Fully automatic segmentation of fluorescein leakage in subjects with diabetic macular edema

Assessment of Baseline Ultra-Widefield Fluorescein Angiographic Quantitative Leakage Parameters with Ultra-widefield Fundus Features and Clinical Parameters in Diabetic Retinopathy in Protocol AA

PURPOSE

Evaluate quantitative leakage parameters on ultra-widefield fluorescein angiography (UWF-FA) images and explore their association with Diabetic Retinopathy Severity Scale (DRSS), predominantly peripheral lesions (PPLs), visual acuity, and clinical characteristics.

DESIGN

A post-hoc analysis of baseline UWF-FA images in the DRCR Retina Network observational study Protocol AA.

PARTICIPANTS

N = 575 eyes from 384 adults across 38 sites in the US and Canada with gradable UWF-FA.

METHODS

A machine learning-enhanced feature extraction platform provided initial leakage segmentation of UWF-FA images sequentially reviewed and corrected by two certified readers for segmentation accuracy. UWF-FA leakage was measured in five retinal zones: panretinal (whole retina), central macular (3-disc diameter fovea-centered circle), posterior pole (6-disc diameter fovea-centered circle), peripheral (outside 6-disc diameter circle) and widefield far peripheral (outside 9-disc diameter circle); associations with clinical factors were evaluated with marginal beta regression models.

MAIN OUTCOME MEASURES

UWF-FA leakage index, calculated as the area with leakage divided by the analyzable retinal area.

RESULTS

The mean quantitative leakage index was 3.5% for panretinal, 6.6% for macular, 4.8% for posterior pole, 3.3% for peripheral and 2.8% for wide-field far peripheral retinal zones. Panretinal leakage was associated with DRSS (mean 2.2% for no to mild NPDR, 3.4% for moderate NPDR, 4.2% for moderately severe NPDR, 4.8% for severe NPDR and 5.1% for PDR; P<.001), HbA1c (3.2% for HbA1c <8% vs. 3.8% for HbA1c ≥8%; P=.01 for continuous HbA1c), visual acuity (3.3% for 20/25 or better vs. 4.7% for 20/32 or worse; continuous P<.001), and UWF-FA-PPL types of IRMA (4.3% vs. 3.3%; P=.005) or NVE (5.7% vs. 3.4%; P=.003). DRSS was also statistically significant for leakage within all retinal zones (P<.001); eyes with non-central DME versus no DME had higher mean leakage in the central macular (11.2% vs. 5.9%; P=0.005) and posterior pole regions (9.2% vs. 4.2%; P=.002).

CONCLUSION

Quantitative UWF-FA leakage analysis identified associations between leakage and DRSS, visual acuity, and presence of DME. In the future, quantitative UWF-FA leakage parameters may be explored as potential biomarkers for disease progression risk.

Automatic interpretation and clinical evaluation for fundus fluorescein angiography images of diabetic retinopathy patients by deep learning

BACKGROUND/AIMS

Fundus fluorescein angiography (FFA) is an important technique to evaluate diabetic retinopathy (DR) and other retinal diseases. The interpretation of FFA images is complex and time-consuming, and the ability of diagnosis is uneven among different ophthalmologists. The aim of the study is to develop a clinically usable multilevel classification deep learning model for FFA images, including prediagnosis assessment and lesion classification.

METHODS

A total of 15 599 FFA images of 1558 eyes from 845 patients diagnosed with DR were collected and annotated. Three convolutional neural network (CNN) models were trained to generate the label of image quality, location, laterality of eye, phase and five lesions. Performance of the models was evaluated by accuracy, F-1 score, the area under the curve and human-machine comparison. The images with false positive and false negative results were analysed in detail.

RESULTS

Compared with LeNet-5 and VGG16, ResNet18 got the best result, achieving an accuracy of 80.79%-93.34% for prediagnosis assessment and an accuracy of 63.67%-88.88% for lesion detection. The human-machine comparison showed that the CNN had similar accuracy with junior ophthalmologists. The false positive and false negative analysis indicated a direction of improvement.

CONCLUSION

This is the first study to do automated standardised labelling on FFA images. Our model is able to be applied in clinical practice, and will make great contributions to the development of intelligent diagnosis of FFA images.

A new retinal OCT-angiography diabetic retinopathy dataset for segmentation and DR grading

PURPOSE

Diabetic retinopathy (DR) is one of the most common diseases caused by diabetes and can lead to vision loss or even blindness. The wide-field optical coherence tomography (OCT) angiography is non-invasive imaging technology and convenient to diagnose DR.

METHODS

A newly constructed Retinal OCT-Angiography Diabetic retinopathy (ROAD) dataset is utilized for segmentation and grading tasks. It contains 1200 normal images, 1440 DR images, and 1440 ground truths for DR image segmentation. To handle the problem of grading DR, we propose a novel and effective framework, named projective map attention-based convolutional neural network (PACNet).

RESULTS

The experimental results demonstrate the effectiveness of our PACNet. The accuracy of the proposed framework for grading DR is 87.5% on the ROAD dataset.

CONCLUSIONS

The information on ROAD can be viewed at URL https://mip2019.github.io/ROAD. The ROAD dataset will be helpful for the development of the early detection of DR field and future research.

TRANSLATIONAL RELEVANCE

The novel framework for grading DR is a valuable research and clinical diagnosis method.

Perspectives of diabetic retinopathy-challenges and opportunities

Diabetic retinopathy (DR) may lead to vision-threatening complications in people living with diabetes mellitus. Decades of research have contributed to our understanding of the pathogenesis of diabetic retinopathy from non-proliferative to proliferative (PDR) stages, the occurrence of diabetic macular oedema (DMO) and response to various treatment options. Multimodal imaging has paved the way to predict the impact of peripheral lesions and optical coherence tomography-angiography is starting to provide new knowledge on diabetic macular ischaemia. Moreover, the availability of intravitreal anti-vascular endothelial growth factors has changed the treatment paradigm of DMO and PDR. Areas of research have explored mechanisms of breakdown of the blood-retinal barrier, damage to pericytes, the extent of capillary non-perfusion, leakage and progression to neovascularisation. However, knowledge gaps remain. From this perspective, we highlight the challenges and future directions of research in this field.

Artificial intelligence in screening, diagnosis, and classification of diabetic macular edema: A systematic review

We review the application of artificial intelligence (AI) techniques in the screening, diagnosis, and classification of diabetic macular edema (DME) by searching six databases- PubMed, Scopus, Web of Science, Science Direct, IEEE, and ACM- from January 1, 2005 to July 4, 2021. A total of 879 articles were extracted, and by applying inclusion and exclusion criteria, 38 articles were selected for more evaluation. The methodological quality of included studies was evaluated using the Quality Assessment for Diagnostic Accuracy Studies (QUADAS-2). We provide an overview of the current state of various AI techniques for DME screening, diagnosis, and classification using retinal imaging modalities such as optical coherence tomography (OCT) and color fundus photography (CFP). Based on our findings, deep learning models have an extraordinary capacity to provide an accurate and efficient system for DME screening and diagnosis. Using these in the processing of modalities leads to a significant increase in sensitivity and specificity values. The use of decision support systems and applications based on AI in processing retinal images provided by OCT and CFP increases the sensitivity and specificity in DME screening and detection.

