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, Pulse-Coupled Neural Network, SHape descriptor selected External Regions after Morphologically filtering, and our previously proposed 2D U-Net model. 3D U-Net demonstrated superior performance in Dice, Jaccard, center-of-mass distance, 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.Significant Methodological Contribution: We proposed a deep-learning-based framework to automatically identify the rodent brain boundaries in MRI. With a fully 3D convolutional network model, 3D U-Net, our proposed method demonstrated improved performance compared to current automatic brain extraction methods, as shown in several qualitative metrics (Dice, Jaccard, PPV, SEN, and Hausdorff). We trust that this tool will avoid human bias and streamline pre-processing steps during 3D high resolution rodent brain MRI data analysis. The software developed herein has been disseminated freely to the community.

Highlights

  • Magnetic resonance imaging (MRI) is a commonly utilized technique to noninvasively study the anatomy and function of rodent brains (Mandino et al, 2019)

  • We demonstrated the use of 3D U-Net for brain extraction in high resolution 3D rat brain MRI data

  • 3D U-Net64 showed high accuracy (Dice > 0.95) in a validation study (Supplementary Figure 2). These results suggest that 3D U-Net64 is a reliable and reproducible approach for rat brain segmentation

Read more

Summary

Introduction

Magnetic resonance imaging (MRI) is a commonly utilized technique to noninvasively study the anatomy and function of rodent brains (Mandino et al, 2019). Rodent brain MRI data is typically acquired at higher magnetic fields (mostly > 7T), where stronger susceptibility artifacts and field biases represent challenges to the rodent brain extraction process. Most rodent MRI studies do not utilize a volume receiver and exhibit higher radiofrequency (RF) coil inhomogeneity. For these reasons, the extraction tools that work with human brains (Kleesiek et al, 2016; Fatima et al, 2020; Wang et al, 2021) cannot be directly adopted for rodent brain applications. A robust and reliable automatic brain extraction tool would streamline the pre-processing pipeline, avoid personnel bias, and significantly improve research efficiency (Babalola et al, 2009; Lu et al, 2010; Gaser et al, 2012; Feo and Giove, 2019; Hsu et al, 2020)

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call