A smartphone ocular alignment measurement app in school screening for strabismus

Abstract Background Strabismus is the leading risk factor for amblyopia, which should be early detected for minimized visual impairment. However, traditional school screening for strabismus can be challenged due to several factors, most notably training, mobility and cost. The purpose of our study is to evaluate the feasibility of using a smartphone application in school vision screening for detection of strabismus. Methods The beta smartphone application, EyeTurn, can measure ocular misalignment by computerized Hirschberg test. The application was used by a school nurse in a routine vision screening for 133 elementary school children. All app measurements were reviewed by an ophthalmologist to assess the rate of successful measurement and were flagged for in-person verification with prism alternating cover test (PACT) using a 2.4Δ threshold (root mean squared error of the app). A receiver operating characteristic (ROC) curve was used to determine the best sensitivity and specificity for an 8Δ threshold (recommended by AAPOS) with the PACT measurement as ground truth. Results The nurse obtained at least one successful app measurement for 93% of children (125/133). 40 were flagged for PACT, of which 6 were confirmed to have strabismus, including 4 exotropia (10△, 10△, 14△ and 18△), 1 constant esotropia (25△) and 1 accommodative esotropia (14△). Based on the ROC curve, the optimum threshold for the app to detect strabismus was determined to be 3.0△, with the best sensitivity (83.0%), specificity (76.5%). With this threshold the app would have missed one child with accommodative esotriopia, whereas conventional screening missed 3 cases of intermittent extropia. Conclusions Results support feasibility of use of the app by personnel without professional training in routine school screenings to improve detection of strabismus.

Download Full-text

A Smartphone Ocular Alignment Measurement App in School Screening for Strabismus

10.21203/rs.3.rs-125162/v1 ◽

2020 ◽

Author(s):

Wenbo Cheng ◽

Marissa H. Lynn ◽

Shrinivas Pundlik ◽

Cheryl Almeida ◽

Gang Luo ◽

...

Keyword(s):

Roc Curve ◽

Professional Training ◽

Mean Squared Error ◽

Ground Truth ◽

Smartphone Application ◽

Vision Screening ◽

School Screening ◽

School Vision ◽

Successful Measurement ◽

Person Verification

Abstract Background: Strabismus is the leading risk factor for amblyopia, which should be early detected for minimized visual impairment. However, traditional school screening for strabismus can be challenged due to several factors, most notably training, mobility and cost. The purpose of our study is to evaluate the feasibility of using a smartphone application in school vision screening for detection of strabismus.Methods: The beta smartphone application, EyeTurn, can measure ocular misalignment by computerized Hirschberg test. The application was used by a school nurse in a routine vision screening for 133 elementary school children. All app measurements were reviewed by an ophthalmologist to assess the rate of successful measurement and were flagged for in-person verification with prism alternating cover test (PACT) using a 2.4Δ threshold (root mean squared error of the app). A receiver operating characteristic (ROC) curve was used to determine the best sensitivity and specificity for an 8Δ threshold (recommended by AAPOS) with the PACT measurement as ground truth.Results: The nurse obtained at least one successful app measurement for 93% of children (125/133). 40 were flagged for PACT, of which 6 were confirmed to have strabismus, including 4 exotropia (10△, 10△, 14△ and 18△), 1 constant esotropia (25△) and 1 accommodative esotropia (14△). Based on the ROC curve, the optimum threshold for the app to detect strabismus was determined to be 3.0△, with the best sensitivity (83.0%), specificity (76.5%). With this threshold the app would have missed one child with accommodative esotriopia, whereas conventional screening missed 3 cases of intermittent extropia.Conclusions: Results support feasibility of use of the app by personnel without professional training in routine school screenings to improve detection of strabismus.

