. Second, LNND descriptor is a compact representation and its dimensionality is typically much lower than the low-level feature descriptor. Therefore, not only the computation time and storage requirement can be accordingly saved by using LNND descriptor for the anomaly detection method with offline training fashion, but also the negative aspects caused by using high-dimensional feature descriptor can be avoided. We validate the effectiveness of LNND descriptor by conducting extensive experiments on different benchmark datasets. Experimental results show the promising performance of LNND-based method against the state-of-the-art methods. It is worthwhile to notice that the LNND-based approach requires less intermediate processing steps without any subsequent processing such as smoothing but achieves comparable event better performance.

Sign in / Sign up

Export Citation Format

Share Document