Cataract Disease Classification using YOLOv11 Algorithm

Cataract is one of the leading causes of blindness globally, significantly impacting individuals' quality of life. Early detection plays a crucial role in reducing the health burden and preventing further deterioration of vision. This research propose a novel method for cataract disease classification utilizing the YOLOv11 (You Only Look Once version 11) object detection model. YOLOv11 is widely recognized for its speed and high accuracy in detecting objects in images, making it an ideal choice for medical image analysis. This study aims to develop an automated system capable of detecting and classifying cataract symptoms in eye images, which would aid in timely diagnosis and treatment. The dataset used in this research consists of images of eyes affected by mature cataracts, immature cataracts, and normal eye conditions, all obtained through advanced medical imaging technologies. YOLOv11 is leveraged to detect abnormalities in the lens of the eye that indicate the presence of cataracts, followed by a classification of the severity based on visual features observed in the images. The classification is performed into three categories: mature cataract, immature cataract, and normal eyes. To evaluate the effectiveness of the model, performance metrics such as accuracy, precision, and recall were employed. The results demonstrated promising outcomes, with the model achieving an accuracy of 98.00% for mature cataracts, 97.78% for immature cataracts, and 100% for normal eye classification. These findings highlight the potential of YOLOv11 as a reliable and efficient tool for cataract detection and classification, which could ultimately support the early diagnosis and management of cataract-related vision impairment.