Crop Filling: a pipeline for repairing memory clinic MRI corrupted by partial brain coverage
Crop Filling: a pipeline for repairing memory clinic MRI corrupted by partial brain coverage
复制标题
作物填充：修复因部分大脑覆盖而损坏的记忆诊所 MRI 的管道
DOI：
10.1101/2023.03.06.23286839
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Leal G
中科院分区：
文献类型：
--
作者：
Leal G
数据驱动的解决方案为改善医疗保健提供了巨大的希望。然而，标准临床神经影像数据受到现实世界成像伪影的影响，这可能导致数据无法用于计算研究和定量神经放射学。 T1 加权结构 MRI 用于痴呆症研究，以获得皮质和皮质下大脑区域的体积测量结果。然而，临床放射科医生通常优先考虑 T2 加权或 FLAIR 扫描进行视觉评估。因此，T1 加权扫描通常会被采集，但可能不是优先事项，导致记忆临床数据中系统地存在部分大脑覆盖等伪影。在这里，我们提出了“MRI Crop Filling”，这是一种用 T2 扫描生成的合成数据替换丢失的 T1 数据的管道，使真实世界的临床 T1 数据可用于包括最新人工智能创新在内的计算研究。我们的方法包括以下步骤：•注册扫描：T2 和（裁剪的）T1。•使用开源深度学习工具合成新的 T1。•替换原始 T1 扫描中丢失的（裁剪的）T1 数据并进行超分辨率以提高图像质量。
Data-driven solutions offer great promise for improving healthcare. However, standard clinical neuroimaging data is subject to real-world imaging artefacts that can render the data unusable for computational research and quantitative neuroradiology. T1 weighted structural MRI is used in dementia research to obtain volumetric measurements from cortical and subcortical brain regions. However, clinical radiologists often prioritise T2 weighted or FLAIR scans for visual assessment. As such, T1 weighted scans are often acquired but may not be a priority, resulting in artefacts such as partial brain coverage being systematically present in memory clinic data.Here we present “MRI Crop Filling”, a pipeline to replace the missing T1 data with synthetic data generated from the T2 scan, making real-world clinical T1 data usable for computational research including the latest AI innovations. Our method consists of the following steps:•Register scans: T2 and (cropped) T1.•Synthesise a new T1 using an open source deep learning tool.•Replace missing (cropped) T1 data in original T1 scan and super-resolve to improve image quality.