Inter-day repeatability assessment of human retinal blood flow using clinical laser speckle contrast imaging

Laser speckle contrast imaging (LSCI) can generate retinal blood flow maps inexpensively and non-invasively. These flow maps can be used to identify various eye disorders associated with reduced blood flow. Despite early success, one of the major obstacles to clinical adoption of LSCI is poor repeatability of the modality. Here, we propose an LSCI registration pipeline that registers contrast maps to correct for rigid movements. Post-registration, intra(same)-day and inter(next)-day repeatability are studied using various quantitative metrics. We have studied LSCI repeatability intra-day by using the coefficient of variation. Using the processing pipelines and custom hardware developed, similar repeatability was observed when compared to previously reported values in the literature. Inter-day repeatability analysis indicates no statistical evidence (p = 0.09) of a difference between flow measurements performed on two independent days. Further improvements to hardware, environmental controls, and participant control must be made to provide higher confidence in the repeatability of blood flow. However, this is the first time that repeatability across two different days (inter-day) using multiple exposure speckle imaging (MESI) has been analyzed and reported.

Automatic Detection of Microaneurysms in OCT Images Using Bag of Features

Diabetic retinopathy (DR) caused by diabetes occurs as a result of changes in the retinal vessels and causes visual impairment. Microaneurysms (MAs) are the early clinical signs of DR, whose timely diagnosis can help detecting DR in the early stages of its development. It has been observed that MAs are more common in the inner retinal layers compared to the outer retinal layers in eyes suffering from DR. Optical coherence tomography (OCT) is a noninvasive imaging technique that provides a cross-sectional view of the retina, and it has been used in recent years to diagnose many eye diseases. As a result, this paper attempts to identify areas with MA from normal areas of the retina using OCT images. This work is done using the dataset collected from FA and OCT images of 20 patients with DR. In this regard, firstly fluorescein angiography (FA) and OCT images were registered. Then, the MA and normal areas were separated, and the features of each of these areas were extracted using the Bag of Features (BOF) approach with the Speeded-Up Robust Feature (SURF) descriptor. Finally, the classification process was performed using a multilayer perceptron network. For each of the criteria of accuracy, sensitivity, specificity, and precision, the obtained results were 96.33%, 97.33%, 95.4%, and 95.28%, respectively. Utilizing OCT images to detect MAs automatically is a new idea, and the results obtained as preliminary research in this field are promising.

Automated Detection of Vascular Leakage in Fluorescein Angiography - A Proof of Concept

Purpose

The purpose of this paper was to develop a deep learning algorithm to detect retinal vascular leakage (leakage) in fluorescein angiography (FA) of patients with uveitis and use the trained algorithm to determine clinically notable leakage changes.

Methods

An algorithm was trained and tested to detect leakage on a set of 200 FA images (61 patients) and evaluated on a separate 50-image test set (21 patients). The ground truth was leakage segmentation by two clinicians. The Dice Similarity Coefficient (DSC) was used to measure concordance.

Results

During training, the algorithm achieved a best average DSC of 0.572 (95% confidence interval [CI] = 0.548–0.596). The trained algorithm achieved a DSC of 0.563 (95% CI = 0.543–0.582) when tested on an additional set of 50 images. The trained algorithm was then used to detect leakage on pairs of FA images from longitudinal patient visits. Longitudinal leakage follow-up showed a >2.21% change in the visible retina area covered by leakage (as detected by the algorithm) had a sensitivity and specificity of 90% (area under the curve [AUC] = 0.95) of detecting a clinically notable change compared to the gold standard, an expert clinician's assessment.

Conclusions

This deep learning algorithm showed modest concordance in identifying vascular leakage compared to ground truth but was able to aid in identifying vascular FA leakage changes over time.

Translational Relevance

This is a proof-of-concept study that vascular leakage can be detected in a more standardized way and that tools can be developed to help clinicians more objectively compare vascular leakage between FAs.

A Weakly Supervised Deep Learning Approach for Leakage Detection in Fluorescein Angiography Images

Purpose

The purpose of this study was to design an automated algorithm that can detect fluorescence leakage accurately and quickly without the use of a large amount of labeled data.

Methods

A weakly supervised learning-based method was proposed to detect fluorescein leakage without the need for manual annotation of leakage areas. To enhance the representation of the network, a residual attention module (RAM) was designed as the core component of the proposed generator. Moreover, class activation maps (CAMs) were used to define a novel anomaly mask loss to facilitate more accurate learning of leakage areas. In addition, sensitivity, specificity, accuracy, area under the curve (AUC), and dice coefficient (DC) were used to evaluate the performance of the methods.

Results

The proposed method reached a sensitivity of 0.73 ± 0.04, a specificity of 0.97 ± 0.03, an accuracy of 0.95 ± 0.05, an AUC of 0.86 ± 0.04, and a DC of 0.87 ± 0.01 on the HRA data set; a sensitivity of 0.91 ± 0.02, a specificity of 0.97 ± 0.02, an accuracy of 0.96 ± 0.03, an AUC of 0.94 ± 0.02, and a DC of 0.85 ± 0.03 on Zhao's publicly available data set; and a sensitivity of 0.71 ± 0.04, a specificity of 0.99 ± 0.06, an accuracy of 0.87 ± 0.06, an AUC of 0.85 ± 0.02, and a DC of 0.78 ± 0.04 on Rabbani's publicly available data set.

Conclusions

The experimental results showed that the proposed method achieves better performance on fluorescence leakage detection and can detect one image within 1 second and thus has great potential value for clinical diagnosis and treatment of retina-related diseases, such as diabetic retinopathy and malarial retinopathy.

Translational Relevance

The proposed weakly supervised learning-based method that automates the detection of fluorescence leakage can facilitate the assessment of retinal-related diseases.

