Automatic Skull Stripping of Rat and Mouse Brain MRI Data Using U-Net

Frontiers in Neuroscience

Woomi Ban¹  Paridhi Ranadive²  Dinggang Shen³  Domenic Hayden Cerri⁴  Sheng Song⁴  Margaret A. Broadwater⁴  Yen-Yu Ian Shih⁴  Tzu-Hao Harry Chao⁴  Lindsay R. Walton⁴  Sung-Ho Lee⁴  Shuai Wang⁵  Li-Ming Hsu⁵ 

[1] Biomedical Research Imaging Center, The University of North Carolina at Chapel Hill, Chapel Hill, NC, United States;Center for Animal Magnetic Resonance Imaging, The University of North Carolina at Chapel Hill, Chapel Hill, NC, United States;Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea;Department of Neurology, The University of North Carolina at Chapel Hill, Chapel Hill, NC, United States;Department of Radiology, The University of North Carolina at Chapel Hill, Chapel Hill, NC, United States;

关键词: rat brain;    mouse brain;    MRI;    U-net;    segmentation;    skull stripping;   

DOI  :  10.3389/fnins.2020.568614

来源: DOAJ

【 摘 要 】

Accurate removal of magnetic resonance imaging (MRI) signal outside the brain, a.k.a., skull stripping, is a key step in the brain image pre-processing pipelines. In rodents, this is mostly achieved by manually editing a brain mask, which is time-consuming and operator dependent. Automating this step is particularly challenging in rodents as compared to humans, because of differences in brain/scalp tissue geometry, image resolution with respect to brain-scalp distance, and tissue contrast around the skull. In this study, we proposed a deep-learning-based framework, U-Net, to automatically identify the rodent brain boundaries in MR images. The U-Net method is robust against inter-subject variability and eliminates operator dependence. To benchmark the efficiency of this method, we trained and validated our model using both in-house collected and publicly available datasets. In comparison to current state-of-the-art methods, our approach achieved superior averaged Dice similarity coefficient to ground truth T2-weighted rapid acquisition with relaxation enhancement and T2∗-weighted echo planar imaging data in both rats and mice (all p < 0.05), demonstrating robust performance of our approach across various MRI protocols.

【 授权许可】

Unknown