Constructing Population-Specific Atlases from Whole Body MRI: Application to the UKBB

Research Square (Research Square)(2023)

引用 0|浏览11
暂无评分
摘要
Population atlases are commonly utilised in medical imaging to facilitate the investigation of variability across populations. Such atlases enable the mapping of medical images into a common coordinate system, promoting comparability and enabling the study of inter-subject differences. Constructing such atlases becomes particularly challenging when working with highly heterogeneous datasets, such as whole-body images, where subjects show significant anatomical variations. In this work, we propose a pipeline for generating a standardised whole-body atlas for a highly heterogeneous population by partitioning the population into meaningful subgroups. We create six whole-body atlases that represent a healthy population average using magnetic resonance (MR) images from the UK Biobank dataset. We furthermore unbias them, and this way obtain a realistic representation of the population. In addition to the anatomical atlases, we generate probabilistic atlases that capture the distributions of abdominal fat and five abdominal organs across the population. We demonstrate different applications of these atlases, using the differences between subjects with medical conditions such as diabetes and cardiovascular diseases and healthy subjects from the atlas space. With this work, we make the constructed anatomical and label atlases publically available and anticipate them to support medical research conducted on whole-body MR images.
更多
查看译文
关键词
whole body mri
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