Imaging diabetic retinal disease: clinical imaging requirements

Diabetic retinopathy (DR) is a sight-threatening complication of diabetes mellitus (DM) and it contributes substantially to the burden of disease globally. During the last decades, the development of multiple imaging modalities to evaluate DR, combined with emerging treatment possibilities, has led to the implementation of large-scale screening programmes resulting in improved prevention of vision loss. However, not all patients are able to participate in such programmes and not all are at equal risk of DR development and progression. In this review, we discuss the relevance of the currently available imaging modalities for the evaluation of DR: colour fundus photography (CFP), ultrawide-field photography (UWFP), fundus fluorescein angiography (FFA), optical coherence tomography (OCT), OCT angiography (OCTA) and functional testing. Furthermore, we suggest where a particular imaging technique of DR may aid the evaluation of the disease in different clinical settings. Combining information from various imaging modalities may enable the design of more personalized care including the initiation of treatment and understanding the progression of disease more adequately.

Quantitative Imaging Biomarkers in Age-Related Macular Degeneration and Diabetic Eye Disease: A Step Closer to Precision Medicine

The management of retinal diseases relies heavily on digital imaging data, including optical coherence tomography (OCT) and fluorescein angiography (FA). Targeted feature extraction and the objective quantification of features provide important opportunities in biomarker discovery, disease burden assessment, and predicting treatment response. Additional important advantages include increased objectivity in interpretation, longitudinal tracking, and ability to incorporate computational models to create automated diagnostic and clinical decision support systems. Advances in computational technology, including deep learning and radiomics, open new doors for developing an imaging phenotype that may provide in-depth personalized disease characterization and enhance opportunities in precision medicine. In this review, we summarize current quantitative and radiomic imaging biomarkers described in the literature for age-related macular degeneration and diabetic eye disease using imaging modalities such as OCT, FA, and OCT angiography (OCTA). Various approaches used to identify and extract these biomarkers that utilize artificial intelligence and deep learning are also summarized in this review. These quantifiable biomarkers and automated approaches have unleashed new frontiers of personalized medicine where treatments are tailored, based on patient-specific longitudinally trackable biomarkers, and response monitoring can be achieved with a high degree of accuracy.

Multi-path cascaded U-net for vessel segmentation from fundus fluorescein angiography sequential images

BACKGROUND AND OBJECTIVE

Fundus fluorescein angiography (FFA) technique is widely used in the examination of retinal diseases. In analysis of FFA sequential images, accurate vessel segmentation is a prerequisite for quantification of vascular morphology. Current vessel segmentation methods concentrate mainly on color fundus images and they are limited in processing FFA sequential images with varying background and vessels.

METHODS

We proposed a multi-path cascaded U-net (MCU-net) architecture for vessel segmentation in FFA sequential images, which is capable of integrating vessel features from different image modes to improve segmentation accuracy. Firstly, two modes of synthetic FFA images that enhance details of small vessels and large vessels are prepared, and are then used together with the raw FFA image as inputs of the MCU-net. By fusion of vessel features from the three modes of FFA images, a vascular probability map is generated as output of MCU-net.

RESULTS

The proposed MCU-net was trained and tested on the public Duke dataset and our own dataset for FFA sequential images as well as on the DRIVE dataset for color fundus images. Results show that MCU-net outperforms current state-of-the-art methods in terms of F1-score, sensitivity and accuracy, and is able of reserving details such as thin vessels and vascular connections. It also shows good robustness in processing FFA images captured at different perfusion stages.

CONCLUSIONS

The proposed method can segment vessels from FFA sequential images with high accuracy and shows good robustness to FFA images in different perfusion stages. This method has potential applications in quantitative analysis of vascular morphology in FFA sequential images.

The 2-Year Leakage Index and Quantitative Microaneurysm Results of the RECOVERY Study: Quantitative Ultra-Widefield Findings in Proliferative Diabetic Retinopathy Treated with Intravitreal Aflibercept

Eyes with proliferative diabetic retinopathy (PDR) have been shown to improve in the leakage index and microaneurysm (MA) count after intravitreal aflibercept (IAI) treatment. The authors investigated these changes via automatic segmentation on ultra-widefield fluorescein angiography (UWFA). Forty subjects with PDR were randomized to receive either 2 mg IAI every 4 weeks (Arm 1) or every 12 weeks (Arm 2) through Year 1. After Year 1, Arm 1 switched to quarterly IAI and Arm 2 to monthly IAI through Year 2. By Year 2, the Arm 1 leakage index decreased by 43% from Baseline (p = 0.03) but increased by 59% from Year 1 (p = 0.04). Arm 2 decreased by 61% from Baseline (p = 0.008) and by 31% from Year 1 (p = 0.12). Both cohorts exhibited a significant decline in MAs from Baseline to Year 2 (871 to 410; p < 0.001; 776 to 207; p < 0.001, respectively). Subjects with an improved leakage and MA count showed a more significant improvement in the Diabetic Retinopathy Severity Scale (DRSS) score. Moreover, central subfield thickness (CST) was positively associated with changes in the leakage index. In conclusion, the leakage index and MA counts significantly improved from Baseline following IAI treatment, and monthly injections provided a more rapid and sustained reduction in these parameters compared with quarterly injections.

Research on the Segmentation of Biomarker for Chronic Central Serous Chorioretinopathy Based on Multimodal Fundus Image

At present, laser surgery is one of the effective ways to treat the chronic central serous chorioretinopathy (CSCR), in which the location of the leakage area is of great importance. In order to alleviate the pressure on ophthalmologists to manually label the biomarkers as well as elevate the biomarker segmentation quality, a semiautomatic biomarker segmentation method is proposed in this paper, aiming to facilitate the accurate and rapid acquisition of biomarker location information. Firstly, the multimodal fundus images are introduced into the biomarker segmentation task, which can effectively weaken the interference of highlighted vessels in the angiography images to the location of biomarkers. Secondly, a semiautomatic localization technique is adopted to reduce the search range of biomarkers, thus enabling the improvement of segmentation efficiency. On the basis of the above, the low-rank and sparse decomposition (LRSD) theory is introduced to construct the baseline segmentation scheme for segmentation of the CSCR biomarkers. Moreover, a joint segmentation framework consisting of the above method and region growing (RG) method is further designed to improve the performance of the baseline scheme. On the one hand, the LRSD is applied to offer the initial location information of biomarkers for the RG method, so as to ensure that the RG method can capture effective biomarkers. On the other hand, the biomarkers obtained by RG are fused with those gained by LRSD to make up for the defect of undersegmentation of the baseline scheme. Finally, the quantitative and qualitative ablation experiments have been carried out to demonstrate that the joint segmentation framework performs well than the baseline scheme in most cases, especially in the sensitivity and F1-score indicators, which not only confirms the effectiveness of the framework in the CSCR biomarker segmentation scene but also implies its potential application value in CSCR laser surgery.

