scholarly journals Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches

Information ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 466
Author(s):  
Francesco Martelli ◽  
Claudia Giacomozzi
Keyword(s):  
Retinal Imaging ◽  
Retinal Images ◽  
Cardiovascular Research ◽  
Vascular Tortuosity ◽  
Retinal Microvasculature ◽  
Growing Body

A growing body of research in retinal imaging is recently considering vascular tortuosity measures or indexes, with definitions and methods mostly derived from cardiovascular research. However, retinal microvasculature has its own peculiarities that must be considered in order to produce reliable measurements. This study analyzed and compared various derived metrics (e.g., TI, TI_avg, TI*CV) across four existing computational workflows. Specifically, the implementation of the models on two critical OCT images highlighted main pitfalls of the methods, which may fail in reliably differentiating a highly tortuous image from a normal one. A tentative, encouraging approach to mitigate the issue on the same OCT exemplificative images is described in the paper, based on the suggested index TI*CV.

Automated Analysis of Retinal Vascular Tortuosity on Color Retinal Images

2010 ◽  
Vol 36 (2) ◽  
pp. 689-697 ◽  
Author(s):  
Alauddin Bhuiyan ◽  
Baikunth Nath ◽  
Kotagiri Ramamohanarao ◽  
Ryo Kawasaki ◽  
Tien Yin Wong
Keyword(s):  
Automated Analysis ◽  
Retinal Images ◽  
Vascular Tortuosity ◽  
Retinal Vascular Tortuosity

scholarly journals Improving Diabetic Diagnosis and Prevention with Machine Learning on Retinal Imaging

2021 ◽  
Vol 271 ◽  
pp. 01034
Author(s):  
Yushan Min
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Diabetic Retinopathy ◽  
Learning Algorithms ◽  
Area Under The Curve ◽  
Retinal Imaging ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Retinal Images ◽  
Support Vector Machine Algorithm

If the retinal images show evidences of abnormalities such as change in volume, diameter, and unusual spots in the retina, then there is a positive correlation to the diabetic progress. Mathematical and statistical theories behind the machine learning algorithms are powerful enough to detect signs of diabetes through retinal images. Several machine learning algorithms: Logistic Regression, Support Vector Machine, Random Forest, and Neural Networks were applied to predict whether images contain signs of diabetic retinopathy or not. After building the models, the computed results of these algorithms were compared by confusion matrixes, receiver operating characteristic curves, and Precision-Recall curves. The performance of the Support Vector Machine algorithm was the best since it had the highest true-positive rate, area under the curve for ROC curve, and area under the curve for Precision-Recall curve. This conclusion shows that the most complex algorithms doesn’t always give the best performance, the final accuracy also depends on the dataset. For this dataset of retinal imaging, the Support Vector Machine algorithm achieved the best results. Detecting signs of diabetic retinopathy is helpful for detecting for diabetes since more than 60% of patients with diabetes have signs of diabetic retinopathy. Machine learning algorithms can speed up the process and improve the accuracy of diagnosis. When the method is reliable enough, it can be utilized in diabetes diagnosis directly in clinics. Current methods require going on diets and taking blood samples, which could be very time consuming and inconvenient. Using machine learning algorithms is fast and noninvasive compared to the existing methods. The purpose of this research was to build an optimized model by machine learning algorithms that can improve the diagnosis accuracy and classification of patients at high risk of diabetes using retinal imaging.

scholarly journals Comparisons of Effective Fields of Two Ultra-Widefield Ophthalmoscopes, Optos 200Tx and Clarus 500

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Yoshitsugu Matsui ◽  
Atsushi Ichio ◽  
Asako Sugawara ◽  
Eriko Uchiyama ◽  
Hitomi Suimon ◽  
...  
Keyword(s):  
Retinal Imaging ◽  
Retinal Vessel ◽  
Effective Field ◽  
Eye Diseases ◽  
The Other ◽  
Retinal Images ◽  
Single Image ◽  
Depth Of Focus ◽  
Temporal Quadrant

