用视频时序特征提升新生儿超声心动图视角分类准确率
Temporal Feature Weaving for Neonatal Echocardiographic Viewpoint Video Classification
- 将视角分类视为视频任务，融合空间与时间信息
- 仅用4帧视频即比图像分类提升4.33%准确率
- 适合医疗AI初学者和超声影像研究者
自动化超声心动图视角分类可帮助资源匮乏的医疗机构在缺乏专家技师时实现快速诊断与筛查。本文提出一种新型超声心动图视角分类方法，表明将其视为视频分类而非图像分类更具优势。提出基于CNN-GRU架构的时序特征编织方法，充分利用空间与时间信息，在仅使用四帧连续图像的情况下，较基线图像分类方法提升4.33%准确率，且计算开销极小。同时发布新生儿超声心动图数据集（NED），包含十六个视角的标注视频，以推动该领域研究发展。代码已公开于：https://github.com/satchelfrench/NED
原文摘要 · Abstract (English)
Automated viewpoint classification in echocardiograms can help under-resourced clinics and hospitals in providing faster diagnosis and screening when expert technicians may not be available. We propose a novel approach towards echocardiographic viewpoint classification. We show that treating viewpoint classification as video classification rather than image classification yields advantage. We propose a CNN-GRU architecture with a novel temporal feature weaving method, which leverages both spatial and temporal information to yield a 4.33\% increase in accuracy over baseline image classification while using only four consecutive frames. The proposed approach incurs minimal computational overhead. Additionally, we publish the Neonatal Echocardiogram Dataset (NED), a professionally-annotated dataset providing sixteen viewpoints and associated echocardipgraphy videos to encourage future work and development in this field. Code available at: https://github.com/satchelfrench/NED
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。