首页|Department of Computer Science Reports Findings in Machine Learning (Resilient b ack-propagation machine learning-based classification on fundus images for retin al microaneurysm detection)
Department of Computer Science Reports Findings in Machine Learning (Resilient b ack-propagation machine learning-based classification on fundus images for retin al microaneurysm detection)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting out of Tamil Nadu, India, by NewsRx editors, research stated, "The timely diagnosis of medical conditions, pa rticularly diabetic retinopathy, relies on the identification of retinal microan eurysms. However, the commonly used retinography method poses a challenge due to the diminutive dimensions and limited differentiation of microaneurysms in imag es." Our news journalists obtained a quote from the research from the Department of C omputer Science, "Automated identification of microaneurysms becomes crucial, ne cessitating the use of comprehensive adhoc processing techniques. Although fluo rescein angiography enhances detectability, its invasiveness limits its suitabil ity for routine preventative screening. This study proposes a novel approach for detecting retinal microaneurysms using a fundus scan, leveraging circular refer ence-based shape features (CR-SF) and radial gradient-based texture features (RG -TF). The proposed technique involves extracting CR-SF and RG-TF for each candid ate microaneurysm, employing a robust back-propagation machine learning method f or training. During testing, extracted features from test images are compared wi th training features to categorize microaneurysm presence. The experimental asse ssment utilized four datasets (MESSIDOR, Diaretdb1, e-ophtha-MA, and ROC), emplo ying various measures. The proposed approach demonstrated high accuracy (98.01% ), sensitivity (98.74%), specificity (97.12%), and are a under the curve (91.72 %). The presented approach showcases a succ essful method for detecting retinal microaneurysms using a fundus scan, providin g promising accuracy and sensitivity."
Tamil NaduIndiaAsiaCyborgsEmergi ng TechnologiesMachine Learning