Medical image generation in the diabetic retinopathy using generative adversarial network
One of the diseases that most affect the human visual system is Diabetic Retinopathy (DR), being one of the main causes of blindness worldwide. This disease is derived from Diabetes. It is important for ophthalmologists to be able to detect this disease in time to be able to give it an adequate trea...
| Autores: | , , , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2024 |
| País: | México |
| Recursos: | UNIVERSIDAD AUTÓNOMA DEL ESTADO DE HIDALGO |
| Repositorio: | PÄDI Boletín Científico de Ciencias Básicas e Ingeniería del ICBI |
| Idioma: | español |
| OAI Identifier: | oai:repository.uaeh.edu.mx:article/11022 |
| Acesso em linha: | https://repository.uaeh.edu.mx/revistas/index.php/icbi/article/view/11022 |
| Access Level: | acceso abierto |
| Palavra-chave: | Deep Learning Diabetic Retinopathy Image processing SinGAN Aprendizaje Profundo Retinopatía Diabética Procesamiento de Imágenes |
| Resumo: | One of the diseases that most affect the human visual system is Diabetic Retinopathy (DR), being one of the main causes of blindness worldwide. This disease is derived from Diabetes. It is important for ophthalmologists to be able to detect this disease in time to be able to give it an adequate treatment. Several works have been proposed to detect the degree of DR and to detect lesions caused by DR. To improve the accuracy of these algorithms, it is necessary to train with a large database segmented in a correct way. To date, the existing DR databases contain a limited number of images. Therefore, it is proposed to increase the number of DR images with the help of SinGAN (Learning a Generative Model from a Single Natural Image). Using this network it is possible to create new images from a single image as the input. |
|---|