Cargando…

Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients

Glioblastoma is an aggressive brain tumor with a low survival rate. Understanding tumor behavior by predicting prognosis outcomes is a crucial factor in deciding a proper treatment plan. In this paper, an automatic overall survival time prediction system (OST) for glioblastoma patients is developed...

Descripción completa

Detalles Bibliográficos
Autores principales: Chato, Lina, Latifi, Shahram
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8705288/
https://www.ncbi.nlm.nih.gov/pubmed/34945808
http://dx.doi.org/10.3390/jpm11121336
_version_ 1784621909260894208
author Chato, Lina
Latifi, Shahram
author_facet Chato, Lina
Latifi, Shahram
author_sort Chato, Lina
collection PubMed
description Glioblastoma is an aggressive brain tumor with a low survival rate. Understanding tumor behavior by predicting prognosis outcomes is a crucial factor in deciding a proper treatment plan. In this paper, an automatic overall survival time prediction system (OST) for glioblastoma patients is developed on the basis of radiomic features and machine learning (ML). This system is designed to predict prognosis outcomes by classifying a glioblastoma patient into one of three survival groups: short-term, mid-term, and long-term. To develop the prediction system, a medical dataset based on imaging information from magnetic resonance imaging (MRI) and non-imaging information is used. A novel radiomic feature extraction method is proposed and developed on the basis of volumetric and location information of brain tumor subregions extracted from MRI scans. This method is based on calculating the volumetric features from two brain sub-volumes obtained from the whole brain volume in MRI images using brain sectional planes (sagittal, coronal, and horizontal). Many experiments are conducted on the basis of various ML methods and combinations of feature extraction methods to develop the best OST system. In addition, the feature fusions of both radiomic and non-imaging features are examined to improve the accuracy of the prediction system. The best performance was achieved by the neural network and feature fusions.
format Online
Article
Text
id pubmed-8705288
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87052882021-12-25 Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients Chato, Lina Latifi, Shahram J Pers Med Article Glioblastoma is an aggressive brain tumor with a low survival rate. Understanding tumor behavior by predicting prognosis outcomes is a crucial factor in deciding a proper treatment plan. In this paper, an automatic overall survival time prediction system (OST) for glioblastoma patients is developed on the basis of radiomic features and machine learning (ML). This system is designed to predict prognosis outcomes by classifying a glioblastoma patient into one of three survival groups: short-term, mid-term, and long-term. To develop the prediction system, a medical dataset based on imaging information from magnetic resonance imaging (MRI) and non-imaging information is used. A novel radiomic feature extraction method is proposed and developed on the basis of volumetric and location information of brain tumor subregions extracted from MRI scans. This method is based on calculating the volumetric features from two brain sub-volumes obtained from the whole brain volume in MRI images using brain sectional planes (sagittal, coronal, and horizontal). Many experiments are conducted on the basis of various ML methods and combinations of feature extraction methods to develop the best OST system. In addition, the feature fusions of both radiomic and non-imaging features are examined to improve the accuracy of the prediction system. The best performance was achieved by the neural network and feature fusions. MDPI 2021-12-09 /pmc/articles/PMC8705288/ /pubmed/34945808 http://dx.doi.org/10.3390/jpm11121336 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chato, Lina
Latifi, Shahram
Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients
title Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients
title_full Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients
title_fullStr Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients
title_full_unstemmed Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients
title_short Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients
title_sort machine learning and radiomic features to predict overall survival time for glioblastoma patients
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8705288/
https://www.ncbi.nlm.nih.gov/pubmed/34945808
http://dx.doi.org/10.3390/jpm11121336
work_keys_str_mv AT chatolina machinelearningandradiomicfeaturestopredictoverallsurvivaltimeforglioblastomapatients
AT latifishahram machinelearningandradiomicfeaturestopredictoverallsurvivaltimeforglioblastomapatients