Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 4 de 4
Filter
Add more filters










Language
Publication year range
1.
Ophthalmol Sci ; 2(4): 100197, 2022 Dec.
Article in English | MEDLINE | ID: mdl-36531577

ABSTRACT

Purpose: A deep learning model was developed to detect nonexudative macular neovascularization (neMNV) using OCT B-scans. Design: Retrospective review of a prospective, observational study. Participants: Normal control eyes and patients with age-related macular degeneration (AMD) with and without neMNV. Methods: Swept-source OCT angiography (SS-OCTA) imaging (PLEX Elite 9000, Carl Zeiss Meditec, Inc) was performed using the 6 × 6-mm scan pattern. Individual B-scans were annotated to distinguish between drusen and the double-layer sign (DLS) associated with the neMNV. The machine learning model was tested on a dataset graded by humans, and model performance was compared with the human graders. Main Outcome Measures: Intersection over Union (IoU) score was measured to evaluate segmentation network performance. Area under the receiver operating characteristic curve values, sensitivity, specificity, and positive predictive value (PPV) and negative predictive value (NPV) were measured to assess the performance of the final classification performance. Chance-corrected agreement between the algorithm and the human grader determinations was measured with Cohen's kappa. Results: A total of 251 eyes from 210 patients, including 182 eyes with DLS and 115 eyes with drusen, were used for model training. Of 125 500 B-scans, 6879 B-scans were manually annotated. A vision transformer segmentation model was built to extract DLS and drusen from B-scans. The extracted prediction masks from all B-scans in a volume were projected to an en face image, and an eye-level projection map was obtained for each eye. A binary classification algorithm was established to identify eyes with neMNV from the projection map. The algorithm achieved 82%, 90%, 79%, and 91% sensitivity, specificity, PPV, and NPV, respectively, on a separate test set of 100 eyes that were evaluated by human graders in a previous study. The area under the curve value was calculated as 0.91 (95% confidence interval, 0.85-0.98). The results of the algorithm showed excellent agreement with the senior human grader (kappa = 0.83, P < 0.001) and moderate agreement with the junior grader consensus (kappa = 0.54, P < 0.001). Conclusions: Our network (code is available at https://github.com/uw-biomedical-ml/double_layer_vit) was able to detect the presence of neMNV from structural B-scans alone by applying a purely transformer-based model.

2.
Article in English | MEDLINE | ID: mdl-19163827

ABSTRACT

Eye movements are utilized in many scientific studies as a probe that reflects the neural representation of 3 dimensional extrapersonal space. This study proposes a method to accurately measure the roll component of eye movements under the conditions in which the pupil diameter changes. Generally, the iris pattern matching between a reference and a test iris image is performed to estimate roll angle of the test image. However, iris patterns are subject to change when the pupil size changes, thus resulting in less accurate roll angle estimation if the pupil sizes in the test and reference images are different. We characterized non-uniform iris pattern contraction/expansion caused by pupil dilation/constriction, and developed an algorithm to convert an iris pattern with an arbitrary pupil size into that with the same pupil size as the reference iris pattern. It was demonstrated that the proposed method improved the accuracy of the measurement of roll eye movement by up to 76.9%.


Subject(s)
Eye Movements/physiology , Image Interpretation, Computer-Assisted/methods , Iris/anatomy & histology , Iris/physiology , Ophthalmoscopy/methods , Pattern Recognition, Automated/methods , Video Recording/methods , Algorithms , Humans , Image Enhancement/methods , Reproducibility of Results , Sensitivity and Specificity
3.
Psicol. esc. educ ; 11(n.esp): 59-69, dez.2007. ilus, tab
Article in English | Index Psychology - journals | ID: psi-36602

ABSTRACT

This paper proposes a framework for designing and improving learning environment for creativity in engineering. The framework consists of the following three components: instructional design based on knowledge from psychology, development of systems for supporting creative activities, and objective evaluation of learning results related to creativity. Based on that framework, we design and practice course based in the programation of a robot at a Japan University in the 2004 academic year. As a result, we confirm the following two advantages of our framework: learners' idea generation skills were improved and their meta-cognitive activities were also activated. In the 2005 academic year, we improve the course based on 2004 results. As a result, we confirm that the number of uploads of activity data from students have increased in the 2005 course, students' reflection sheets have become more detailed, and their volume of information have also increased.(AU)


Esse artigo propõe uma estrutura para projetar e implementar meios de aprendizagem da criatividade na engenharia. A estrutura é composta por três componentes: modelos instrucionais baseados no conhecimento da psicologia, desenvolvimento de sistemas para apoiar atividades criativas e avaliação objetiva de resultados relacionados com a criatividade no aprendizado. Baseado nessa estrutura, projetou-se e testou-se um curso baseado na programação de um robô em uma Universidade Japonesa em 2004. Como resultado, confirmaram-se duas vantagens da estrutura escolhida: a habilidade dos estudantes para gerar idéias foi ampliada e ativaram suas habilidades metacognitivas. No ano de 2005, o curso foi estruturado e implementado a partir dos resultados observados no curso de 2004. Como resultado final, confirmou-se que o número de atividades realizadas pelos alunos cresceu no curso de 2005. Os relatórios dos alunos se tornaram mais detalhados, com maior quantidade de informações descritas neles.(AU)


Subject(s)
Humans , Creativity , Learning , Knowledge , Cognition
4.
Psicol. esc. educ ; 11(n.esp): 59-69, dez. 2007. ilus, tab
Article in English | LILACS | ID: lil-484733

ABSTRACT

This paper proposes a framework for designing and improving learning environment for creativity in engineering. The framework consists of the following three components: instructional design based on knowledge from psychology, development of systems for supporting creative activities, and objective evaluation of learning results related to creativity. Based on that framework, we design and practice course based in the programation of a robot at a Japan University in the 2004 academic year. As a result, we confirm the following two advantages of our framework: learners' idea generation skills were improved and their meta-cognitive activities were also activated. In the 2005 academic year, we improve the course based on 2004 results. As a result, we confirm that the number of uploads of activity data from students have increased in the 2005 course, students' reflection sheets have become more detailed, and their volume of information have also increased.


Esse artigo propõe uma estrutura para projetar e implementar meios de aprendizagem da criatividade na engenharia. A estrutura é composta por três componentes: modelos instrucionais baseados no conhecimento da psicologia, desenvolvimento de sistemas para apoiar atividades criativas e avaliação objetiva de resultados relacionados com a criatividade no aprendizado. Baseado nessa estrutura, projetou-se e testou-se um curso baseado na programação de um robô em uma Universidade Japonesa em 2004. Como resultado, confirmaram-se duas vantagens da estrutura escolhida: a habilidade dos estudantes para gerar idéias foi ampliada e ativaram suas habilidades metacognitivas. No ano de 2005, o curso foi estruturado e implementado a partir dos resultados observados no curso de 2004. Como resultado final, confirmou-se que o número de atividades realizadas pelos alunos cresceu no curso de 2005. Os relatórios dos alunos se tornaram mais detalhados, com maior quantidade de informações descritas neles.


Subject(s)
Humans , Cognition , Creativity , Knowledge , Learning
SELECTION OF CITATIONS
SEARCH DETAIL
...