Longitudinal panretinal microaneurysm dynamics on ultra-widefield fluorescein angiography in eyes treated with intravitreal aflibercept for proliferative diabetic retinopathy in the recovery study

BACKGROUND/AIMS

Quantifying microaneurysms (MAs) turnover may be an objective measure for therapeutic response in diabetic retinopathy. This study assesses changes in MA counts on ultra-widefield fluorescein angiography (UWFA) in subjects undergoing treatment with intravitreal aflibercept injection (IAI) for proliferative diabetic retinopathy (PDR) in the Intravitreal Aflibercept for Retinal Non-Perfusion in Proliferative Diabetic Retinopathy(RECOVERY) study using an automated MA detection platform.

METHODS

RECOVERY is a prospective study that enrolled 40 subjects with PDR randomised 1:1 to receive 2 mg IAI every 4 weeks(q4wk) or every 12 weeks (q12wk). UWFA images were obtained at baseline, 6 months and 1 year. Images were analysed using an automated segmentation platform to detect and quantify MAs. Zones 1, 2 and 3 correspond to the macula, mid-periphery and far-periphery, respectively.

RESULTS

The q4wk cohort demonstrated a significant decline in MAs in all zones and panretinally at baseline versus month 6, baseline versus year 1, and month 6 versus year 1 (-20.0% to -61.8%; all p<0.001). In the q12wk cohort, baseline versus month 6 showed a significant decline panretinally (mean: -34.2%; p<0.001) and in zone 3 (mean -44.18%; p<0.001). Addiitonally, baseline to year 1 in the q12wk group demonstrated significant decline panretinally (mean: -47.7%; p<0.001) and in zone 3 (mean: -59.8%; p<0.001). All zones demonstrated significantly decline from month 6 to year 1 in the q12wk group.

CONCLUSION

Therapy with IAI demonstrates significantly reduced panretinal MA counts in PDR at 1 year in both treatment groups. The use of automated platforms to detect and quantify MAs may provide a novel imaging marker for evaluating disease activity and therapeutic impact.

TRIAL REGISTRATION NUMBER

NCT02863354.

Automatic detection of leakage point in central serous chorioretinopathy of fundus fluorescein angiography based on time sequence deep learning

PURPOSE

To detect the leakage points of central serous chorioretinopathy (CSC) automatically from dynamic images of fundus fluorescein angiography (FFA) using a deep learning algorithm (DLA).

METHODS

The study included 2104 FFA images from 291 FFA sequences of 291 eyes (137 right eyes and 154 left eyes) from 262 patients. The leakage points were segmented with an attention gated network (AGN). The optic disk (OD) and macula region were segmented simultaneously using a U-net. To reduce the number of false positives based on time sequence, the leakage points were matched according to their positions in relation to the OD and macula.

RESULTS

With the AGN alone, the number of cases whose detection results perfectly matched the ground truth was only 37 out of 61 cases (60.7%) in the test set. The dice on the lesion level were 0.811. Using an elimination procedure to remove false positives, the number of accurate detection cases increased to 57 (93.4%). The dice on the lesion level also improved to 0.949.

CONCLUSIONS

Using DLA, the CSC leakage points in FFA can be identified reproducibly and accurately with a good match to the ground truth. This novel finding may pave the way for potential application of artificial intelligence to guide laser therapy.

Hybrid registration of retinal fluorescein angiography and optical coherence tomography images of patients with diabetic retinopathy

Diabetic retinopathy (DR) is a common ophthalmic disease among diabetic patients. It is essential to diagnose DR in the early stages of treatment. Various imaging systems have been proposed to detect and visualize retina diseases. The fluorescein angiography (FA) imaging technique is now widely used as a gold standard technique to evaluate the clinical manifestations of DR. Optical coherence tomography (OCT) imaging is another technique that provides 3D information of the retinal structure. The FA and OCT images are captured in two different phases and field of views and image fusion of these modalities are of interest to clinicians. This paper proposes a hybrid registration framework based on the extraction and refinement of segmented major blood vessels of retinal images. The newly extracted features significantly improve the success rate of global registration results in the complex blood vessel network of retinal images. Afterward, intensity-based and deformable transformations are utilized to further compensate the motion magnitude between the FA and OCT images. Experimental results of 26 images of the various stages of DR patients indicate that this algorithm yields promising registration and fusion results for clinical routine.

Deep-learning based multi-modal retinal image registration for the longitudinal analysis of patients with age-related macular degeneration

This work reports a deep-learning based registration algorithm that aligns multi-modal retinal images collected from longitudinal clinical studies to achieve accuracy and robustness required for analysis of structural changes in large-scale clinical data. Deep-learning networks that mirror the architecture of conventional feature-point-based registration were evaluated with different networks that solved for registration affine parameters, image patch displacements, and patch displacements within the region of overlap. The ground truth images for deep learning-based approaches were derived from successful conventional feature-based registration. Cross-sectional and longitudinal affine registrations were performed across color fundus photography (CFP), fundus autofluorescence (FAF), and infrared reflectance (IR) image modalities. For mono-modality longitudinal registration, the conventional feature-based registration method achieved mean errors in the range of 39-53 µm (depending on the modality) whereas the deep learning method with region overlap prediction exhibited mean errors in the range 54-59 µm. For cross-sectional multi-modality registration, the conventional method exhibited gross failures with large errors in more than 50% of the cases while the proposed deep-learning method achieved robust performance with no gross failures and mean errors in the range 66-69 µm. Thus, the deep learning-based method achieved superior overall performance across all modalities. The accuracy and robustness reported in this work provide important advances that will facilitate clinical research and enable a detailed study of the progression of retinal diseases such as age-related macular degeneration.

RETINAL LEAKAGE INDEX DYNAMICS ON ULTRA-WIDEFIELD FLUORESCEIN ANGIOGRAPHY IN EYES TREATED WITH INTRAVITREAL AFLIBERCEPT FOR PROLIFERATIVE DIABETIC RETINOPATHY IN THE RECOVERY STUDY

PURPOSE

Characterization of leakage indices on ultra-widefield fluorescein angiography in proliferative diabetic retinopathy treated with intravitreal aflibercept.

METHODS

Prospective study enrolling subjects for treatment of proliferative diabetic retinopathy randomized 1:1 to receive 2-mg intravitreal aflibercept every 4 weeks (2q4) or every 12 weeks (2q12). Ultra-widefield fluorescein angiography images obtained at baseline, 24, and 48 weeks were analyzed using a semiautomated leakage segmentation platform. Panretinal and zonal leakage indices were calculated.

RESULTS

Forty eyes of 40 subjects were included, and mean age was 48 ± 12.1 years. Mean number of injections was 11 ± 1.7 in the 2q4 arm and 4 ± 0.4 in the 2q12 arm. Median baseline leakage index in the 2q4 and 2q12 groups was 5.1% and 4.3%, respectively (P = 0.28). At 24 and 48 weeks, the 2q4 group significantly improved to 1.1% (-79%, P < 0.0001). At Week 24, the 2q12 group demonstrated nonsignificant improvement (3.4%; -21%, P = 0.47); by Week 48, improvement was significant (1.4%; -68%, P = 0.02). The 2q4 group resulted in lower leakage index compared with the 2q12 group at 24 weeks (1.1% vs. 3.4%, respectively; P = 0.008), but by 48 weeks, leakage index was similar between both groups (1.1% vs. 1.4%, respectively; P = 0.34).

