Search

Previous studies have explored the associations of retinal vessel calibre, measured from retinal photographs or fundus images using semi-automated computer programs, with cognitive impairment and dementia, supporting the concept that retinal blood vessels reflect microvascular changes in the brain. Recently, artificial intelligence deep-learning algorithms have been developed for the fully automated assessment of retinal vessel calibres. Therefore, we aimed to determine whether deep-learning-based retinal vessel calibre measurements are predictive of risk of cognitive decline and dementia. We conducted a prospective study recruiting participants from memory clinics at the National University Hospital and St. Luke’s Hospital in Singapore; all participants had comprehensive clinical and neuropsychological examinations at baseline and annually for up to 5 years. Fully automated measurements of retinal arteriolar and venular calibres from retinal fundus images were estimated using a deep-learning system. Cox regression models were then used to assess the relationship between baseline retinal vessel calibre and the risk of cognitive decline and developing dementia, adjusting for age, gender, ethnicity, education, cerebrovascular disease status, hypertension, hyperlipidemia, diabetes, and smoking. A total of 491 participants were included in this study, of whom 254 developed cognitive decline over 5 years. In multivariable models, narrower retinal arteriolar calibre (hazard ratio per standard deviation decrease = 1.258, P = 0.008) and wider retinal venular calibre (hazard ratio per standard deviation increase = 1.204, P = 0.037) were associated with increased risk of cognitive decline. Among participants with cognitive impairment but no dementia at baseline (n = 212), 44 progressed to have incident dementia; narrower retinal arteriolar calibre was also associated with incident dementia (hazard ratio per standard deviation decrease = 1.624, P = 0.021). In summary, deep-learning-based measurement of retinal vessel calibre was associated with risk of cognitive decline and dementia.

BackgroundIt is generally recommended to keep the wrist joint mildly dorsiflexed during radial artery catheterisation. However, wrist dorsiflexion might decrease the success rate of radial artery catheterisation with dynamic needle tip positioning technique. Therefore, we assessed the success rates of two groups with or without wrist dorsiflexion by 5 cm wrist elevation in adult patients.MethodsThis randomised controlled clinical trial was performed between March and December 2018 in the First Affiliated Hospital of Shantou University Medical College, China. We recruited 120 adult patients undergoing major surgical procedures and randomly allocated them into two groups: dorsiflexion group (group D) and neutral group (group N). The primary outcome was first-attempt success rates of two groups. Secondary outcomes were overall success rates within 5 min; numbers of insertion and cannulation attempts; overall catheterisation time; duration of localisation, insertion and cannulation; and complication rates of catheterisation.ResultsFirst-attempt success rate was 88.3% in group D and 81.7% in group N (p=0.444). The overall success rate within 5 min was 93.3% in group D compared with 90.0% in group N (p=0.743). Numbers of insertion and cannulation attempts, overall catheterisation time, duration of localisation and insertion, and complication rates did not show a significant difference between the two groups. Cannulation time was longer in group N (35.68 s) than that in group D (26.19 s; pConclusionWrist dorsiflexion may not be a necessity for ultrasound-guided radial artery catheterisation using dynamic needle tip positioning technique in adult patients.Trial registration numberChiCTR1800015262.

Retinal blood vessels provide information on the risk of cardiovascular disease (CVD). Here, we report the development and validation of deep-learning models for the automated measurement of retinal-vessel calibre in retinal photographs, using diverse multiethnic multicountry datasets that comprise more than 70,000 images. Retinal-vessel calibre measured by the models and by expert human graders showed high agreement, with overall intraclass correlation coefficients of between 0.82 and 0.95. The models performed comparably to or better than expert graders in associations between measurements of retinal-vessel calibre and CVD risk factors, including blood pressure, body-mass index, total cholesterol and glycated-haemoglobin levels. In retrospectively measured prospective datasets from a population-based study, baseline measurements performed by the deep-learning system were associated with incident CVD. Our findings motivate the development of clinically applicable explainable end-to-end deep-learning systems for the prediction of CVD on the basis of the features of retinal vessels in retinal photographs. Deep-learning models for the automated measurement of retinal-vessel calibre in retinal photographs perform comparably to or better than expert graders in associations of measurements of retinal-vessel calibre with cardiovascular risk factors.

