Automated skull stripping in mouse fMRI analysis using 3D U-Net

Automated skull stripping in mouse fMRI analysis using 3D U-Net
复制标题

使用 3D U-Net 进行小鼠 fMRI 分析中的自动颅骨剥离

DOI:
10.1101/2021.10.08.462356
复制
发表时间:
2021-10
期刊:
bioRxiv
影响因子:
--
通讯作者:
Yanqiu Feng
Yanqiu Feng
中科院分区:
其他
文献类型:
--
作者:
Guohui Ruan;Jiaming Liu;Ziqi An;Kaiibin Wu;Chuanjun Tong;Qiang Liu;Ping Liang;Zhifeng Liang;Wufan Chen;Xinyuan Zhang;Yanqiu Feng

文献摘要

参考文献

相似文献

颅骨剥离是小鼠功能磁共振成像分析过程中的第一步,也是关键步骤。人工标记大脑通常会受到评分者内部和之间的可变性的影响,并且非常耗时。因此,对小鼠功能磁共振成像的研究迫切需要一种自动、高效的颅骨剥离方法。在这项研究中,我们研究了一种基于3D U网的脑自动提取方法,用于小鼠功能磁共振研究。两个U网模型分别在T2加权解剖图像和T2加权功能图像上进行训练。训练好的模型在内部和外部数据集上进行了测试。与两种广泛使用的小鼠颅骨剥离方法(老鼠和SHERM)相比,3D U网络模型在提取T2加权图像(Dice>0.984,Jaccard指数>0.968和Hausdorff距离0.964,Jaccard指数>0.931和Hausdorff距离&3.3%)中产生了更高的准确率。使用3D U网模型自动分割的静息状态fMRI结果与基于种子和组独立分量分析的手动分割获得的结果相同。这些结果表明,基于3DU网的方法可以替代人工脑提取在小鼠fMRI分析中的应用。
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 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 identical to 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.
DOI: 10.1101/527457
发表时间: 2019-01
期刊: Neuron
影响因子: 16.2
作者:
V. Zerbi;Amalia Floriou-Servou;M. Markicevic;Y. Vermeiren;Oliver Sturman;Mattia Privitera;Lukas M. von Ziegler;Kim David Ferrari;B. Weber;P. D. de Deyn;N. Wenderoth;J. Bohacek
通讯作者: V. Zerbi;Amalia Floriou-Servou;M. Markicevic;Y. Vermeiren;Oliver Sturman;Mattia Privitera;Lukas M. von Ziegler;Kim David Ferrari;B. Weber;P. D. de Deyn;N. Wenderoth;J. Bohacek
DOI: 10.1109/trpms.2018.2890359
发表时间: 2019-03
影响因子: 4.4
作者:
Guo Z;Li X;Huang H;Guo N;Li Q
通讯作者: Li Q
DOI: 10.3389/fnins.2020.568614
发表时间: 2020
影响因子: 4.3
作者:
Hsu LM;Wang S;Ranadive P;Ban W;Chao TH;Song S;Cerri DH;Walton LR;Broadwater MA;Lee SH;Shen D;Shih YI
通讯作者: Shih YI
DOI: 10.1016/j.media.2017.01.008
发表时间: 2017-04
影响因子: 10.9
作者:
Suk HI;Lee SW;Shen D;Alzheimer’s Disease Neuroimaging Initiative
通讯作者: Alzheimer’s Disease Neuroimaging Initiative
DOI: 10.1371/journal.pone.0018876
发表时间: 2011-04-18
期刊: PloS one
影响因子: 3.7
作者:
Jonckers E;Van Audekerke J;De Visscher G;Van der Linden A;Verhoye M
通讯作者: Verhoye M