Format

Send to

Choose Destination
Int J Comput Assist Radiol Surg. 2018 Apr;13(4):563-571. doi: 10.1007/s11548-017-1691-5. Epub 2017 Dec 21.

MRI radiomics analysis of molecular alterations in low-grade gliomas.

Author information

1
Division of Neurosurgery, Tel Aviv Sourasky Medical Center, 6 Weizman St., 64239, Tel Aviv, Israel.
2
Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
3
The Functional Brain Center, Tel Aviv Sourasky Medical Center, 6 Weizman St., 64239, Tel Aviv, Israel.
4
Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel. dafnab@tlvmc.gov.il.
5
The Functional Brain Center, Tel Aviv Sourasky Medical Center, 6 Weizman St., 64239, Tel Aviv, Israel. dafnab@tlvmc.gov.il.
6
Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel. dafnab@tlvmc.gov.il.
7
Department of Chemical Physics, Weizmann Institute of Science, Rehovot, Israel.
8
Neuro-Oncology Service, Tel-Aviv Medical Center, Tel Aviv, Israel.
9
Department of Neurosurgery, Shaare Zedek Medical Center, Jerusalem, Israel.

Abstract

PURPOSE:

Low-grade gliomas (LGG) are classified into three distinct groups based on their IDH1 mutation and 1p/19q codeletion status, each of which is associated with a different clinical expression. The genomic sub-classification of LGG requires tumor sampling via neurosurgical procedures. The aim of this study was to evaluate the radiomics approach for noninvasive classification of patients with LGG and IDH mutation, based on their 1p/19q codeletion status, by testing different classifiers and assessing the contribution of the different MR contrasts.

METHODS:

Preoperative MRI scans of 47 patients diagnosed with LGG with IDH1-mutated tumors and a genetic analysis for 1p/19q deletion status were included in this study. A total of 152 features, including size, location and texture, were extracted from fluid-attenuated inversion recovery images, [Formula: see text]-weighted images (WI) and post-contrast [Formula: see text]. Classification was performed using 17 machine learning classifiers. Results were evaluated by a fivefold cross-validation analysis.

RESULTS:

Radiomic analysis differentiated tumors with 1p/19q intact ([Formula: see text]; astrocytomas) from those with 1p/19q codeleted ([Formula: see text]; oligodendrogliomas). Best classification was obtained using the Ensemble Bagged Trees classifier, with sensitivity [Formula: see text] 92%, specificity [Formula: see text] 83% and accuracy [Formula: see text] 87%, and with area under the curve [Formula: see text] 0.87. Tumors with 1p/19q intact were larger than those with 1p/19q codeleted ([Formula: see text] vs. [Formula: see text] cc, respectively; [Formula: see text]) and predominantly located to the left insula ([Formula: see text]).

CONCLUSION:

The proposed method yielded good discrimination between LGG with and without 1p/19q codeletion. Results from this study demonstrate the great potential of this method to aid decision-making in the clinical management of patients with LGG.

KEYWORDS:

1p/19q Codeletion; Low-grade gliomas; MRI; Machine learning classifiers; Radiomics

PMID:
29270916
DOI:
10.1007/s11548-017-1691-5
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center