期刊
JOURNAL OF CEREBRAL BLOOD FLOW AND METABOLISM
卷 40, 期 11, 页码 2240-2253出版社
SAGE PUBLICATIONS INC
DOI: 10.1177/0271678X19888123
关键词
Cerebral blood flow; arterial spin labeling; magnetic resonance imaging; positron emission tomography; deep convolutional neural network
资金
- NIH [5R01NS066506, 5K99NS102884]
- NCRR [5P41RR09784]
- GE Healthcare
To improve the quality of MRI-based cerebral blood flow (CBF) measurements, a deep convolutional neural network (dCNN) was trained to combine single- and multi-delay arterial spin labeling (ASL) and structural images to predict gold-standard O-15-water PET CBF images obtained on a simultaneous PET/MRI scanner. The dCNN was trained and tested on 64 scans in 16 healthy controls (HC) and 16 cerebrovascular disease patients (PT) with 4-fold cross-validation. Fidelity to the PET CBF images and the effects of bias due to training on different cohorts were examined. The dCNN significantly improved CBF image quality compared with ASL alone (mean +/- standard deviation): structural similarity index (0.854 +/- 0.036 vs. 0.743 +/- 0.045 [single-delay] and 0.732 +/- 0.041 [multi-delay], P < 0.0001); normalized root mean squared error (0.209 +/- 0.039 vs. 0.326 +/- 0.050 [single-delay] and 0.344 +/- 0.055 [multi-delay], P < 0.0001). The dCNN also yielded mean CBF with reduced estimation error in both HC and PT (P < 0.001), and demonstrated better correlation with PET. The dCNN trained with the mixed HC and PT cohort performed the best. The results also suggested that models should be trained on cases representative of the target population.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据