Generating retinal flow maps from structural optical coherence tomography with artificial intelligence

Lee, Cecilia S.; Tyring, Ariel J.; Wu, Yue; Xiao, Sa; Rokem, Ariel; Deruyter, Nicolaas P.; Zhang, Qinqin; Tufail, Adnan; Wang, Ke; Lee, Aaron

doi:10.1038/s41598-019-42042-y

Cited by 75 publications

(66 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…American scientists [32] propose to use AI in medical imaging more actively and to use images from optical coherent tomography (OCT) to create flow maps from images of standard OCT.…”

Section: B Modern Approaches Using Artificial Intelligence In Identimentioning

confidence: 99%

Using Natural and Artificial Intelligence in the Talent Management System

Vinichenko*¹,

Rybakova²,

Сhulanova³

et al. 2019

IJRTE

View full text Add to dashboard Cite

Abstract: The article describes the nature of the use of natural and artificial intelligence in the talent management system in the Moscow Region. The extent of using talent management technology, the tools, the ratio of demand for natural and artificial intelligence in talent management, and the level of employee confidence in man (robot) in management are analyzed. It is revealed and substantiated that personnel management services and the management of companies do not effectively use natural intelligence in the framework of the talent management system, relying on chance and a typical approach. Ambiguity in the assessment of artificial intelligence by both employees and company management was revealed. Increased use and fears of the negative impact of artificial intelligence become opposing factors in talent management. It is proposed to quickly implement advanced technologies based on artificial intelligence, with no harm to the human and his potential. It is also proposed to constantly keep in focus the risks of intercepting initiatives in the management of artificial intelligence and the crowding out of a person from the labor market. The main advantage of the article is an integrated approach to the study of the pattern of using natural and artificial intelligence in the talent management system. The authors considered the issue of identifying the ratio of artificial and natural intelligence in talent management for the first time. The results can serve as a basis for further research in the system of human resource management, as well as good support for making management decisions in the implementation of artificial intelligence in business processes and organization management.

show abstract

“…American scientists [32] propose to use AI in medical imaging more actively and to use images from optical coherent tomography (OCT) to create flow maps from images of standard OCT.…”

Section: B Modern Approaches Using Artificial Intelligence In Identimentioning

confidence: 99%

Using Natural and Artificial Intelligence in the Talent Management System

Vinichenko*¹,

Rybakova²,

Сhulanova³

et al. 2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…32 Recently, transfer learning has also been explored in OCT for detecting choroidal neovascularization, diabetic macular edema, 28 and AMD. 33 In principle, transfer learning can involve a single layer or multiple layers, because each layer has weights that can be retrained. For example, the specific number of layers required for retraining in a 16-layer CNN (Fig.…”

Section: Introductionmentioning

confidence: 99%

Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy

Alam

Yao

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

To test the feasibility of using deep learning for optical coherence tomography angiography (OCTA) detection of diabetic retinopathy. Methods: A deep-learning convolutional neural network (CNN) architecture, VGG16, was employed for this study. A transfer learning process was implemented to retrain the CNN for robust OCTA classification. One dataset, consisting of images of 32 healthy eyes, 75 eyes with diabetic retinopathy (DR), and 24 eyes with diabetes but no DR (NoDR), was used for training and cross-validation. A second dataset consisting of 20 NoDR and 26 DR eyes was used for external validation. To demonstrate the feasibility of using artificial intelligence (AI) screening of DR in clinical environments, the CNN was incorporated into a graphical user interface (GUI) platform. Results: With the last nine layers retrained, the CNN architecture achieved the best performance for automated OCTA classification. The cross-validation accuracy of the retrained classifier for differentiating among healthy, NoDR, and DR eyes was 87.27%, with 83.76% sensitivity and 90.82% specificity. The AUC metrics for binary classification of healthy, NoDR, and DR eyes were 0.97, 0.98, and 0.97, respectively. The GUI platform enabled easy validation of the method for AI screening of DR in a clinical environment. Conclusions: With a transfer learning process for retraining, a CNN can be used for robust OCTA classification of healthy, NoDR, and DR eyes. The AI-based OCTA classification platform may provide a practical solution to reducing the burden of experienced ophthalmologists with regard to mass screening of DR patients. Translational Relevance: Deep-learning-based OCTA classification can alleviate the need for manual graders and improve DR screening efficiency.

show abstract

“…4 More specifically, deep learning, a subset of machine learning within the field of AI, has been particularly successful in training powerful algorithms for the classification of medical images and other high-dimensional data. [5][6][7][8][9] Taken together, these approaches may offer many benefits for patients, including automated screening and triage of disease and treatment optimization. For example, AIenabled screening of diseases such as diabetic retinopathy, retinopathy of prematurity, and glaucoma could improve early detection and treatment.…”

Section: Introductionmentioning

confidence: 99%