Choroid Plexus Segmentation Using Optimized 3D U-Net

The choroid plexus is the primary organ that secretes the cerebrospinal fluid. Its structure and function may be associated with the brain drainage pathway and the clearance of amyloid-beta in Alzheimer's Disease. However, choroid plexus segmentation methods have rarely been studied. Therefore, the purpose of this work is to fill the gap using a deep convolutional network. MR images of 10 healthy subjects ($75.5\pm 8.0$ years) were retrospectively selected from the Alzheimer's Disease Neuroimaging Initiative database (ADNI). The benchmark of choroid plexus segmentation was provided by the FreeSurfer package and manual correction. A 3D U-Net was developed and optimized in the patch extraction, augmentation, and loss function. In leave-one-out cross-validations, the optimized U-Net provided superior performance compared to the FreeSurfer results (Dice score $0.732\pm 0.046$ vs $0.581\pm 0.093$, Jaccard coefficient $0.579\pm 0.057$ vs $0.416\pm 0.091$, 95% Hausdorff distance $1.871\pm 0.549$ vs $7.257\pm 5.038$, and sensitivity $0.761 \pm 0.078$ vs $0.539\pm 0.117$).