Purpose. To compare the effective fields of the Optos 200Tx® and Clarus 500™, two ultra-widefield ophthalmoscopes, based on their ability to image branches of retinal vessel in the four retinal quadrants. Methods. Ninety retinal images from 90 patients with various eye diseases were studied. All patients had undergone 200° retinal imaging to obtain a single image of Optos (O) and the montage of two images of the Clarus (C). The highest number of traceable vessel branches in the four retinal quadrants was determined by two masked raters. An image was classified as “O > C” when the number of identifiable branch was greater in the Optos than the Clarus, as “O = C” when the number was equal and as “O < C” when the number was fewer in the Optos than the Clarus. Results. The appearance probability of “O > C” was significantly higher at the upper temporal quadrant than “O < C” (p<0.01 for both raters). In contrast, the appearance probability of “O < C” was significantly higher at the lower nasal quadrant than “O > C” (p<0.01 for both raters). There were no significant differences in the appearance probability between “O > C” and “O < C” at the other two retinal quadrants (p>0.50 for both raters). Conclusions. These results demonstrate that the effective field of views was different between the two devices at different retina quadrants. Further studies are needed to clarify possible factors such as artifacts by the eyelashes, differences in the depth of focus, motion of the device, and different locations of the images on the effective field of views.

scholarly journals Iterative-Trained Semi-Blind Deconvolution Algorithm to Compensate Straylight in Retinal Images

2021 ◽  
Vol 7 (4) ◽  
pp. 73
Author(s):  
Francisco J. Ávila ◽  
Jorge Ares ◽  
María C. Marcellán ◽  
María V. Collados ◽  
Laura Remón
Keyword(s):  
Healthy Subjects ◽  
Spatial Information ◽  
Blind Deconvolution ◽  
Imaging System ◽  
Retinal Imaging ◽  
Optical Quality ◽  
Retinal Images ◽  
Image Sharpness ◽  
Deconvolution Algorithm ◽  
Spread Function

The optical quality of an image depends on both the optical properties of the imaging system and the physical properties of the medium in which the light travels from the object to the final imaging sensor. The analysis of the point spread function of the optical system is an objective way to quantify the image degradation. In retinal imaging, the presence of corneal or cristalline lens opacifications spread the light at wide angular distributions. If the mathematical operator that degrades the image is known, the image can be restored through deconvolution methods. In the particular case of retinal imaging, this operator may be unknown (or partially) due to the presence of cataracts, corneal edema, or vitreous opacification. In those cases, blind deconvolution theory provides useful results to restore important spatial information of the image. In this work, a new semi-blind deconvolution method has been developed by training an iterative process with the Glare Spread Function kernel based on the Richardson-Lucy deconvolution algorithm to compensate a veiling glare effect in retinal images due to intraocular straylight. The method was first tested with simulated retinal images generated from a straylight eye model and applied to a real retinal image dataset composed of healthy subjects and patients with glaucoma and diabetic retinopathy. Results showed the capacity of the algorithm to detect and compensate the veiling glare degradation and improving the image sharpness up to 1000% in the case of healthy subjects and up to 700% in the pathological retinal images. This image quality improvement allows performing image segmentation processing with restored hidden spatial information after deconvolution.

scholarly journals A Deep Learning Approach for Retinal Image Feature Extraction

2021 ◽  
Vol 29 (4) ◽  
Author(s):  
Mohammed Enamul Hoque ◽  
Kuryati Kipli ◽  
Tengku Mohd Afendi Zulcaffle ◽  
Abdulrazak Yahya Saleh Al-Hababi ◽  
Dayang Azra Awang Mat ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Retinal Image ◽  
Image Data ◽  
Disease Diagnosis ◽  
Image Features ◽  
Image Feature ◽  
Diagnostic Tools ◽  
Retinal Images ◽  
Retinal Microvasculature

Retinal image analysis is crucially important to detect the different kinds of life-threatening cardiovascular and ophthalmic diseases as human retinal microvasculature exhibits remarkable abnormalities responding to these disorders. The high dimensionality and random accumulation of retinal images enlarge the data size, that creating complexity in managing and understating the retinal image data. Deep Learning (DL) has been introduced to deal with this big data challenge by developing intelligent tools. Convolutional Neural Network (CNN), a DL approach, has been designed to extract hierarchical image features with more abstraction. To assist the ophthalmologist in eye screening and ophthalmic disease diagnosis, CNN is being explored to create automatic systems for microvascular pattern analysis, feature extraction, and quantification of retinal images. Extraction of the true vessel of retinal microvasculature is significant for further analysis, such as vessel diameter and bifurcation angle quantification. This study proposes a retinal image feature, true vessel segments extraction approach exploiting the Faster RCNN. The fundamental Image Processing principles have been employed for pre-processing the retinal image data. A combined database assembling image data from different publicly available databases have been used to train, test, and evaluate this proposed method. This proposed method has obtained 92.81% sensitivity and 63.34 positive predictive value in extracting true vessel segments from the top first tier of colour retinal images. It is expected to integrate this method into ophthalmic diagnostic tools with further evaluation and validation by analysing the performance.

