|
Activity Number:
|
157
- Contributed Poster Presentations: Section on Statistics in Imaging
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 8, 2022 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistics in Imaging
|
|
Abstract #323446
|
|
|
Title:
|
BOSS: Beta-Mixture Unsupervised Oligodendrocytes Segmentation System
|
|
Author(s):
|
Eunchan Caleb Bae* and Jennifer L Orthmann-murphy and Russell Shinohara
|
|
Companies:
|
University of Pennsylvania and University of Pennsylvania and University of Pennsylvania
|
|
Keywords:
|
Segmentation;
Tracking;
Unsupervised Model;
Mixture Model;
Oligodendrocytes;
Multiple Sclerosis
|
|
Abstract:
|
Oligodendrocytes are myelinating cells of the central nervous system (CNS). There is an urgent need to better understand the physiology of loss and replacement of oligodendrocytes to develop reparative therapies for demyelinating disorders like multiple sclerosis (MS). In vivo two photon fluorescence microscopy has recently been developed to visualize oligodendrogenesis and myelin sheath dynamics in cortical circuits at high resolution. This technology allows for the investigation of the loss and replacement of oligodendrocytes and myelination patterns in acquired demyelination models. With development of this new imaging method, there is a growing need for automated quantification and analysis of changes in oligodendrocytes. Here, we propose a novel beta-mixture unsupervised oligodendrocyte segmentation system (BOSS) that can segment and track oligodendrocytes in three-dimensional images over time. We evaluated the performance of the BOSS model on a set of eight longitudinally imaged cortical volumes from the intact rodent brain. We showed that the BOSS model can segment and track oligodendrocytes similar to a blinded human observer.
|
Authors who are presenting talks have a * after their name.
