Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics

Sarv Priya; Yanan Liu; Caitlin Ward; Nam H Le; Neetu Soni; Ravishankar Pillenahalli Maheshwarappa; Varun Monga; Honghai Zhang; Milan Sonka; Girish Bathla

doi:10.1038/s41598-021-90032-w

Back

Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics

Journal article

Open access

Peer reviewed

Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics

Sarv Priya, Yanan Liu, Caitlin Ward, Nam H Le, Neetu Soni, Ravishankar Pillenahalli Maheshwarappa, Varun Monga, Honghai Zhang, Milan Sonka and Girish Bathla

Scientific reports, Vol.11(1), pp.10478-10478

05/18/2021

DOI: 10.1038/s41598-021-90032-w

PMID: 34006893

Files and links (1)

url

https://doi.org/10.1038/s41598-021-90032-wView

Published (Version of record) Open Access

Abstract

Few studies have addressed radiomics based differentiation of Glioblastoma (GBM) and intracranial metastatic disease (IMD). However, the effect of different tumor masks, comparison of single versus multiparametric MRI (mp-MRI) or select combination of sequences remains undefined. We cross-compared multiple radiomics based machine learning (ML) models using mp-MRI to determine optimized configurations. Our retrospective study included 60 GBM and 60 IMD patients. Forty-five combinations of ML models and feature reduction strategies were assessed for features extracted from whole tumor and edema masks using mp-MRI [T1W, T2W, T1-contrast enhanced (T1-CE), ADC, FLAIR], individual MRI sequences and combined T1-CE and FLAIR sequences. Model performance was assessed using receiver operating characteristic curve. For mp-MRI, the best model was LASSO model fit using full feature set (AUC 0.953). FLAIR was the best individual sequence (LASSO-full feature set, AUC 0.951). For combined T1-CE/FLAIR sequence, adaBoost-full feature set was the best performer (AUC 0.951). No significant difference was seen between top models across all scenarios, including models using FLAIR only, mp-MRI and combined T1-CE/FLAIR sequence. Top features were extracted from both the whole tumor and edema masks. Shape sphericity is an important discriminating feature.

Cancer imaging

CNS cancer

Details

Title: Subtitle: Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics
Creators: Sarv Priya - 200 Hawkins Drive, Iowa City, IA 52242 USA
Yanan Liu - Iowa City, IA USA
Caitlin Ward - Iowa City, IA USA
Nam H Le - Iowa City, IA USA
Neetu Soni - 200 Hawkins Drive, Iowa City, IA 52242 USA
Ravishankar Pillenahalli Maheshwarappa - 200 Hawkins Drive, Iowa City, IA 52242 USA
Varun Monga - Iowa City, IA USA
Honghai Zhang - Iowa City, IA USA
Milan Sonka - Iowa City, IA USA
Girish Bathla - 200 Hawkins Drive, Iowa City, IA 52242 USA
Resource Type: Journal article
Publication Details: Scientific reports, Vol.11(1), pp.10478-10478
DOI: 10.1038/s41598-021-90032-w
PMID: 34006893
NLM abbreviation: Sci Rep
ISSN: 2045-2322
eISSN: 2045-2322
Publisher: Nature Publishing Group UK
Language: English
Date published: 05/18/2021
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Hematology, Oncology, and Blood & Marrow Transplantation; Engineering Administration; Radiation Oncology; Nursing; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Internal Medicine; Ophthalmology and Visual Sciences
Record Identifier: 9984101223302771

Metrics

29 Record Views

34 Times Cited - Web of Science