Download Full-text

Experimental Evaluation of Computer Vision and Machine Learning-Based UAV Detection and Ranging

Drones ◽

10.3390/drones5020037 ◽

2021 ◽

Vol 5 (2) ◽

pp. 37

Author(s):

Bingsheng Wei ◽

Martin Barczyk

Keyword(s):

Machine Learning ◽

Mean Squared Error ◽

Tracking System ◽

Ground Truth ◽

White Background ◽

Cascade Classifier ◽

Detection Algorithms ◽

Squared Error ◽

Test Conditions ◽

Video Feed

We consider the problem of vision-based detection and ranging of a target UAV using the video feed from a monocular camera onboard a pursuer UAV. Our previously published work in this area employed a cascade classifier algorithm to locate the target UAV, which was found to perform poorly in complex background scenes. We thus study the replacement of the cascade classifier algorithm with newer machine learning-based object detection algorithms. Five candidate algorithms are implemented and quantitatively tested in terms of their efficiency (measured as frames per second processing rate), accuracy (measured as the root mean squared error between ground truth and detected location), and consistency (measured as mean average precision) in a variety of flight patterns, backgrounds, and test conditions. Assigning relative weights of 20%, 40% and 40% to these three criteria, we find that when flying over a white background, the top three performers are YOLO v2 (76.73 out of 100), Faster RCNN v2 (63.65 out of 100), and Tiny YOLO (59.50 out of 100), while over a realistic background, the top three performers are Faster RCNN v2 (54.35 out of 100, SSD MobileNet v1 (51.68 out of 100) and SSD Inception v2 (50.72 out of 100), leading us to recommend Faster RCNN v2 as the recommended solution. We then provide a roadmap for further work in integrating the object detector into our vision-based UAV tracking system.

Download Full-text

Unexpectedly high prevalence of asthenopia in Australian school children identified by the CISS survey tool

BMC Ophthalmology ◽

10.1186/s12886-020-01642-3 ◽

2020 ◽

Vol 20 (1) ◽

Author(s):

Barbara M. Junghans ◽

Serap Azizoglu ◽

Sheila G. Crewther

Keyword(s):

Handheld Devices ◽

Vision Screening ◽

School Students ◽

Visual Discomfort ◽

Survey Tool ◽

School Aged Children ◽

School Vision ◽

Accommodative Convergence ◽

The Mean ◽

General School

Abstract Background To date there have been few systematic attempts to establish the general prevalence of asthenopia in unselected populations of school-aged children. Thus, the aim of this study was to determine whether the incorporation of Borsting et al’s 2003 Revised Convergence-Insufficiency Symptom Survey (CISS) into a general school vision screening could aid in the identification of children with visual discomfort and indicate the need for further investigation. Methods Vision screening of an unselected middle school population investigated and analysed the incidence of self-reported nearwork-related visual discomfort via the CISS along with distance and near visual acuities plus non-cycloplegic autorefraction using a Shin-Nippon NVision-K 5001. Results Of the 384 unselected students approached in Grades 6–9, 353 participated (92.2%, mean 13.2 ± 1.4 years). The mean CISS score for the population without amblyopia and/or strabismus (96.0% of all students) was 16.8 ± 0.6, i.e., 45% of students in this cohort had CISS scores greater than one standard deviation above the mean found by Borsting et al. in 2003 during their validation study of the CISS on 9 to 18 year old children without binocular anomalies. Regression analyses indicated significantly higher (p < 0.001) mean CISS scores for the 3.2% who were hyperopes ≥ + 2.00D by non-cycloplegic autorefraction (27.7 ± 14.7) and for those who were amblyopic (24.3 ± 6.6) or strabismic (34.0 ± 9.8). The mean CISS score of 31.6 ± 9.0 for non-amblyopic/strabismic students having near vision poorer than 0.1 LogMAR was significantly higher (p < 0.001) than for those with good acuity. Conclusion The most important finding of this study was the high incidence of asthenopia in an unselected population and that refractive status per se was not a major contributor to CISS scores. The results highlight the usefulness of the CISS questionnaire for assessment of visual discomfort in school vision screenings and the need for future exploration of near binocular vision status as a potential driver of asthenopia in school students, especially given current trends for frequent daily use of computers and handheld devices and necessarily prolonged accommodative-convergence effort at near, both at school and at home.

Download Full-text

School vision screening programmes in reducing uncorrected refractive error among children in Low and Middle-Income countries-LMIC (systematic review)

Advances in Ophthalmology & Visual System ◽

10.15406/aovs.2020.10.00392 ◽

2020 ◽

Vol 10 (4) ◽

pp. 91-105

Author(s):

Abraham Opare ◽

Leila H Abdullahi ◽

Deon Minnies ◽

Colin Cook ◽

Maylene Shung-King ◽

...

