RESUMEN
There is a growing number of publicly available ophthalmic imaging datasets and open-source code for Machine Learning algorithms. This allows ophthalmic researchers and practitioners to independently perform various deep-learning tasks. With the advancement in artificial intelligence (AI) and in the field of imaging, the choice of the most appropriate AI architecture for different tasks will vary greatly. The best-performing AI-dataset combination will depend on the specific problem that needs to be solved and the type of data available. The article discusses different machine learning models and deep learning architectures currently used for various ophthalmic imaging modalities and for different machine learning tasks. It also proposes the most appropriate models based on accuracy and other important factors such as training time, the ability to deploy the model on clinical devices/smartphones, heatmaps that enhance the self-explanatory nature of classification decisions, and the ability to train/adapt on small image datasets to determine if further data collection is worthwhile. The article extensively reviews the existing state-of-the-art AI methods focused on useful machine-learning applications for ophthalmology. It estimates their performance and viability through training and evaluating architectures with different public and private image datasets of different modalities, such as full-color retinal images, OCT images, and 3D OCT scans. The article is expected to benefit the readers by enriching their knowledge of artificial intelligence applied to ophthalmology.
Asunto(s)
Aprendizaje Profundo , Oftalmología , Humanos , Oftalmología/métodos , Inteligencia Artificial , Algoritmos , Aprendizaje Automático , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Purpose/Background: We evaluate how a deep learning model can be applied to extract refractive error metrics from pupillary red reflex images taken by a low-cost handheld fundus camera. This could potentially provide a rapid and economical vision-screening method, allowing for early intervention to prevent myopic progression and reduce the socioeconomic burden associated with vision impairment in the later stages of life. Methods: Infrared and color images of pupillary crescents were extracted from eccentric photorefraction images of participants from Choithram Hospital in India and Dargaville Medical Center in New Zealand. The pre-processed images were then used to train different convolutional neural networks to predict refractive error in terms of spherical power and cylindrical power metrics. Results: The best-performing trained model achieved an overall accuracy of 75% for predicting spherical power using infrared images and a multiclass classifier. Conclusions: Even though the model's performance is not superior, the proposed method showed good usability of using red reflex images in estimating refractive error. Such an approach has never been experimented with before and can help guide researchers, especially when the future of eye care is moving towards highly portable and smartphone-based devices.
RESUMEN
INTRODUCTION: The present study proposes a new hand-held non-mydriatic fundus camera for retinal imaging. The goal is to design a fundus camera which is equally effective in both clinical and telemedicine scenarios. AREAS COVERED: A new retinal illumination approach is proposed to address the main dilemma of the optical design, i.e. balancing efficacy with structural simplicity. This is achieved by symmetrical and co-axial placement of multiple illumination sources along the optical pathway. Each illumination source includes a white and a Near Infra-Red (NIR) LED, which are placed adjacent to each other. Hence, the camera can produce a view-finder with NIR illumination without the need for additional beam-splitters and filters. EXPERT OPINION: The proposed design blends the structural simplicity of the 'off-axis illumination with the wide field of view and uniform illumination of the 'ring' illumination. Moreover, the camera is designed to work with Android-based smartphones, which can easily be mounted and interfaced. The efficacy of the proposed camera is determined by ocular safety analysis and comparative evaluation with a table-top fundus camera. The results convincingly demonstrate the ability of the proposed camera as a primary driver of a wide-scale screening program in both clinical and remote resource constraint environments.