A lightweight deep learning model (LWBNA_UNET) for automatic segmentation and analysis of eye images developed by researchers at Tohoku University in Japan should help doctors identify and treat eye, heart, blood vessel and brain diseases.
The so-called “lightweight” model can be applied to mobile devices and practiced using only a few images, even those full of noise.
The model works by examining images and dividing them by creating boundary lines to evaluate tumors and various phenomena of the body. The use of the model, according to the team of researchers, will be used more in the future to diagnose various diseases and common eye diseases.