CONCLUSION

Proliferative diabetic retinopathy treated with intravitreal aflibercept demonstrated significant leakage index reductions at 1 year. Monthly dosing provided more rapid reduction in leakage index compared with quarterly dosing.

TRIAL REGISTRATION

RECOVERY study (NCT02863354); https://clinicaltrials.gov/ct2/show/NCT02863354.

Infrared retinal images for flashless detection of macular edema

This study evaluates the use of infrared (IR) images of the retina, obtained without flashes of light, for machine-based detection of macular oedema (ME). A total of 41 images of 21 subjects, here with 23 cases and 18 controls, were studied. Histogram and gray-level co-occurrence matrix (GLCM) parameters were extracted from the IR retinal images. The diagnostic performance of the histogram and GLCM parameters was calculated in hindsight based on the known labels of each image. The results from the one-way ANOVA indicated there was a significant difference between ME eyes and the controls when using GLCM features, with the correlation feature having the highest area under the curve (AUC) (A_Z) value. The performance of the proposed method was also evaluated using a support vector machine (SVM) classifier that gave sensitivity and specificity of 100%. This research shows that the texture of the IR images of the retina has a significant difference between ME eyes and the controls and that it can be considered for machine-based detection of ME without requiring flashes of light.

Non-Proliferative Diabetic Retinopathy Is Characterized by Nonuniform Alterations of Peripapillary Capillary Networks

Purpose

The purpose of this study was to use three-dimensional confocal microscopy to quantify the spatial patterns of capillary network alterations in nonproliferative diabetic retinopathy (NPDR).

Methods

The retinal microvasculature was perfusion-labelled in seven normal human donor eyes and six age-matched donor eyes with NPDR. The peripapillary microcirculation was studied using confocal scanning laser microscopy. Capillary density and diameters of the radial peripapillary capillary plexus (RPCP), superficial capillary plexus (SCP), intermediate capillary plexus (ICP), and deep capillary plexus (DCP) were quantified and compared. Three-dimensional visualization strategies were also used to compare the communications between capillary beds and precapillary arterioles and postcapillary venules.

Results

Mean capillary diameter was significantly increased in the NPDR group (P < 0.001). Intercapillary distance was significantly increased in the DCP (P = 0.004) and RPCP (P = 0.022) of the NPDR group (P = 0.010) but not the SCP (P = 0.155) or ICP (P = 0.103). The NPDR group was associated with an increased frequency of inflow communication between the SCP and ICP/DCP and a decreased frequency of communication between the SCP and RPCP (P = 0.023). There was no difference in the patterns of outflow communications between the two groups (P = 0.771).

Conclusions

This study demonstrates that capillary plexuses are nonuniformly perturbed in NPDR. These structural changes may be indicative of perturbations to blood flow patterns between different retinal layers. Our findings may aid the interpretation of previous clinical observations made using optical coherence tomography angiography as well as improve our understanding of the pathogenesis of NPDR.

Artery-venous classification in fluorescein angiograms based on region growing with sequential and structural features

BACKGROUND AND OBJECTIVES

Fluorescein angiography (FA) is widely used in ophthalmology for examining retinal hemodynamics and vascular morphology. Artery-venous classification is an important step in FA image processing for measurement of feature parameters, such as arterio-venous passage time (AVP) and arterio-venous width ratio (AVR) that are proven useful in clinical assessment of circulation disturbance and vessel abnormalities. However, manual artery-venous classification needs expertise and is rather time consuming, and little effort has been devoted to develop automatic classification methods. In order to solve this problem, we propose a novel artery-venous classification method using region growing strategy with sequential and structural features (RGSS).

METHODS

The main procedures of our proposed RGSS method include: (i) registration of FA image sequence by mutual-information method; (ii) extraction of sequential features of the dye perfusion process from the registrated FA images; (iii) extraction of vessel structural features from vascular centerline map; (iv) based on the obtained features, seeds of arteries and veins within initial growing region (here optic disk) are generated and then propagated in the entire vessel network using region growing strategy. The RGSS method was tested on our own dataset and public Duke dataset, and its performance was evaluated quantitatively.

RESULTS

Tests show that RGSS method is able to classify arteries and veins from the complicated vessel network in FA images, with high classification accuracy of 0.91 ± 0.04 on Duke dataset and 0.92 ± 0.03 on our dataset. The employed sequential and structural features are demonstrated to be effective in classifying thin arteries and veins at vessel crossings.

CONCLUSIONS

Automatic artery-venous classification can be accomplished using our proposed RGSS method with high accuracy. The RGSS method not only emancipates ophthalmologists from hard work of manual marking of arteries and veins, but also helps in measuring important parameters (such as AVP and AVR) for clinical assessment of circulation disturbance and vessel abnormalities.

Registration of fluorescein angiography and optical coherence tomography images of curved retina via scanning laser ophthalmoscopy photographs

Accurate and automatic registration of multimodal retinal images such as fluorescein angiography (FA) and optical coherence tomography (OCT) enables utilization of supplementary information. FA is a gold standard imaging modality that depicts neurovascular structure of retina and is used for diagnosing neurovascular-related diseases such as diabetic retinopathy (DR). Unlike FA, OCT is non-invasive retinal imaging modality that provides cross-sectional data of retina. Due to differences in contrast, resolution and brightness of multimodal retinal images, the images resulted from vessel extraction of image pairs are not exactly the same. Also, prevalent feature detection, extraction and matching schemes do not result in perfect matches. In addition, the relationships between retinal image pairs are usually modeled by affine transformation, which cannot generate accurate alignments due to the non-planar retina surface. In this paper, a precise registration scheme is proposed to align FA and OCT images via scanning laser ophthalmoscopy (SLO) photographs as intermediate images. For this purpose, first a retinal vessel segmentation is applied to extract main blood vessels from the FA and SLO images. Next, a novel global registration is proposed based on the Gaussian model for curved surface of retina. For doing so, first a global rigid transformation is applied to FA vessel-map image using a new feature-based method to align it with SLO vessel-map photograph, in a way that outlier matched features resulted from not-perfect vessel segmentation are completely eliminated. After that, the transformed image is globally registered again considering Gaussian model for curved surface of retina to improve the precision of the previous step. Eventually a local non-rigid transformation is exploited to register two images perfectly. The experimental results indicate the presented scheme is more precise compared to other registration methods.

