Abstract

The present study proposed a computer-aided diagnosis system based on radiomic features extracted through magnetic resonance imaging to determine the isocitrate dehydrogenase status in glioblastomas. Magnetic resonance imaging data were obtained from 32 patients with wild-typeisocitrate dehydrogenase and 7 patients with mutant isocitrate dehydrogenase in glioblastomas. Radiomic features, namely morphological, intensity, and textural features, were extracted from the tumor area of each patient. The feature sets were evaluated using a logistic regression classifier to develop a prediction model. The accuracy of the global morphological and intensity features was 51% (20/39) and 59% (23/39), respectively. The textural features describing local patterns yielded an accuracy of 85% (33/39), which is significantly higher than that yielded by the morphological and intensity features. The agreement level (κ) between the prediction results and biopsy-proven pathology was 0.60. The proposed diagnosis system based on radiomic textural features shows promise for application in providing suggestions to radiologists for distinguishing isocitrate dehydrogenase mutations in glioblastomas.

Original languageEnglish
Pages (from-to)45888-45897
Number of pages10
JournalOncotarget
Volume8
Issue number28
DOIs
Publication statusPublished - 2017

Fingerprint

Isocitrate Dehydrogenase
Glioblastoma
Mutation
Magnetic Resonance Imaging
Genes
Oxidoreductases
Logistic Models
Pathology
Biopsy
Neoplasms

Keywords

  • Brain tumor
  • Computer-aided diagnosis
  • Glioblastoma
  • Isocitrate dehydrogenase
  • Magnetic resonance imaging

ASJC Scopus subject areas

  • Oncology

Cite this

Radiomic model for predicting mutations in the isocitrate dehydrogenase gene in glioblastomas. / Hsieh, Kevin Li Chun; Chen, Cheng Yu; Lo, Chung Ming.

In: Oncotarget, Vol. 8, No. 28, 2017, p. 45888-45897.

Research output: Contribution to journalArticle

@article{340469c27bd04eb5a5fd37c365717aea,
title = "Radiomic model for predicting mutations in the isocitrate dehydrogenase gene in glioblastomas",
abstract = "The present study proposed a computer-aided diagnosis system based on radiomic features extracted through magnetic resonance imaging to determine the isocitrate dehydrogenase status in glioblastomas. Magnetic resonance imaging data were obtained from 32 patients with wild-typeisocitrate dehydrogenase and 7 patients with mutant isocitrate dehydrogenase in glioblastomas. Radiomic features, namely morphological, intensity, and textural features, were extracted from the tumor area of each patient. The feature sets were evaluated using a logistic regression classifier to develop a prediction model. The accuracy of the global morphological and intensity features was 51{\%} (20/39) and 59{\%} (23/39), respectively. The textural features describing local patterns yielded an accuracy of 85{\%} (33/39), which is significantly higher than that yielded by the morphological and intensity features. The agreement level (κ) between the prediction results and biopsy-proven pathology was 0.60. The proposed diagnosis system based on radiomic textural features shows promise for application in providing suggestions to radiologists for distinguishing isocitrate dehydrogenase mutations in glioblastomas.",
keywords = "Brain tumor, Computer-aided diagnosis, Glioblastoma, Isocitrate dehydrogenase, Magnetic resonance imaging",
author = "Hsieh, {Kevin Li Chun} and Chen, {Cheng Yu} and Lo, {Chung Ming}",
year = "2017",
doi = "10.18632/oncotarget.17585",
language = "English",
volume = "8",
pages = "45888--45897",
journal = "Oncotarget",
issn = "1949-2553",
publisher = "Impact Journals LLC",
number = "28",

}

TY - JOUR

T1 - Radiomic model for predicting mutations in the isocitrate dehydrogenase gene in glioblastomas

AU - Hsieh, Kevin Li Chun

AU - Chen, Cheng Yu

AU - Lo, Chung Ming

PY - 2017

Y1 - 2017

N2 - The present study proposed a computer-aided diagnosis system based on radiomic features extracted through magnetic resonance imaging to determine the isocitrate dehydrogenase status in glioblastomas. Magnetic resonance imaging data were obtained from 32 patients with wild-typeisocitrate dehydrogenase and 7 patients with mutant isocitrate dehydrogenase in glioblastomas. Radiomic features, namely morphological, intensity, and textural features, were extracted from the tumor area of each patient. The feature sets were evaluated using a logistic regression classifier to develop a prediction model. The accuracy of the global morphological and intensity features was 51% (20/39) and 59% (23/39), respectively. The textural features describing local patterns yielded an accuracy of 85% (33/39), which is significantly higher than that yielded by the morphological and intensity features. The agreement level (κ) between the prediction results and biopsy-proven pathology was 0.60. The proposed diagnosis system based on radiomic textural features shows promise for application in providing suggestions to radiologists for distinguishing isocitrate dehydrogenase mutations in glioblastomas.

AB - The present study proposed a computer-aided diagnosis system based on radiomic features extracted through magnetic resonance imaging to determine the isocitrate dehydrogenase status in glioblastomas. Magnetic resonance imaging data were obtained from 32 patients with wild-typeisocitrate dehydrogenase and 7 patients with mutant isocitrate dehydrogenase in glioblastomas. Radiomic features, namely morphological, intensity, and textural features, were extracted from the tumor area of each patient. The feature sets were evaluated using a logistic regression classifier to develop a prediction model. The accuracy of the global morphological and intensity features was 51% (20/39) and 59% (23/39), respectively. The textural features describing local patterns yielded an accuracy of 85% (33/39), which is significantly higher than that yielded by the morphological and intensity features. The agreement level (κ) between the prediction results and biopsy-proven pathology was 0.60. The proposed diagnosis system based on radiomic textural features shows promise for application in providing suggestions to radiologists for distinguishing isocitrate dehydrogenase mutations in glioblastomas.

KW - Brain tumor

KW - Computer-aided diagnosis

KW - Glioblastoma

KW - Isocitrate dehydrogenase

KW - Magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=85022219723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022219723&partnerID=8YFLogxK

U2 - 10.18632/oncotarget.17585

DO - 10.18632/oncotarget.17585

M3 - Article

AN - SCOPUS:85022219723

VL - 8

SP - 45888

EP - 45897

JO - Oncotarget

JF - Oncotarget

SN - 1949-2553

IS - 28

ER -