To determine the relationship between baseline retinal-vessel calibers computed by a deep-learning system and the risk of normal tension glaucoma (NTG) progression.Prospective cohort study.Three hundred and ninety eyes from 197 patients with NTG were followed up for at least 24 months. Retinal-vessel calibers (central retinal arteriolar equivalent [CRAE] and central retinal venular equivalent [CRVE]) were computed from fundus photographs at baseline using a previously validated deep-learning system. Retinal nerve fiber layer (RNFL) thickness and visual field (VF) were evaluated semiannually. The Cox proportional-hazards model was used to evaluate the relationship of baseline retinal-vessel calibers to the risk of glaucoma progression.Over a mean follow-up period of 34.36 ± 5.88 months, 69 NTG eyes (17.69%) developed progressive RNFL thinning and 22 eyes (5.64%) developed VF deterioration. In the multivariable Cox regression analysis adjusting for age, gender, intraocular pressure, mean ocular perfusion pressure, systolic blood pressure, axial length, standard automated perimetry mean deviation, and RNFL thickness, narrower baseline CRAE (hazard ratio per SD decrease [95% confidence interval], 1.36 [1.01-1.82]) and CRVE (1.35 [1.01-1.80]) were associated with progressive RNFL thinning and narrower baseline CRAE (1.98 [1.17-3.35]) was associated with VF deterioration.In this study, each SD decrease in the baseline CRAE or CRVE was associated with a more than 30% increase in the risk of progressive RNFL thinning and a more than 90% increase in the risk of VF deterioration during the follow-up period. Baseline attenuation of retinal vasculature in NTG eyes was associated with subsequent glaucoma progression. High-throughput deep-learning-based retinal vasculature analysis demonstrated its clinical utility for NTG risk assessment.

Ischemic stroke is a leading cause of death and long-term disability that is difficult to predict reliably. Retinal fundus photography has been proposed for stroke risk assessment, due to its non-invasiveness and the similarity between retinal and cerebral microcirculations, with past studies claiming a correlation between venular caliber and stroke risk. However, it may be that other retinal features are more appropriate. In this paper, extensive experiments with deep learning on six retinal datasets are described. Feature isolation involving segmented vascular tree images is applied to establish the effectiveness of vessel caliber and shape alone for stroke classification, and dataset ablation is applied to investigate model generalizability on unseen sources. The results suggest that vessel caliber and shape could be indicative of ischemic stroke, and sourcespecific features could influence model performance.

Summary Background Screening for chronic kidney disease is a challenge in community and primary care settings, even in high-income countries. We developed an artificial intelligence deep learning algorithm (DLA) to detect chronic kidney disease from retinal images, which could add to existing chronic kidney disease screening strategies. Methods We used data from three population-based, multiethnic, cross-sectional studies in Singapore and China. The Singapore Epidemiology of Eye Diseases study (SEED, patients aged ≥40 years) was used to develop (5188 patients) and validate (1297 patients) the DLA. External testing was done on two independent datasets: the Singapore Prospective Study Program (SP2, 3735 patients aged ≥25 years) and the Beijing Eye Study (BES, 1538 patients aged ≥40 years). Chronic kidney disease was defined as estimated glomerular filtration rate less than 60 mL/min per 1·73m2. Three models were trained: 1) image DLA; 2) risk factors (RF) including age, sex, ethnicity, diabetes, and hypertension; and 3) hybrid DLA combining image and RF. Model performances were evaluated using the area under the receiver operating characteristic curve (AUC). Findings In the SEED validation dataset, the AUC was 0·911 for image DLA (95% CI 0·886 −0·936), 0·916 for RF (0·891–0·941), and 0·938 for hybrid DLA (0·917–0·959). Corresponding estimates in the SP2 testing dataset were 0·733 for image DLA (95% CI 0·696–0·770), 0·829 for RF (0·797–0·861), and 0·810 for hybrid DLA (0·776–0·844); and in the BES testing dataset estimates were 0·835 for image DLA (0·767–0·903), 0·887 for RF (0·828–0·946), and 0·858 for hybrid DLA (0·794–0·922). AUC estimates were similar in subgroups of people with diabetes (image DLA 0·889 [95% CI 0·850–0·928], RF 0·899 [0·862–0·936], hybrid 0·925 [0·893–0·957]) and hypertension (image DLA 0·889 [95% CI 0·860–0·918], RF 0·889 [0·860–0·918], hybrid 0·918 [0·893–0·943]). Interpretation A retinal image DLA shows good performance for estimating chronic kidney disease, underlying the feasibility of using retinal photography as an adjunctive or opportunistic screening tool for chronic kidney disease in community populations. Funding National Medical Research Council, Singapore.

