Journal Article

Local shape descriptors for neuron segmentation

Sheridan, Arlo, Saalfeld, Stephan, Manor, Uri, Turaga, Srinivas C., Funke, Jan, Lee, Wei-Chung Allen, Deb, Diptodip, Nguyen, Tri M.

2023

Overview

We present an auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of local shape descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The shape descriptors capture local statistics about the neuron to be segmented, such as diameter, elongation, and direction. On a study comparing several existing methods across various specimen, imaging techniques, and resolutions, auxiliary learning of LSDs consistently increases segmentation accuracy of affinity-based methods over a range of metrics. Furthermore, the addition of LSDs promotes affinity-based segmentation methods to be on par with the current state of the art for neuron segmentation (flood-filling networks), while being two orders of magnitudes more efficient—a critical requirement for the processing of future petabyte-sized datasets. During segmentation of neurons in electron microscopy datasets, auxiliary learning via the prediction of local shape descriptors increases efficiency, which is important for the processing of datasets of ever-increasing size.

• Publisher: Nature Publishing Group US,Nature Publishing Group
• Subject: 631/114/1305 / 631/114/1564 / 631/378/116 / Affinity / Bioinformatics / Biological Microscopy / Biological Techniques / Biomedical and Life Sciences / Biomedical Engineering/Biotechnology / Cognitive tasks / Datasets / Electron microscopy / Elongation / Image Processing, Computer-Assisted - methods / Image segmentation / Imaging techniques / Learning / Life Sciences / Microscopy / Neurons / Proteomics