A survey on medical image analysis in diabetic retinopathy

Diabetic Retinopathy (DR) represents a highly-prevalent complication of diabetes in which individuals suffer from damage to the blood vessels in the retina. The disease manifests itself through lesion presence, starting with microaneurysms, at the nonproliferative stage before being characterized by neovascularization in the proliferative stage. Retinal specialists strive to detect DR early so that the disease can be treated before substantial, irreversible vision loss occurs. The level of DR severity indicates the extent of treatment necessary - vision loss may be preventable by effective diabetes management in mild (early) stages, rather than subjecting the patient to invasive laser surgery. Using artificial intelligence (AI), highly accurate and efficient systems can be developed to help assist medical professionals in screening and diagnosing DR earlier and without the full resources that are available in specialty clinics. In particular, deep learning facilitates diagnosis earlier and with higher sensitivity and specificity. Such systems make decisions based on minimally handcrafted features and pave the way for personalized therapies. Thus, this survey provides a comprehensive description of the current technology used in each step of DR diagnosis. First, it begins with an introduction to the disease and the current technologies and resources available in this space. It proceeds to discuss the frameworks that different teams have used to detect and classify DR. Ultimately, we conclude that deep learning systems offer revolutionary potential to DR identification and prevention of vision loss.

Repeatability of automated leakage quantification and microaneurysm identification utilising an analysis platform for ultra-widefield fluorescein angiography

Background/aimsUltra-widefield fluorescein angiography (UWFA) provides unique opportunities for panretinal assessment of retinal diseases. The objective quantification of UWFA features is a labour-intensive manual process, limiting its utility. The present study assesses the consistency/repeatability of an automated assessment platform for the characterisation of retinal vascular features, quantification of microaneurysms (MA) and leakage foci in UWFA images.

METHODS

An Institutional Review Board-approved retrospective image analysis study was performed on UWFA images. For each eye, two arteriovenous-phase images and two late-phase images were selected. Automated assessment was performed for retinal vascular features, MA identification and leakage segmentation. Panretinal and zonal assessment of metrics was performed.

RESULTS

There was a significant correlation between paired time points for retinal vessel area and vessel length on early images (Pearson r=0.92, p<0.0001; Pearson r=0.94, p<0.0001) and late images (Pearson r=0.92, p<0.0001; Pearson r=0.92, p<0.0001, respectively). Panretinal and zonal MA counts demonstrated high repeatability between images (all p<0.0001). Similarly, panretinal leakage area and zonal leakage areas were highly correlated (all p<0.001).

CONCLUSION

This automated algorithm demonstrated very strong intrastudy correlation between paired time points in the same phases of the angiogram for quantifying retinal vascular characteristics, MA count and leakage parameters in UWFA images. These findings suggest significant flexibility in the platform for consistency in evaluating metrics over time and is encouraging for longitudinal assessment opportunities.

Automated retinal lesion detection via image saliency analysis

BACKGROUND AND OBJECTIVE

The detection of abnormalities such as lesions or leakage from retinal images is an important health informatics task for automated early diagnosis of diabetic and malarial retinopathy or other eye diseases, in order to prevent blindness and common systematic conditions. In this work, we propose a novel retinal lesion detection method by adapting the concepts of saliency.

METHODS

Retinal images are first segmented as superpixels, two new saliency feature representations: uniqueness and compactness, are then derived to represent the superpixels. The pixel level saliency is then estimated from these superpixel saliency values via a bilateral filter. These extracted saliency features form a matrix for low-rank analysis to achieve saliency detection. The precise contour of a lesion is finally extracted from the generated saliency map after removing confounding structures such as blood vessels, the optic disk, and the fovea. The main novelty of this method is that it is an effective tool for detecting different abnormalities at the pixel level from different modalities of retinal images, without the need to tune parameters.

RESULTS

To evaluate its effectiveness, we have applied our method to seven public datasets of diabetic and malarial retinopathy with four different types of lesions: exudate, hemorrhage, microaneurysms, and leakage. The evaluation was undertaken at the pixel level, lesion level, or image level according to ground truth availability in these datasets.

CONCLUSIONS

The experimental results show that the proposed method outperforms existing state-of-the-art ones in applicability, effectiveness, and accuracy.

Imaging and Biomarkers in Diabetic Macular Edema and Diabetic Retinopathy

PURPOSE OF REVIEW

Diabetic retinopathy (DR) is the leading cause of acquired vision loss in adults across the globe. Early identification and treatment of patients with DR is paramount for vision preservation. The aim of this review paper is to outline current and new imaging techniques and biomarkers that are valuable for clinical diagnosis and management of DR.

RECENT FINDINGS

Ultrawide field imaging and automated deep learning algorithms are recent advancements on traditional fundus photography and fluorescein angiography. Optical coherence tomography (OCT) and OCT angiography are techniques that image retinal anatomy and vasculature and OCT is routinely used to monitor response to treatment. Many circulating, vitreous, and genetic biomarkers have been studied to facilitate disease detection and development of new treatments. Recent advancements in retinal imaging and identification of promising new biomarkers for DR have the potential to increase detection, risk stratification, and treatment for patients with DR.

Deep Ensemble Learning Based Objective Grading of Macular Edema by Extracting Clinically Significant Findings from Fused Retinal Imaging Modalities

Macular edema (ME) is a retinal condition in which central vision of a patient is affected. ME leads to accumulation of fluid in the surrounding macular region resulting in a swollen macula. Optical coherence tomography (OCT) and the fundus photography are the two widely used retinal examination techniques that can effectively detect ME. Many researchers have utilized retinal fundus and OCT imaging for detecting ME. However, to the best of our knowledge, no work is found in the literature that fuses the findings from both retinal imaging modalities for the effective and more reliable diagnosis of ME. In this paper, we proposed an automated framework for the classification of ME and healthy eyes using retinal fundus and OCT scans. The proposed framework is based on deep ensemble learning where the input fundus and OCT scans are recognized through the deep convolutional neural network (CNN) and are processed accordingly. The processed scans are further passed to the second layer of the deep CNN model, which extracts the required feature descriptors from both images. The extracted descriptors are then concatenated together and are passed to the supervised hybrid classifier made through the ensemble of the artificial neural networks, support vector machines and naïve Bayes. The proposed framework has been trained on 73,791 retinal scans and is validated on 5100 scans of publicly available Zhang dataset and Rabbani dataset. The proposed framework achieved the accuracy of 94.33% for diagnosing ME and healthy subjects and achieved the mean dice coefficient of 0.9019 ± 0.04 for accurately extracting the retinal fluids, 0.7069 ± 0.11 for accurately extracting hard exudates and 0.8203 ± 0.03 for accurately extracting retinal blood vessels against the clinical markings.

