A probabilistic deep motion model for unsupervised cardiac shape anomaly assessment

Medical Image Analysis(2022)

引用 2|浏览7
暂无评分
摘要
•A probabilistic spatiotemporal anomaly detection method suitable for high-dimensional data•Expectation-Maximisation-based learning is proposed to soft cluster outlier cardiac shapes•Shapes showing excessive deviation from ’normality’ can indicate pathology or poor shape quality•Potential use to sift pathologies that affect cardiac shape among a large-scale dataset
更多
查看译文
关键词
Cardiac shape quality control,Deep learning,Expectation-maximisation,Probabilistic model,Spatio-temporal anomaly detection,UK Biobank
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要