arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.04740cs.CVmath.DGq-bio.TO
收藏

预测形状发展:一种黎曼方法

Predicting Shape Development: a Riemannian Method

Istanbul Technical University(伊斯坦布尔理工大学);Imperial College London(帝国理工学院);Zuse Institute Berlin(柏林朱瑟研究所);Freie Universität Berlin(柏林自由大学)

Doğa Türkseven, Islem Rekik, Christoph von Tycowicz, Martin Hanik

AI总结:

本文提出一种基于黎曼形状空间和分层统计建模的形状预测方法,在预测阿尔茨海默病海马体发展和人体运动任务中优于深度学习方法。

摘要:

从单次基线观测预测解剖形状的未来发展是一项具有挑战性的任务,但对临床决策可能至关重要。研究表明,此类任务应在弯曲的形状空间中处理,因为(例如与疾病相关的)形状变化常常表现出非线性特征。因此,我们提出了一种新颖的预测方法,将整个形状编码在黎曼形状空间中。该方法随后学习一种基于纵向训练数据的分层统计建模的简单预测技术。在应用于预测阿尔茨海默病下右侧海马体的未来形状发展以及人体运动时,其性能优于深度学习支持的变体以及当前最先进的方法。

英文摘要:

Predicting the future development of an anatomical shape from a single baseline observation is a challenging task. But it can be essential for clinical decision-making. Research has shown that it should be tackled in curved shape spaces, as (e.g., disease-related) shape changes frequently expose nonlinear characteristics. We thus propose a novel prediction method that encodes the whole shape in a Riemannian shape space. It then learns a simple prediction technique founded on hierarchical statistical modeling of longitudinal training data. When applied to predict the future development of the shape of the right hippocampus under Alzheimer's disease and to human body motion, it outperforms deep learning-supported variants as well as state-of-the-art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