A Novel Tool for Supervised Segmentation Using 3D Slicer

The rather impressive extension library of medical image-processing platform 3D Slicer lacks a wide range of machine-learning toolboxes. The authors have developed such a toolbox that incorporates commonly used machine-learning libraries. The extension uses a simple graphical user interface that all...

Full description

Saved in:
Bibliographic Details
Published in:Symmetry (Basel) 2018-11, Vol.10 (11), p.627
Main Authors: Chalupa, Daniel, Mikulka, Jan
Format: Article
Language:English
Subjects:
3D slicer
Accuracy
Brain cancer
Classification
Classifiers
Datasets
extension
Graphical user interface
Image classification
Image processing
Image segmentation
Impact analysis
Libraries
Machine learning
Medical imaging
Parameters
Physical properties
random forest
segmentation
sensitivity analysis
support vector machine
Support vector machines
Training
tumor
Tumors
Usability
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The rather impressive extension library of medical image-processing platform 3D Slicer lacks a wide range of machine-learning toolboxes. The authors have developed such a toolbox that incorporates commonly used machine-learning libraries. The extension uses a simple graphical user interface that allows the user to preprocess data, train a classifier, and use that classifier in common medical image-classification tasks, such as tumor staging or various anatomical segmentations without a deeper knowledge of the inner workings of the classifiers. A series of experiments were carried out to showcase the capabilities of the extension and quantify the symmetry between the physical characteristics of pathological tissues and the parameters of a classifying model. These experiments also include an analysis of the impact of training vector size and feature selection on the sensitivity and specificity of all included classifiers. The results indicate that training vector size can be minimized for all classifiers. Using the data from the Brain Tumor Segmentation Challenge, Random Forest appears to have the widest range of parameters that produce sufficiently accurate segmentations, while optimal Support Vector Machines’ training parameters are concentrated in a narrow feature space.
ISSN:2073-8994
2073-8994
DOI:10.3390/sym10110627