3D U-Net improves automatic brain extraction for isotropic rat brain MRI data

Abstract

Brain extraction is a critical pre-processing step in brain magnetic resonance imaging (MRI) analytical pipelines. In rodents, this is often achieved by manually editing brain masks slice-by-slice, a time-consuming task where workloads increase with higher spatial resolution datasets. We recently demonstrated successful automatic brain extraction via a deep-learning-based framework, U-Net, using 2D convolutions. However, such an approach cannot make use of the rich 3D spatial-context information from volumetric MRI data. In this study, we advanced our previously proposed U-Net architecture by replacing all 2D operations with their 3D counterparts and created a 3D U-Net framework. We trained and validated our model using a recently released CAMRI rat brain database acquired at isotropic spatial resolution, including T2-weighted turbo-spin-echo structural MRI and T2*-weighted echo-planar-imaging functional MRI. The performance of our 3D U-Net model was compared with existing rodent brain extraction tools, including Rapid Automatic Tissue Segmentation (RATS), Pulse-Coupled Neural Network (PCNN), SHape descriptor selected External Regions after Morphologically filtering (SHERM), and our previously proposed 2D U-Net model. 3D U-Net demonstrated superior performance in Dice, Jaccard, Hausdorff distance, and sensitivity. Additionally, we demonstrated the reliability of 3D U-Net under various noise levels, evaluated the optimal training sample sizes, and disseminated all source codes publicly, with a hope that this approach will benefit rodent MRI research community.

The ANTsX Ecosystem for Mapping the Mouse Brain

“…In order to create a generalized mouse brain extraction network, we built whole-head templates from two publicly available datasets. The Center for Animal MRI (CAMRI) dataset 58 from the University of North Carolina at Chapel Hill consists of 16 T2-weighted MRI volumes of voxel resolution 0.16 × 0.16 × 0.16mm 3 . The second high-resolution dataset 59 comprises 88 specimens each with three spatially aligned canonical views with in-plane resolution of 0.08 × 0.08mm 2 with a slice thickness of 0.5mm.…”