Automated Brain Masking of Fetal Functional MRI with Open Data

Abstract

Fetal resting-state functional magnetic resonance imaging (rs-fMRI) has emerged as a critical new approach for characterizing brain development before birth. Despite the rapid and widespread growth of this approach, at present, we lack neuroimaging processing pipelines suited to address the unique challenges inherent in this data type. Here, we solve the most challenging processing step, rapid and accurate isolation of the fetal brain from surrounding tissue across thousands of non-stationary 3D brain volumes. Leveraging our library of 1,241 manually traced fetal fMRI images from 207 fetuses, we trained a Convolutional Neural Network (CNN) that achieved excellent performance across two held-out test sets from separate scanners and populations. Furthermore, we unite the auto-masking model with additional fMRI preprocessing steps from existing software and provide insight into our adaptation of each step. This work represents an initial advancement towards a fully comprehensive, open-source workflow, with openly shared code and data, for fetal functional MRI data preprocessing.

Hypoconnectivity between anterior insula and amygdala in neonates with familial history of autism

“…Functional data were processed using validated fetal fMRI pipelines. 53,54 Functional data were corrected for motion using a two-pass registration approach optimized for fetuses to correct for large and small head movements. 53 Outlying frames were censored for data quality based on signal-to-noise (SNR) ratio within the fetal brain, the final weighted correlation value from optimization, and the frame-to-frame motion between adjacent frames.…”

An ode to fetal, infant, and toddler neuroimaging: Chronicling early clinical to research applications with MRI, and an introduction to an academic society connecting the field

“…Fetal MRI has also been used for gestational-age equivalent controls for preterm infants ( Bouyssi-Kobar et al, 2016 , De Asis-Cruz et al, 2020 , Khan et al, 2019 ). In large part, this work has been made possible by new methodological advancements in MRI acquisition techniques and analysis pipelines ( Fogtmann et al, 2014 , Kim et al, 2010 , Marami et al, 2017 , Pontabry et al, 2017 , Rutherford et al, 2021 , Seshamani et al, 2013 ).…”

FetalGAN: Automated Segmentation of Fetal Functional Brain MRI Using Deep Generative Adversarial Learning and Multi-Scale 3D U-Net

“…Deep convolutional neural networks (CNN) such as U-Net have achieved remarkable success for anatomical medical image segmentation and have been shown to be versatile and effective ( Ronneberger et al, 2015 ; Yang et al, 2018 ; Zhao et al, 2018 ; Son et al, 2020 ). Recently, 2D U-Net has been successfully applied to fetal resting state functional MRI data ( Rutherford et al, 2021 ), a crucial step in automating preprocessing of fetal rs-fMRI. However, there are several limitations in using CNN-based approaches for segmentation ( Ronneberger et al, 2015 ; Xue et al, 2018 ; Li et al, 2019 ; Rutherford et al, 2021 ).…”

“…Recently, 2D U-Net has been successfully applied to fetal resting state functional MRI data ( Rutherford et al, 2021 ), a crucial step in automating preprocessing of fetal rs-fMRI. However, there are several limitations in using CNN-based approaches for segmentation ( Ronneberger et al, 2015 ; Xue et al, 2018 ; Li et al, 2019 ; Rutherford et al, 2021 ). Although U-Nets can use skip connections to combine both low- and high-level features, there is no guarantee of spatial consistency in the final segmentation map, especially at the boundaries ( Isola et al, 2017 ; Yang et al, 2018 ; Zhao et al, 2018 ; Dhinagar et al, 2021 ).…”

“…Generally, traditional CNNs have a tradeoff between achieving good localization performance/higher level of semantics (i.e., correctly classifying each voxel’s label) and crisper, more well-defined boundaries. This is a potential disadvantage specifically when applied to brain segmentation of fetal rs-fMRI, which often have low-contrast boundaries, varied voxel intensities, and features at different scales/orientations ( Ronneberger et al, 2015 ; Xue et al, 2018 ; Dolz et al, 2020 ; Rutherford et al, 2021 ).…”