Axonal Structure Identification Using a Graph Transversal and Path Search Algorithm

Session Number

Project ID: CMPS 27

Advisor(s)

Dr. Gregory W. Schwartz, Northwestern University, Feinberg School of Medicine,

Discipline

Computer Science

Start Date

17-4-2024 10:00 AM

End Date

17-4-2024 10:15 AM

Abstract

ImageJ is a software platform for open-source image analysis that has assisted researchers with various image analysis applications. Its success has been primarily attributed to supportive and cooperative developer and user communities. ImageJ is also useful for data segmentation, which assigns a label to every pixel in an image such that images with the same label share similar qualities. Segmenting objects is the first step in tracking analysis, which allows researchers to follow the segmented objects' movements over time. Many advanced tools and techniques, including Trainable WEKA Segmentation (TWS) and Labkit, use machine learning to implement pixel classification functionality through the open WEKA library for segmentation. The data used in this study underwent immunohistochemical staining and revealed axonal structures in three separate panels. This paper presents a qualitative analysis of another Fiji plugin, PathFinder, that utilizes a graph transversal and path search algorithm called A* and uses heuristics to estimate the most efficient path, alongside TWS and LabKit.

Share

COinS
 
Apr 17th, 10:00 AM Apr 17th, 10:15 AM

Axonal Structure Identification Using a Graph Transversal and Path Search Algorithm

ImageJ is a software platform for open-source image analysis that has assisted researchers with various image analysis applications. Its success has been primarily attributed to supportive and cooperative developer and user communities. ImageJ is also useful for data segmentation, which assigns a label to every pixel in an image such that images with the same label share similar qualities. Segmenting objects is the first step in tracking analysis, which allows researchers to follow the segmented objects' movements over time. Many advanced tools and techniques, including Trainable WEKA Segmentation (TWS) and Labkit, use machine learning to implement pixel classification functionality through the open WEKA library for segmentation. The data used in this study underwent immunohistochemical staining and revealed axonal structures in three separate panels. This paper presents a qualitative analysis of another Fiji plugin, PathFinder, that utilizes a graph transversal and path search algorithm called A* and uses heuristics to estimate the most efficient path, alongside TWS and LabKit.