automatic lesion pattern discrimination
Posted: Fri Jun 25, 2021 12:30 am
A R-Script for Generating Multiple Sclerosis Lesion Pattern Discrimination Plots
https://www.researchgate.net/profile/Ro ... -Plots.pdf
Abstract:
One significant characteristic of Multiple Sclerosis (MS), a chronic inflammatory demyelinating disease of the central nervous system, is the evolution of highly variable patterns of white matter lesions.
Based on geostatistical metrics, the MS-Lesion Pattern Discrimination Plot reduces complex three- and four-dimensional configurations of MS-White Matter Lesions to a well-arranged and standardized two-dimensional plot that facilitates follow-up, cross-sectional and medication impact analysis.
Here, we present a script that generates the MS-Lesion Pattern Discrimination Plot, using the widespread statistical computing environment R.
Input data to the script are Nifti-1 or Analyze-7.5 files with individual MS-White Matter Lesion masks in Montreal Normal Brain geometry.The MS-Lesion Pattern Discrimination Plot, variogram plots and associated fitting statistics are output to the R console and exported to standard graphics and text files.
Besides reviewing relevant geostatistical basics and commenting on implementation details for smooth customization and extension, the paper guides through generating MS-Lesion Pattern Discrimination Plots using publicly available synthetic MS-Lesion patterns.
The paper is accompanied by the R script LDP generator.r, a small sample data set and associated graphics for comparison.
https://www.researchgate.net/profile/Ro ... -Plots.pdf
Abstract:
One significant characteristic of Multiple Sclerosis (MS), a chronic inflammatory demyelinating disease of the central nervous system, is the evolution of highly variable patterns of white matter lesions.
Based on geostatistical metrics, the MS-Lesion Pattern Discrimination Plot reduces complex three- and four-dimensional configurations of MS-White Matter Lesions to a well-arranged and standardized two-dimensional plot that facilitates follow-up, cross-sectional and medication impact analysis.
Here, we present a script that generates the MS-Lesion Pattern Discrimination Plot, using the widespread statistical computing environment R.
Input data to the script are Nifti-1 or Analyze-7.5 files with individual MS-White Matter Lesion masks in Montreal Normal Brain geometry.The MS-Lesion Pattern Discrimination Plot, variogram plots and associated fitting statistics are output to the R console and exported to standard graphics and text files.
Besides reviewing relevant geostatistical basics and commenting on implementation details for smooth customization and extension, the paper guides through generating MS-Lesion Pattern Discrimination Plots using publicly available synthetic MS-Lesion patterns.
The paper is accompanied by the R script LDP generator.r, a small sample data set and associated graphics for comparison.