Estimation of Gestational Age via Image Analysis of Anterior Lens Capsule Vascularity in Preterm Infants: A Pilot Study

Introduction: Anterior lens capsule vascularity (ALCV) is resorbed in the developing fetus from 27 to 35 weeks gestation. In this pilot study, we evaluated the feasibility and validity of combining smartphone ophthalmoscope videos of ALCV and image analysis for gestational age estimation. Methods: ALCV videos were captured longitudinally in preterm neonates from delivery using a PanOptic® Ophthalmoscope with an iExaminer® adapter (Welch-Allyn). ALCV video frames were manually selected and quantified using semi-automatic image analysis. A predictive model based on ALCV features was compared to gold-standard ultrasound gestational age estimates. Results: A total of 64 image-capture sessions were carried out in 24 neonates. Ultrasound-estimated gestational age and ALCV-predicted gestational age estimates indicate that the two methods are similar (r = 0.78, p < 0.0001). ALCV estimates of gestational age were within 0.11 ± 1.3 weeks of ultrasound estimates. In the final model, gestational age was predicted within ± 1 week for 54% and within ± 2 weeks for 86% of the measures. Conclusions: This novel application of smartphone ophthalmoscopy and ALCV image analysis may provide a safe, accurate and non-invasive technology to estimate postnatal gestational age, especially in low income countries where gestational age may not be known at birth.

Vitreous and intraretinal macular changes in diabetic macular edema with and without tractional components

Diabetic macular edema (DME) is still one of the main causes of visual impairment. Repeated intravitreal injections of ranibizumab are considered the gold standard treatment, but the efficacy in patients with prominent cystic characteristics remains uncertain. In diabetic retinas, the identification of both antero-posterior and, particularly, tangential tractions is crucial to prevent misdiagnosis of tractional and refractory DME, and therefore to prevent poor treatment outcomes. The treatment of tractional DME with anti-VEGF injections could be poorly effective due to the influence of a tractional force. Pars plana vitrectomy (PPV) is a surgical procedure that has been widely used in the treatment of diffuse and refractory DME. Anatomical improvement, although stable and immediate, did not result in visual improvement. PPV with internal limiting membrane (ILM) peeling for the treatment of non-tractional DME in patients with prominent cysts (> 390 μm) causes subfoveal atrophy, defined as "floor effect". Epiretinal tangential forces and intraretinal change evaluation by SD-OCT of non-tractional DME are essential for determining appropriate management.

Non-rigid registration of Fluorescein Angiography and Optical Coherence Tomography via scanning laser ophthalmoscope imaging

Fluorescein Angiography (FA) imaging is the gold standard technique for neurovascular imaging regarding assessing neurovascular diseases such as Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME). On the other hand, as FA imaging is invasive and does not provide any depth information, Optical Coherence Tomography (OCT) imaging technique is a good complementary for it in diagnosis process. To correlate the information of both FA and OCT images, an image alignment/registration process is needed. In absence of an automatic registration software, the clinician should do intuitive comparison to integrate these data which is a subjective and time consuming process. In this paper, we demonstrate a non-rigid registration method called multi-step correlation-based registration algorithm to automatically register FA and OCT images together. Our algorithm consists of two steps including rigid/global and non-rigid/local registration. We evaluate our algorithm's performance by labeling Micro-Aneurysm (MA) spots -hallmarks of DR- on FA images and determining MA regions on OCT B-scans after registration. Our Results show that our algorithm performs accurately regarding registration of FA images and OCT B-scans.

High-resolution, in vivo multimodal photoacoustic microscopy, optical coherence tomography, and fluorescence microscopy imaging of rabbit retinal neovascularization

Photoacoustic microscopy (PAM) is an emerging imaging technology that can non-invasively visualize ocular structures in animal eyes. This report describes an integrated multimodality imaging system that combines PAM, optical coherence tomography (OCT), and fluorescence microscopy (FM) to evaluate angiogenesis in larger animal eyes. High-resolution in vivo imaging was performed in live rabbit eyes with vascular endothelial growth factor (VEGF)-induced retinal neovascularization (RNV). The results demonstrate that our multimodality imaging system can non-invasively visualize RNV in both albino and pigmented rabbits to determine retinal pathology using PAM and OCT and verify the leakage of neovascularization using FM and fluorescein dye. This work presents high-resolution visualization of angiogenesis in rabbits using a multimodality PAM, OCT, and FM system and may represent a major step toward the clinical translation of the technology.

Visualization of changes in the foveal avascular zone in both observed and treated diabetic macular edema using optical coherence tomography angiography

BACKGROUND

Central vision loss in diabetic retinopathy is commonly related to diabetic macular edema (DME). The objective of this study was to describe changes between consecutive visits on optical coherence tomography angiography (OCTA) of the foveal avascular zone (FAZ) in eyes with DME.

METHODS

20 eyes from 14 patients with DME were imaged on 2 successive clinic visits separated by at least 1 month. The mean interval between visits was 3.2 months. The only intervention used was intravitreal anti-VEGF in 11 eyes; the others were observed over time without treatment. Two different readers measured FAZ area using a pseudo-automated tool in comparison to a manual tracing tool. Qualitative changes in the appearance of the vasculature surrounding the FAZ were also recorded. The retinal capillary plexus was segmented into deep and superficial plexuses, and FAZ measurements were done on the superficial, deep, and summated plexuses.

RESULTS

Pseudo-automated and manual measurements of FAZ area decreased significantly (p < 0.05) between visits in the deep, superficial, and summated plexuses. Qualitative analysis of vasculature surrounding the FAZ showed that most of the vascular changes (65%) over time were visible in the deep plexus, compared to 30 and 20% in the superficial and summated plexuses, respectively.

CONCLUSIONS

The most significant differences in FAZ size over time were in the summated plexus (p < 0.001), while changes in FAZ appearance were most prominent in the deep plexus. Absolute decrease in FAZ size over visits was largest in the deep plexus. Our results demonstrate that OCTA can effectively be used to measure FAZ area in patients with DME, visualize qualitative changes in retinal vasculature, and visualize the segmentation levels at which these changes can be best appreciated. However, larger studies are needed to evaluate the reproducibility of manual and pseudo-automated measuring techniques.

Automated quantitative characterisation of retinal vascular leakage and microaneurysms in ultra-widefield fluorescein angiography

Ultra-widefield fluorescein angiography (UWFA) is an emerging imaging modality used to characterise pathology in the retinal vasculature such as microaneurysms (MAs) and vascular leakage. Despite its potential value for diagnosis and disease surveillance, objective quantitative assessment of retinal pathology by UWFA is currently limited because it requires laborious manual segmentation by trained human graders. In this report, we describe a novel fully automated software platform, which segments MAs and leakage areas in native and dewarped UWFA images with retinal vascular disease. Comparison of the algorithm with human grader-generated gold standards demonstrated significant strong correlations for MA and leakage areas (intraclass correlation coefficient (ICC)=0.78-0.87 and ICC=0.70-0.86, respectively, p=2.1×10^-7 to 3.5×10^-10 and p=7.8×10^-6 to 1.3×10^-9, respectively). These results suggest the algorithm performs similarly to human graders in MA and leakage segmentation and may be of significant utility in clinical and research settings.

