A hydrolyzed lipid blend diet promotes myelination in neonatal piglets in a region and concentration-dependent manner.

The impact of early life nutrition on myelin development is of interest given that cognitive and behavioral function depends on proper myelination. Evidence shows that myelination can be altered by dietary lipid, but most of these studies have been performed in the context of disease or impairment. Here, we assessed the effects of lipid blends containing various levels of a hydrolyzed fat (HF) system on myelination in healthy piglets. Piglets were sow-reared, fed a control diet, or a diet containing 12%, 25%, or 53% HF consisting of cholesterol, fatty acids, monoglycerides, and phospholipid from lecithin. At postnatal day 28/29, magnetic resonance imaging (MRI) was performed to assess changes to brain development, followed by brain collection for microscopic analyses of myelin in targeted regions using CLARITY tissue clearing, immunohistochemistry, and electron microscopy techniques. Sow-reared piglets exhibited the highest overall brain white matter volume by MRI. However, a 25% HF diet resulted in the greatest total myelin density in the prefrontal cortex based on 3D modeling analysis of myelinated filaments. Nodal gap length and g-ratio were inversely correlated with percentage of HF in the corpus callosum, as well as in the PFC and internal capsule for g-ratio, indicating that a 53% HF diet resulted in the thickest myelin per axon and a 0% HF control diet the thinnest in specific brain regions. These findings indicate that HF promoted myelination in the neonatal piglet in a region- and concentration-dependent manner.

Automated identification of piglet brain tissue from MRI images using Region-based Convolutional Neural Networks.

Magnetic resonance imaging is an important tool for characterizing volumetric changes of the piglet brain during development. Typically, an early step of an imaging analysis pipeline is brain extraction, or skull stripping. Brain extractions are usually performed manually; however, this approach is time-intensive and can lead to variation between brain extractions when multiple raters are used. Automated brain extractions are important for reducing the time required for analyses and improving the uniformity of the extractions. Here we demonstrate the use of Mask R-CNN, a Region-based Convolutional Neural Network (R-CNN), for automated brain extractions of piglet brains. We validate our approach using Nested Cross-Validation on six sets of training/validation data drawn from 32 pigs. Visual inspection of the extractions shows acceptable accuracy, Dice coefficients are in the range of 0.95-0.97, and Hausdorff Distance values in the range of 4.1-8.3 voxels. These results demonstrate that R-CNNs provide a viable tool for skull stripping of piglet brains.