A Novel Tool for Supervised Segmentation Using 3D Slicer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F18%3APU129719" target="_blank" >RIV/00216305:26220/18:PU129719 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.mdpi.com/2073-8994/10/11/627" target="_blank" >https://www.mdpi.com/2073-8994/10/11/627</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/sym10110627" target="_blank" >10.3390/sym10110627</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Novel Tool for Supervised Segmentation Using 3D Slicer

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

A Novel Tool for Supervised Segmentation Using 3D Slicer

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

<a href="/cs/project/NV18-08-00459" target="_blank" >NV18-08-00459: Prostorová analýza silového zatížení deformované rostoucí páteře a využití modelování korekčních sil k minimalizaci rozsahu operace skoliozy.</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Symmetry

ISSN

2073-8994

e-ISSN

—

Svazek periodika

10

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

9

Strana od-do

1-9

Kód UT WoS článku

000451165100094

EID výsledku v databázi Scopus

2-s2.0-85057783248