Axon Centerline Detection
As advances in microscopy imaging provide an ever clearer window into the human brain, accurate reconstruction of neural connectivity can yield valuable insight into the relationship between brain structure and function. However, human manual tracing is a slow and laborious task, and requires domain expertise. Automated methods are thus needed to enable rapid and accurate analysis at scale. This toolbox implements deep neural networks for dense axon tracing while incorporating axon topological information into the loss function with a goal to improve the performance on both voxel-based segmentation and axon centerline detection. We evaluated three models using a modified 3D U-Net architecture trained on a mouse brain dataset imaged with light sheet microscopy and achieved a 10% increase in axon tracing accuracy over previous methods.
Toolbox for segmentation and centerline detection in axon imagery.
As advances in microscopy imaging provide an ever clearer window into the human brain, accurate reconstruction of neural connectivity can yield valuable insight into the relationship between brain structure and function. However, human manual tracing is a slow and laborious task, and requires domain expertise. Automated methods are thus needed to enable rapid and accurate analysis at scale. This toolbox implements deep neural networks for dense axon tracing while incorporating axon topological information into the loss function with a goal to improve the performance on both voxel-based segmentation and axon centerline detection. We evaluated three models using a modified 3D U-Net architecture trained on a mouse brain dataset imaged with light sheet microscopy and achieved a 10% increase in axon tracing accuracy over previous methods.