Porter Valerie A, Hobson Brad A, Foster Brent, Lein Pamela J, Chaudhari Abhijit J
Department of Biomedical Engineering, University of California, Davis, CA 95616, USA; Department of Radiology, University of California, Davis, CA 95817, USA.
Department of Biomedical Engineering, University of California, Davis, CA 95616, USA; Center for Molecular and Genomic Imaging, University of California, Davis, CA 95616, USA.
J Neurosci Methods. 2024 May;405:110078. doi: 10.1016/j.jneumeth.2024.110078. Epub 2024 Feb 8.
Whole brain delineation (WBD) is utilized in neuroimaging analysis for data preprocessing and deriving whole brain image metrics. Current automated WBD techniques for analysis of preclinical brain MRI data show limited accuracy when images present with significant neuropathology and anatomical deformations, such as that resulting from organophosphate intoxication (OPI) and Alzheimer's Disease (AD), and inadequate generalizability.
A modified 2D U-Net framework was employed for WBD of MRI rodent brains, consisting of 27 convolutional layers, batch normalization, two dropout layers and data augmentation, after training parameter optimization. A total of 265 T-weighted 7.0 T MRI scans were utilized for the study, including 125 scans of an OPI rat model for neural network training. For testing and validation, 20 OPI rat scans and 120 scans of an AD rat model were utilized. U-Net performance was evaluated using Dice coefficients (DC) and Hausdorff distances (HD) between the U-Net-generated and manually segmented WBDs.
The U-Net achieved a DC (median[range]) of 0.984[0.936-0.990] and HD of 1.69[1.01-6.78] mm for OPI rat model scans, and a DC (mean[range]) of 0.975[0.898-0.991] and HD of 1.49[0.86-3.89] for the AD rat model scans.
The proposed approach is fully automated and robust across two rat strains and longitudinal brain changes with a computational speed of 8 seconds/scan, overcoming limitations of manual segmentation.
The modified 2D U-Net provided a fully automated, efficient, and generalizable segmentation approach that achieved high accuracy across two disparate rat models of neurological diseases.
全脑轮廓描绘（WBD）用于神经影像分析中的数据预处理和推导全脑图像指标。当前用于临床前脑MRI数据分析的自动WBD技术，在存在明显神经病理学和解剖学变形的图像（如有机磷中毒（OPI）和阿尔茨海默病（AD）导致的图像）中，准确性有限且通用性不足。
采用改进的二维U-Net框架对MRI啮齿动物脑进行WBD，该框架由27个卷积层、批量归一化、两个随机失活层和数据增强组成，经过训练参数优化。总共265幅T加权7.0 T MRI扫描用于该研究，其中125幅OPI大鼠模型扫描用于神经网络训练。为进行测试和验证，使用了20幅OPI大鼠扫描图像和120幅AD大鼠模型扫描图像。使用U-Net生成的WBD与手动分割的WBD之间的骰子系数（DC）和豪斯多夫距离（HD）来评估U-Net的性能。
对于OPI大鼠模型扫描，U-Net的DC（中位数[范围]）为0.984[0.936 - 0.990]，HD为1.69[1.01 - 6.78]mm；对于AD大鼠模型扫描，DC（平均值[范围]）为0.975[0.898 - 0.991]，HD为1.49[0.86 - 3.89]。
所提出的方法是完全自动化的，并且在两种大鼠品系以及纵向脑变化中都具有鲁棒性，计算速度为8秒/扫描，克服了手动分割的局限性。
改进的二维U-Net提供了一种完全自动化、高效且通用的分割方法，在两种不同的神经疾病大鼠模型中均实现了高精度。
