Provides functionality for image processing and shape analysis in the context of reconstructed medical images generated by deep learning-based methods or standard image processing algorithms and produced from different medical imaging types, such as X-ray, Computational Tomography (CT), Magnetic Resonance Imaging (MRI), and pathology imaging. Specifically, offers tools to segment regions of interest and to extract quantitative shape descriptors for applications in signal processing, statistical analysis and modeling, and machine learning.
The R package SAFARI (Shape Analysis for AI-Reconstructed Images) provides functions for reading, preprocessing, segmenting ROI, and extracting shape-based features in AI-reconstructed images.
SAFARI is an R package that consists of a collection of functions for image processing and shape analysis. The available functions allow users to segment regions of interest and extract quantitative shape descriptors in AI-reconstructed images, especially those produced from medical imaging modalities.
The latest version of the package is under development at GitHub. One may install it by
## install.packages("devtools")
devtools::install_github("estfernandez/SAFARI")
This package requires the use of EBImage from the
Bioconductor
project. One must install this package by
## install.packages("BiocManager")
BiocManager::install("EBImage")
Examples are provided for the main functions. One may get started from those examples and the function documentation. We also provide a command-line tool for applications in the terminal.
library(SAFARI)
?read.image # read and preprocess reconstructed image
?binary.segmentation # segmentation procedure
?compute.features # feature extraction for an individual ROI
?rc.plot # visualize binary or segmented images