Over-fitting is a common issue of training deep convolutional neural network especially when the dataset is limited. In this work, we propose a patch-level regularizer to force a convolutional neural network to learn many sub-models during training, and aggregate these models during testing. This approach proves to be robust and noise tolerant as our regularizer exposes small patches of an image to the network to learn all the features equally during training. The regularizer can be easily applied to the convolutional neural networks to further improve their classification performance. Experiment results on publicly available datasets demonstrate consistent improvement over existing regularizers.

Vessel type classification is a preliminary step in quantifying the severity of various diseases. This paper proposes DBA, a simple yet effective vessel type classification method based on the principle that arteries are brighter than veins at the local scale. The weighted local difference of the red channel intensity of the main trunk of each vessel is compared with that of its two immediately neighbouring vessels, a feature that is highly correlated with vessel-rectified oxygen capacity, and in turn, vessel type. Experiments on the publicly-available INSPIRE-AVR and DRIVE datasets obtained average vessel accuracies of 0.9217/0.9071, and average pixel accuracies of 0.9602/0.9634 respectively, with particular effectiveness on images with low contrast, non-uniform illumination and colour variation confirmed on the SiMES 1 dataset.

Previous clutter metrics have less than the desired accuracy in predicting targeting performance, in this paper, a structural difference based image clutter metric is proposed based on the given definition of image clutter metric. According to the sensitivity of human visual perception to image structural information, a structural similarity measure between the target and clutter images is firstly established. Previous clutter metrics not considering brain cognitive characteristics, we define an information content weight measure by introducing the widely accepted brain cognitive information extracting model in the field of image quality assessment (IQA), and then, pool the structural similarity measure to be a clutter metric, which can be entitled BSD metric. Comparative field tests show that BSD metric makes a more significant improvement than previously proposed metrics in predicting target acquisition performance including detection probability and search time.

There exist complex gray mapping relationships among infrared and visible images because of the different imaging mechanisms. The difficulty of infrared and visible image registration is to find a reasonable similarity definition. In this paper, we develop a novel image similarity called implicit line segment similarity(ILS) and a registration algorithm of infrared and visible images based on ILS. Essentially, the algorithm achieves image registration by aligning the corresponding line segment features in two images. First, we extract line segment features and record their coordinate positions in one of the images, and map these line segments into the second image based on the geometric transformation model. Then we iteratively maximize the degree of similarity between the line segment features and correspondence regions in the second image to obtain the model parameters. The advantage of doing this is no need directly measuring the gray similarity between the two images. We adopt a multi-resolution analysis method to calculate the model parameters from coarse to fine on Gaussian scale space. The geometric transformation parameters are finally obtained by the improved Powell algorithm. Comparative experiments demonstrate that the proposed algorithm can effectively achieve the automatic registration for infrared and visible images, and under considerable accuracy it makes a more significant improvement on computational efficiency and anti-noise ability than previously proposed algorithms.

