首页|University of Malaya Reports Findings in Machine Learning (Enhancing reginal wal l abnormality detection accuracy: Integrating machine learning, optical flow alg orithms, and temporal convolutional networks in multi-view echocardiography)
University of Malaya Reports Findings in Machine Learning (Enhancing reginal wal l abnormality detection accuracy: Integrating machine learning, optical flow alg orithms, and temporal convolutional networks in multi-view echocardiography)
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 – New research on Machine Learning is the subject o f a report. According to news reporting originating in Kuala Lumpur, Malaysia, b y NewsRx journalists, research stated, “Regional Wall Motion Abnormality (RWMA) serves as an early indicator of myocardial infarction (MI), the global leader in mortality. Accurate and early detection of RWMA is vital for the successful tre atment of MI.” The news reporters obtained a quote from the research from the University of Mal aya, “Current automated echocardiography analyses typically concentrate on peak values from left ventricular (LV) dis-placement curves, based on LV contour annot ations or key frames during the heart’s systolic or diastolic phases within a si ngle echocardiographic cycle. This approach may overlook the rich motion field f eatures available in multi-cycle cardiac data, which could enhance RWMA detectio n. In this research, we put forward an innovative approach to detect RWMA by har nessing motion information across multiple echocardiographic cycles and multi-vi ews. Our methodology synergizes U-Net-based segmentation with optical flow algor ithms for detailed cardiac structure delineation, and Temporal Convolutional Net works (ConvNet) to extract nuanced motion features. We utilize a variety of mach ine learning and deep learning classifiers on both A2C and A4C views echocardiog rams to enhance detection accuracy. A three-phase algorithm-originating from the HMC-QU dataset-incorporates U-Net for segmentation, followed by optical flow fo r cardiac wall motion field features. Temporal ConvNet, inspired by the Temporal Segment Network (TSN), is then applied to interpret these motion field features , independent of traditional cardiac parameter curves or specific key phase fram e inputs. Employing five-fold cross-validation, our SVM classifier demonstrated high performance, with a sensitivity of 93.13%, specificity of 83.6 1%, precision of 88.52%, and an F1 score of 90.39% . When compared with other studies using the HMC-QU datasets, these Fig s stand out, underlining our method’s effectiveness. The classifier also attained an ove rall accuracy of 89.25% and Area Under the Curve (AUC) of 95% , reinforcing its potential for reliable RWMA detection in echocardiographic ana lysis.”
Kuala LumpurMalaysiaAsiaAlgorithmsCardiologyCardiovascularCyborgsDiagnosisDiagnostic Techniques and Proc eduresDoppler EchocardiographyEchocardiographyEmerging TechnologiesHealt h and MedicineMachine Learning
NETL
NSTL
