Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper optimizes the YOLOv8 architecture for cataract detection using fundus and anterior segment images. The optimization focuses on enhancing feature extraction and employs techniques like five-fold cross-validation, color magnification, and stochastic weight averaging (SWA) during training. The resulting model achieves a 98.9% F1-score and 0.995 mAP50 on an external test set, demonstrating improved accuracy and real-time performance compared to ResNet- and MobileNet-based approaches.
Real-time cataract diagnosis is now possible on low-cost GPUs, thanks to a YOLOv8 optimization that beats previous benchmarks by 4% in F1-score and slashes latency by 68%.
Cataracts remain the leading cause of visual impairment worldwide. We focus on improving the you only look once (YOLO) architecture through targeted optimization to enhance feature extraction. We trained the optimized YOLOv8 detector using 11,274 annotated fundus and anterior segment images. During training, five-fold cross-validation, color magnification, and stochastic weight averaging (SWA) were applied to ensure convergence. In the external test set, the model achieved an F1-score of 98.9% and an mAP50 of 0.995. On an NVIDIA RTX A2000 GPU, the inference speed reached 520 frames per second. Our network enables real-time cataract diagnosis on low-cost GPUs, surpassing previous ResNet- and MobileNet-based benchmarks by ?4% in F1-score and reducing output latency by 68%.