Previous image clutter metrics were proposed on the thought that clutter was just a perceptual effect, while we identify clutter as both perceptual and cognitive effects. Under this identification, we give a new definition of image clutter metric by analyzing the research results in the fields of visual psychology and psychophysics. According to the definition, we further put forward a DisSIMilarity (DSIM) based image clutter metric, which can also be taken as a kind of HVS-based signal-to-clutter ratio. The earlier image clutter metrics produced limited success in predicting targeting performance mainly since they did not consider brain cognitive characteristics. We develop a brain cognitive dissimilarity measure (BCDM) as a quantitative estimate of the selection weights which are allocated by brain attentional mechanism to affect visual selection processes. A human vision perceptual dissimilarity measure (VPDM), fully embodying vision perceptual properties, is first established between the target and clutter images, and then we utilize the BCDM between the two images as selection weights to pool the VPDM to be a clutter metric, which can be called DSIM metric. The metric is tested in Search_2 dataset provided by TNO Human Factors Research Institute of Netherlands. Error analysis and correlation tests demonstrate that the DSIM metric makes a more significant improvement than previously proposed metrics in predicting 62 observers' targeting performances including detection probability, false alarm probability and search time.

To compare the effects of propofol and inhalation anesthesia on the incidence of early postoperative cognitive dysfunction (POCD) in elderly patients undergoing noncardiac surgeries.PubMed, Cochrane Library, CBM, CNKI, Wanfang data and VIP Database (by October 2012) were searched for randomized controlled trials (RCTs) comparing propofol and inhalation anesthesia for their impact on the incidence of early POCD in elderly patients undergoing noncardiac surgeries. After data extraction and quality evaluation, Stata 12.0 software was used for statistical data analysis.Thirteen RCTs, including 2 comparing propofol with xenon, 7 comparing propofol with sevoflurane, and 4 comparing propofol with isoflurane were obtained, involving a total of 753 patients. The odds ratio of early POCD incidence between patients with propofol anesthesia and those with xenon anesthesia, sevoflurane anesthesia, and isoflurane anesthesia were 1.62 (95% CI 0.81-3.23, P=0.533), 0.67 (95% CI 0.39-1.14, P=0.830), and 0.20 (95% CI 0.08-0.50, P=0.925), respectively. Overall, the odds ratio of early POCD incidence between propofol anesthesia and inhalation anesthesia was 0.68 (95% CI 0.47-0.98, P=0.189). Egger's test showed a publication bias of the RCTs retrieved (P=0.011).Compared with inhalation anesthesia, propofol anesthesia is associated with a lower incidence of early POCD in elderly patients, but this conclusion needs to be further verified by more well-designed large-scale RCTs.

Visual tracking is a critical task in many computer vision applications such as surveillance, vehicle tracking, and motion analysis. The challenges in designing a robust visual tracking algorithm are caused by the presence of background clutter, occlusion, and illumination changes. In this paper, we propose a visual tracking algorithm in a particle filter framework to overcome these three challenging issues. Particle filter is an inference technique for estimating the unknown motion state from a noisy collection of observations, so we employ particle filter to learn the trajectory of a target. The proposed algorithm depends on the learned trajectory to predict the position of a target at a new frame, and corrects the predication by a process that can be entitled field transition. At the beginning of the tracking stage, a set of disturbance templates around the target template are accurately selected and defined as particles. During tracking, a position of the tracked target is firstly predicted based on the learned motion state, and then we take the normalized cross-correlation coefficient as a level to select the most suitable field transition parameters of the predicted position from the corresponding parameters of the particles. After judging the target is not occluded, we apply the named field transition with the selected parameters to compensate the predicted position to the accurate location of the target, meanwhile, we make use of the calculated cross-correlation coefficient as a posterior knowledge to update the weights of all the particles for the next prediction. In order to evaluate the performance of the proposed tracking algorithm, we test the approach on challenging sequences involving heavy background clutter, severe occlusions, and drastic illumination changes. Comparative experiments have demonstrated that this method makes a more significant improvement in efficiency and accuracy than two previously proposed algorithms: the mean shift tracking algorithm (MS) and the covariance tracking algorithm (CT).