Multi‐Deep Learning Approach With Transfer Learning for 7‐Stages Diabetic Retinopathy Classification

International Journal of Imaging Systems and Technology, Journal Year: 2024, Volume and Issue: 34(6)

Published: Nov. 1, 2024

ABSTRACT Proposed novel investigation focused on leveraging an innovative diabetic retinopathy (DR) dataset comprising seven severity stages, approach not previously examined. By capitalizing this unique resource, study′s findings set a new benchmark for DR classification, highlighting the transformative potential of incorporating advanced data into AI models. This study developed Vgg16 transfer learning model and gauged its performance against established algorithms including Vgg‐19, AlexNet, SqueezeNet. Remarkably, our results achieved accuracy rates 96.95, 96.75, 96.09, 92.96, respectively, emphasizing contribution work. We strongly emphasized comprehensive rating, yielding perfect impressive F1‐scores 1.00 “mild NPDR” 97.00 “no signs.” The Vgg16‐TL consistently outperformed other models across all levels, reinforcing value discoveries. Our deep training process, carefully selecting rate 1e‐05, allowed continuous refinements in validation accuracy. Beyond metrics, underscores vital clinical importance precise classification preventing vision loss. conclusively establishes as powerful tool developing effective with to improve patient outcomes advance ophthalmology standards.

Language: Английский

Training artificial neural networks using self-organizing migrating algorithm for skin segmentation

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 30, 2024

Language: Английский