A Quantitative Approach to Predict Differential Effects of Anti-VEGF Treatment on Diffuse and Focal Leakage in Patients with Diabetic Macular Edema: A Pilot Study

Purpose

We use semiautomated segmentation of fluorescein angiography (FA) to determine whether anti-vascular endothelial growth factor (VEGF) treatment for diabetic macular edema (DME) differentially affects microaneurysm (MA)–associated leakage, termed focal leakage, versus non-MA–associated leakage, termed diffuse leakage.

Methods

We performed a retrospective study of 29 subjects treated with at least three consecutive injections of anti-VEGF agents for DME (mean 4.6 injections; range, 3–10) who underwent Heidelberg FA before and after anti-VEGF therapy. Inclusion criteria were macula center involving DME and at least 3 consecutive anti-VEGF injections. Exclusion criteria were macular edema due to cause besides DME, anti-VEGF within 3 months of initial FA, concurrent treatment for DME besides anti-VEGF, and macular photocoagulation within 1 year. At each time point, total leakage was semiautomatically segmented using a modified version of our previously published software. Microaneurysms were identified by an expert grader and leakage within a 117 μm radius of each MA was classified as focal leakage. Remaining leakage was classified as diffuse leakage. The absolute and percent changes in total, diffuse, and focal leakage were calculated for each subject.

Results

Mean pretreatment total leakage was 8.2 mm² and decreased by a mean of 40.1% (P < 0.0001; 95% confidence interval [CI], [−28.6, −52.5]) following treatment. Diffuse leakage decreased by a mean of 45.5% (P < 0.0001; 95% CI, [−31.3, −59.6]) while focal leakage decreased by 17.9% (P = 0.02; 95% CI, [−1.0, −34.8]). The difference in treatment response between focal and diffuse leakage was statistically significant (P = 0.01).

Conclusions

Anti-VEGF treatment for DME results in decreased diffuse leakage but had relatively little effect on focal leakage as assessed by FA. This suggests that diffuse leakage may be a marker of VEGF-mediated pathobiology. Patients with predominantly focal leakage may be less responsive to anti-VEGF therapy.

Translational Relevance

Fluorescein angiography can define focal and diffuse subtypes of diabetic macular edema and these may respond differently to anti-VEGF treatment.

Retinal biomarkers provide "insight" into cortical pharmacology and disease

The retina is an easily accessible out-pouching of the central nervous system (CNS) and thus lends itself to being a biomarker of the brain. More specifically, the presence of neuronal, vascular and blood-neural barrier parallels in the eye and brain coupled with fast and inexpensive methods to quantify retinal changes make ocular biomarkers an attractive option. This includes its utility as a biomarker for a number of cerebrovascular diseases as well as a drug pharmacology and safety biomarker for the CNS. It is a rapidly emerging field, with some areas well established, such as stroke risk and multiple sclerosis, whereas others are still in development (Alzheimer's, Parkinson's, psychological disease and cortical diabetic dysfunction). The current applications and future potential of retinal biomarkers, including potential ways to improve their sensitivity and specificity are discussed. This review summarises the existing literature and provides a perspective on the strength of current retinal biomarkers and their future potential.

Joint alignment of multispectral images via semidefinite programming

In this paper, we introduce a novel feature-point-matching based framework for achieving an optimized joint-alignment of sequential images from multispectral imaging (MSI). It solves a low-rank and semidefinite matrix that stores all pairwise-image feature-mappings by minimizing the total amount of point-to-point matching cost via a convex optimization of a semidefinite programming formulation. This unique strategy takes a complete consideration of the information aggregated by all point-matching costs and enables the entire set of pairwise-image feature-mappings to be solved simultaneously and near-optimally. Our framework is capable of running in an automatic or interactive fashion, offering an effective tool for eliminating spatial misalignments introduced into sequential MSI images during the imaging process. Our experimental results obtained from a database of 28 sequences of MSI images of human eye demonstrate the superior performances of our approach to the state-of-the-art techniques. Our framework is potentially invaluable in a large variety of practical applications of MSI images.

Segmentation Based Sparse Reconstruction of Optical Coherence Tomography Images

We demonstrate the usefulness of utilizing a segmentation step for improving the performance of sparsity based image reconstruction algorithms. In specific, we will focus on retinal optical coherence tomography (OCT) reconstruction and propose a novel segmentation based reconstruction framework with sparse representation, termed segmentation based sparse reconstruction (SSR). The SSR method uses automatically segmented retinal layer information to construct layer-specific structural dictionaries. In addition, the SSR method efficiently exploits patch similarities within each segmented layer to enhance the reconstruction performance. Our experimental results on clinical-grade retinal OCT images demonstrate the effectiveness and efficiency of the proposed SSR method for both denoising and interpolation of OCT images.

Intensity and Compactness Enabled Saliency Estimation for Leakage Detection in Diabetic and Malarial Retinopathy

Leakage in retinal angiography currently is a key feature for confirming the activities of lesions in the management of a wide range of retinal diseases, such as diabetic maculopathy and paediatric malarial retinopathy. This paper proposes a new saliency-based method for the detection of leakage in fluorescein angiography. A superpixel approach is firstly employed to divide the image into meaningful patches (or superpixels) at different levels. Two saliency cues, intensity and compactness, are then proposed for the estimation of the saliency map of each individual superpixel at each level. The saliency maps at different levels over the same cues are fused using an averaging operator. The two saliency maps over different cues are fused using a pixel-wise multiplication operator. Leaking regions are finally detected by thresholding the saliency map followed by a graph-cut segmentation. The proposed method has been validated using the only two publicly available datasets: one for malarial retinopathy and the other for diabetic retinopathy. The experimental results show that it outperforms one of the latest competitors and performs as well as a human expert for leakage detection and outperforms several state-of-the-art methods for saliency detection.

Contemporary retinal imaging techniques in diabetic retinopathy: a review

Over the last decade, there has been an expansion of imaging modalities available to clinicians to diagnose and monitor the treatment and progression of diabetic retinopathy. Recently, advances in image technologies related to OCT and OCT angiography have enabled improved visualization and understanding of this disease. In this review, we will describe the use of imaging techniques such as colour fundus photography, fundus autofluorescence, fluorescein angiography, infrared reflectance imaging, OCT, OCT-Angiography and techniques in adaptive optics and hyperspectral imaging in the diagnosis and management of diabetic retinopathy.