Table_1_Automated Skull Stripping in Mouse Functional Magnetic Resonance Imaging Analysis Using 3D U-Net.DOCX
Skull stripping is an initial and critical step in the pipeline of mouse fMRI analysis. Manual labeling of the brain usually suffers from intra- and inter-rater variability and is highly time-consuming. Hence, an automatic and efficient skull-stripping method is in high demand for mouse fMRI studies. In this study, we investigated a 3D U-Net based method for automatic brain extraction in mouse fMRI studies. Two U-Net models were separately trained on T2-weighted anatomical images and T2*-weighted functional images. The trained models were tested on both interior and exterior datasets. The 3D U-Net models yielded a higher accuracy in brain extraction from both T2-weighted images (Dice > 0.984, Jaccard index > 0.968 and Hausdorff distance < 7.7) and T2*-weighted images (Dice > 0.964, Jaccard index > 0.931 and Hausdorff distance < 3.3), compared with the two widely used mouse skull-stripping methods (RATS and SHERM). The resting-state fMRI results using automatic segmentation with the 3D U-Net models are highly consistent with those obtained by manual segmentation for both the seed-based and group independent component analysis. These results demonstrate that the 3D U-Net based method can replace manual brain extraction in mouse fMRI analysis.
History
References
- https://doi.org//10.1073/pnas.1703309114
- https://doi.org//10.1016/j.neuroimage.2019.116242
- https://doi.org//10.1109/TIP.2011.2126587
- https://doi.org//10.1038/s41591-018-0107-6
- https://doi.org//10.1016/j.neuroimage.2021.117734
- https://doi.org//10.1016/s0926-6410%2898%2900004-4
- https://doi.org//10.1016/j.neuroimage.2011.09.012
- https://doi.org//10.1109/TRPMS.2018.2890359
- https://doi.org//10.3389/fnins.2020.568614
- https://doi.org//10.1016/j.neuroimage.2014.01.059
- https://doi.org//10.1109/34.232073
- https://doi.org//10.1371/journal.pone.0018876
- https://doi.org//10.1016/j.neuroimage.2016.01.024
- https://doi.org//10.1038/s41592-020-00984-6
- https://doi.org//10.1038/nature09108
- https://doi.org//10.3174/ajnr.A3263
- https://doi.org//10.1016/j.neucom.2018.10.099
- https://doi.org//10.1109/TPAMI.2018.2858826
- https://doi.org//10.1007/s12021-020-09453-z
- https://doi.org//10.1016/j.neuroimage.2014.03.078
- https://doi.org//10.1016/j.jneumeth.2013.09.021
- https://doi.org//10.1007/978-1-4939-7531-0_8
- https://doi.org//10.1007/978-3-319-24574-4_28
- https://doi.org//10.1109/ISBI.2018.8363667
- https://doi.org//10.1016/j.neuroimage.2004.03.032
- https://doi.org//10.1002/hbm.10062
- https://doi.org//10.1016/j.media.2017.01.008
- https://doi.org//10.3389/fnins.2019.00810
- https://doi.org//10.1109/CVPR.2015.7298594
- https://doi.org//10.1109/BigData47090.2019.9005976
- https://doi.org//10.1109/TMI.2010.2046908
- https://doi.org//10.1016/j.neuroimage.2019.06.063
- https://doi.org//10.1016/j.neuroimage.2013.11.044
- https://doi.org//10.1007/s10278-017-0037-8
- https://doi.org//10.1109/TMI.2010.2058861
- https://doi.org//10.1109/ICDM.2019.00088
- https://doi.org//10.1016/j.neuron.2019.05.034
- https://doi.org//10.1016/j.neuroimage.2015.07.090
- https://doi.org//10.1109/TNNLS.2020.2988928
Usage metrics
Read the peer-reviewed publication
Categories
- Radiology and Organ Imaging
- Decision Making
- Autonomic Nervous System
- Cellular Nervous System
- Biological Engineering
- Central Nervous System
- Sensory Systems
- Neuroscience
- Endocrinology
- Artificial Intelligence and Image Processing
- Clinical Nursing: Tertiary (Rehabilitative)
- Image Processing
- Signal Processing
- Rehabilitation Engineering
- Biomedical Engineering not elsewhere classified
- Stem Cells
- Neurogenetics
- Developmental Biology