Keyword(s):

Academic Performance ◽

School Children ◽

Refractive Error ◽

Positive Impact ◽

Cost Effective ◽

Vision Screening ◽

Middle Income ◽

Middle Income Countries ◽

School Vision ◽

Uncorrected Refractive Error

ackground: The prevalence of uncorrected refractive error among school-age children is on the rise with detrimental effect on academic performance and socio-economic status of those affected. School vision screening programmes appear to be an effective way of identifying children with uncorrected refractive errors so early intervention can be made. Despite the increasing popularity of school vision screening programmes over the past few years, there is a lot of debate on its effectiveness in reducing the proportion of children with uncorrected refractive error in the long term, especially in settings where resources are limited. Some studies argue that school vision screening programmes are effective while other studies have reported otherwise. The purpose of this systematic review was to assess the effectiveness of school vision screening programmes in reducing uncorrected refractive error among children in low and middle income countries using evidence from published studies. Methods and findings: A comprehensive and systematic strategy was used to search various databases including PubMed, Cochrane Central Register of Controlled Trials (CENTRAL) which contains the Cochrane Eyes and vision Trial Register, the Cochrane Library, Medline (1980-2018), CINAHL, Academic Search Premier, Web of Science, the WHO’s Library Information System, Africa-Wide and Scopus. The search was restricted to articles published in English. Randomized control trials, cross-sectional studies, case-control studies and cohort studies were included in this review. Participants included school children with refractive error. Full-text review of search results, data extraction and risk of bias assessment was done by two independent reviewers. The certainty of the evidence was assessed using the GRADE approach and data were pooled using the random-effect model. Thirty studies met the inclusion criteria. This review found moderate certainty evidence indicating that school vision screenings may be effective in reducing uncorrected refractive error among school children by 81% (95% CI: 77%; 84%), 24% (95% CI: 13%; 35%) and 20% (95% CI: 18%; 22%) at two, six, and more than six months respectively after its introduction. Results: Results of this review also suggest that school vision screening may be effective in achieving 54% (95% CI: 25%; 100%), 57% (95% CI: 46%; 70%), 37% (95% CI: 26%; 52%), and 32% (95% CI: 14%; 72%) spectacle-wear compliance among school children at less than three months, at three months, at six months and at more than six months respectively after its introduction (low to moderate certainty evidence). This review further found moderate to high certainty evidence indicating that school vision screening, together with provision of spectacles, may be relatively cost effective, safe and has a positive impact on the academic performance of school children. Conclusion: The findings of this review show that school vision screening, together with provision of spectacles, may be a safe and cost-effective way of reducing the proportion of children with uncorrected refractive error, with long-term positive impact on academic performance of children. Most of the studies included in this review were, however, conducted in Asia. Research to investigate the effectiveness of school vision screening programmes in other parts of the world like Africa where few studies have been conducted is highly recommended

Download Full-text

A Theoretical Framework for Estimating Swarm Success Probability Using Scouts

International Journal of Swarm Intelligence Research ◽

10.4018/jsir.2010100102 ◽

2010 ◽

Vol 1 (4) ◽

pp. 17-45

Author(s):

Antons Rebguns ◽

Diana F. Spears ◽

Richard Anderson-Sprecher ◽

Aleksey Kletsov

Keyword(s):

Mean Squared Error ◽

Success Probability ◽

Ground Truth ◽

Theoretical Framework ◽

Bernoulli Trials ◽

Lennard Jones ◽

Squared Error ◽

The Mean ◽

The Bayesian Approach ◽

Bayesian Formula

This paper presents a novel theoretical framework for swarms of agents. Before deploying a swarm for a task, it is advantageous to predict whether a desired percentage of the swarm will succeed. The authors present a framework that uses a small group of expendable “scout” agents to predict the success probability of the entire swarm, thereby preventing many agent losses. The scouts apply one of two formulas to predict – the standard Bernoulli trials formula or the new Bayesian formula. For experimental evaluation, the framework is applied to simulated agents navigating around obstacles to reach a goal location. Extensive experimental results compare the mean-squared error of the predictions of both formulas with ground truth, under varying circumstances. Results indicate the accuracy and robustness of the Bayesian approach. The framework also yields an intriguing result, namely, that both formulas usually predict better in the presence of (Lennard-Jones) inter-agent forces than when their independence assumptions hold.

Download Full-text