scholarly journals Advancing the Detection and Management of Diabetic Retinopathy with Ultra-widefield Retinal Imaging

2017 ◽  
Vol 10 (01) ◽  
pp. 23 ◽  
Author(s):  
David M Brown ◽  
Keyword(s):  
Diabetic Retinopathy ◽  
Wide Spectrum ◽  
Retinal Imaging ◽  
Standard Of Care ◽  
Fundus Photography ◽  
Eye Disease ◽  
Retinal Images ◽  
The Us ◽  
Diabetic Eye Disease ◽  
Underlying Mechanisms

The incidence of diabetes in the US population has increased more than fourfold over the last several decades and a high proportion of these patients manifest diabetic eye disease, including diabetic retinopathy (DR) and diabetic macular edema (DME). Ultra-widefield (UWF) retinal imaging has emerged as a valuable tool in the evolving standard of care for DR, providing essential visualization of ischemia and related pathology across the retina, particularly in the periphery, where these signs may appear earliest but may not be detected by conventional fundus photography. Multimodal UWF imaging has helped correlate changes in the periphery with DR progression, providing important guidance for treatment planning and facilitating improved understanding of the underlying mechanisms of disease. Rapid capture, immediate retrieval and efficient sharing of UWF retinal images support a wide spectrum of care settings—including teleophthalmology programs—and facilitate patient education.

scholarly journals Retinal Self Examination “Selfies” During a Pandemic

2021 ◽  
Vol 15 (1) ◽  
pp. 206-208
Author(s):  
Ben O’Keeffe ◽  
Sheng Chiong Hong ◽  
Renoh Chalakkal
Keyword(s):  
High Resolution ◽  
Clinical Setting ◽  
Retinal Imaging ◽  
Transmission Risk ◽  
Retinal Images ◽  
Imaging Device ◽  
Self Examination

The advancement of smartphone camera technology allowing a smaller, high-resolution forward-facing camera on a smartphone allows a user to see the image they are about to capture of themselves at arm’s length, therefore taking a ‘selfie’ image of themselves. The idea of a ‘selfie’ in a clinical setting is novel, but the exploration of this as a concept has been made necessary as COVID-19 infection and transmission risk is based on the proximity, that is, a susceptible person coming near to the person, who is infected. This report discusses an innovative smartphone-based device, oDocs nun IR, a retinal imaging device, as a tool for taking selfie retinal images/videos by patients, that could be later analyzed by the specialists/optometrists over the teleophthalmology portal.

scholarly journals Key factors in a rigorous longitudinal image-based assessment of retinopathy of prematurity

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tatiana R. Rosenblatt ◽  
Marco H. Ji ◽  
Daniel Vail ◽  
Cassie A. Ludwig ◽  
Ahmad Al-Moujahed ◽  
...  
Keyword(s):  
Retinopathy Of Prematurity ◽  
Kappa Statistic ◽  
Weighted Kappa ◽  
Image Features ◽  
Longitudinal Change ◽  
Retinal Images ◽  
Disease Trajectory ◽  
Vascular Tortuosity ◽  
Vessel Growth ◽  
Disease Stabilization

AbstractTo describe a database of longitudinally graded telemedicine retinal images to be used as a comparator for future studies assessing grader recall bias and ability to detect typical progression (e.g. International Classification of Retinopathy of Prematurity (ICROP) stages) as well as incremental changes in retinopathy of prematurity (ROP). Cohort comprised of retinal images from 84 eyes of 42 patients who were sequentially screened for ROP over 6 consecutive weeks in a telemedicine program and then followed to vascular maturation or treatment, and then disease stabilization. De-identified retinal images across the 6 weekly exams (2520 total images) were graded by an ROP expert based on whether ROP had improved, worsened, or stayed the same compared to the prior week’s images, corresponding to an overall clinical “gestalt” score. Subsequently, we examined which parameters might have influenced the examiner’s ability to detect longitudinal change; images were graded by the same ROP expert by image view (central, inferior, nasal, superior, temporal) and by retinal components (vascular tortuosity, vascular dilation, stage, hemorrhage, vessel growth), again determining if each particular retinal component or ROP in each image view had improved, worsened, or stayed the same compared to the prior week’s images. Agreement between gestalt scores and view, component, and component by view scores was assessed using percent agreement, absolute agreement, and Cohen’s weighted kappa statistic to determine if any of the hypothesized image features correlated with the ability to predict ROP disease trajectory in patients. The central view showed substantial agreement with gestalt scores (κ = 0.63), with moderate agreement in the remaining views. Of retinal components, vascular tortuosity showed the most overall agreement with gestalt (κ = 0.42–0.61), with only slight to fair agreement for all other components. This is a well-defined ROP database graded by one expert in a real-world setting in a masked fashion that correlated with the actual (remote in time) exams and known outcomes. This provides a foundation for subsequent study of telemedicine’s ability to longitudinally assess ROP disease trajectory, as well as for potential artificial intelligence approaches to retinal image grading, in order to expand patient access to timely, accurate ROP screening.

Inflammageing in the cardiovascular system: mechanisms, emerging targets, and novel therapeutic strategies

2020 ◽  
Vol 134 (17) ◽  
pp. 2243-2262
Author(s):  
Danlin Liu ◽  
Gavin Richardson ◽  
Fehmi M. Benli ◽  
Catherine Park ◽  
João V. de Souza ◽  
...  
Keyword(s):  
Cardiovascular Diseases ◽  
Cardiovascular System ◽  
Nlrp3 Inflammasome ◽  
Molecular Mechanisms ◽  
Molecular Targets ◽  
Therapeutic Interventions ◽  
Low Grade ◽  
Cardiovascular Research ◽  
Inflammatory Processes ◽  
Ach Receptors

Abstract In the elderly population, pathological inflammation has been associated with ageing-associated diseases. The term ‘inflammageing’, which was used for the first time by Franceschi and co-workers in 2000, is associated with the chronic, low-grade, subclinical inflammatory processes coupled to biological ageing. The source of these inflammatory processes is debated. The senescence-associated secretory phenotype (SASP) has been proposed as the main origin of inflammageing. The SASP is characterised by the release of inflammatory cytokines, elevated activation of the NLRP3 inflammasome, altered regulation of acetylcholine (ACh) nicotinic receptors, and abnormal NAD+ metabolism. Therefore, SASP may be ‘druggable’ by small molecule therapeutics targeting those emerging molecular targets. It has been shown that inflammageing is a hallmark of various cardiovascular diseases, including atherosclerosis, hypertension, and adverse cardiac remodelling. Therefore, the pathomechanism involving SASP activation via the NLRP3 inflammasome; modulation of NLRP3 via α7 nicotinic ACh receptors; and modulation by senolytics targeting other proteins have gained a lot of interest within cardiovascular research and drug development communities. In this review, which offers a unique view from both clinical and preclinical target-based drug discovery perspectives, we have focused on cardiovascular inflammageing and its molecular mechanisms. We have outlined the mechanistic links between inflammageing, SASP, interleukin (IL)-1β, NLRP3 inflammasome, nicotinic ACh receptors, and molecular targets of senolytic drugs in the context of cardiovascular diseases. We have addressed the ‘druggability’ of NLRP3 and nicotinic α7 receptors by small molecules, as these proteins represent novel and exciting targets for therapeutic interventions targeting inflammageing in the cardiovascular system and beyond.

Deficits in Selective Attention Alter Gait in Frail Older Adults

GeroPsych ◽  
2016 ◽  
Vol 29 (1) ◽  
pp. 29-36 ◽  
Author(s):  
Véronique Cornu ◽  
Jean-Paul Steinmetz ◽  
Carine Federspiel
Keyword(s):  
Older Adults ◽  
Nursing Home ◽  
Selective Attention ◽  
Dual Task ◽  
Nursing Home Residents ◽  
Gait Rehabilitation ◽  
Rehabilitation Programs ◽  
Gait Parameters ◽  
Growing Body ◽  
Task Conditions

Abstract. A growing body of research demonstrates an association between gait disorders, falls, and attentional capacities in older adults. The present work empirically analyzes differences in gait parameters in frail institutionalized older adults as a function of selective attention. Gait analysis under single- and dual-task conditions as well as selective attention measures were collected from a total of 33 nursing-home residents. We found that differences in selective attention performances were related to the investigated gait parameters. Poorer selective attention performances were associated with higher stride-to-stride variabilities and a slowing of gait speed under dual-task conditions. The present findings suggest a contribution of selective attention to a safe gait. Implications for gait rehabilitation programs are discussed.

Sign in / Sign up

Export Citation Format

Share Document