Radiomics in paediatric neuro-oncology: A multicentre study on MRI texture analysis

Research output: Contribution to journalArticlepeer-review

Standard

Radiomics in paediatric neuro-oncology : A multicentre study on MRI texture analysis. / Fetit, Ahmed E; Novak, Jan; Rodriguez, Daniel; Auer, Dorothee P; Clark, Christopher A; Grundy, Richard G; Peet, Andrew C; Arvanitis, Theodoros N.

In: NMR in biomedicine, Vol. 31, No. 1, e3781, 01.2018.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Fetit, Ahmed E ; Novak, Jan ; Rodriguez, Daniel ; Auer, Dorothee P ; Clark, Christopher A ; Grundy, Richard G ; Peet, Andrew C ; Arvanitis, Theodoros N. / Radiomics in paediatric neuro-oncology : A multicentre study on MRI texture analysis. In: NMR in biomedicine. 2018 ; Vol. 31, No. 1.

Bibtex

@article{469e311f54d545169c36244f6bd480dc,
title = "Radiomics in paediatric neuro-oncology: A multicentre study on MRI texture analysis",
abstract = "Brain tumours are the most common solid cancers in children in the UK and are the most common cause of cancer deaths in this age group. Despite current advances in MRI, non-invasive diagnosis of paediatric brain tumours has yet to find its way into routine clinical practice. Radiomics, the high-throughput extraction and analysis of quantitative image features (e.g. texture), offers potential solutions for tumour characterization and decision support. In the search for diagnostic oncological markers, the primary aim of this work was to study the application of MRI texture analysis (TA) for the classification of paediatric brain tumours. A multicentre study was carried out, within a supervised classification framework, on clinical MR images, and a support vector machine (SVM) was trained with 3D textural attributes obtained from conventional MRI. To determine the cross-centre transferability of TA, an assessment of how SVM performs on unseen datasets was carried out through rigorous pairwise testing. The study also investigated the nature of features that are most likely to train classifiers that can generalize well with the data. Finally, the issue of class imbalance, which arises due to some tumour types being more common than others, was explored. For each of the tests carried out through pairwise testing, the optimal area under the receiver operating characteristic curve ranged between 76% and 86%, suggesting that the model was able to capture transferable tumour information. Feature selection results suggest that similar aspects of tumour texture are enhanced by MR images obtained at different hospitals. Our results also suggest that the availability of equally represented classes has enabled SVM to better characterize the data points. The findings of the study presented here support the use of 3D TA on conventional MR images to aid diagnostic classification of paediatric brain tumours.",
keywords = "Journal Article",
author = "Fetit, {Ahmed E} and Jan Novak and Daniel Rodriguez and Auer, {Dorothee P} and Clark, {Christopher A} and Grundy, {Richard G} and Peet, {Andrew C} and Arvanitis, {Theodoros N}",
note = "Copyright {\textcopyright} 2017 John Wiley & Sons, Ltd.",
year = "2018",
month = jan,
doi = "10.1002/nbm.3781",
language = "English",
volume = "31",
journal = "NMR in biomedicine",
issn = "0952-3480",
publisher = "Wiley",
number = "1",

}

RIS

TY - JOUR

T1 - Radiomics in paediatric neuro-oncology

T2 - A multicentre study on MRI texture analysis

AU - Fetit, Ahmed E

AU - Novak, Jan

AU - Rodriguez, Daniel

AU - Auer, Dorothee P

AU - Clark, Christopher A

AU - Grundy, Richard G

AU - Peet, Andrew C

AU - Arvanitis, Theodoros N

N1 - Copyright © 2017 John Wiley & Sons, Ltd.

PY - 2018/1

Y1 - 2018/1

N2 - Brain tumours are the most common solid cancers in children in the UK and are the most common cause of cancer deaths in this age group. Despite current advances in MRI, non-invasive diagnosis of paediatric brain tumours has yet to find its way into routine clinical practice. Radiomics, the high-throughput extraction and analysis of quantitative image features (e.g. texture), offers potential solutions for tumour characterization and decision support. In the search for diagnostic oncological markers, the primary aim of this work was to study the application of MRI texture analysis (TA) for the classification of paediatric brain tumours. A multicentre study was carried out, within a supervised classification framework, on clinical MR images, and a support vector machine (SVM) was trained with 3D textural attributes obtained from conventional MRI. To determine the cross-centre transferability of TA, an assessment of how SVM performs on unseen datasets was carried out through rigorous pairwise testing. The study also investigated the nature of features that are most likely to train classifiers that can generalize well with the data. Finally, the issue of class imbalance, which arises due to some tumour types being more common than others, was explored. For each of the tests carried out through pairwise testing, the optimal area under the receiver operating characteristic curve ranged between 76% and 86%, suggesting that the model was able to capture transferable tumour information. Feature selection results suggest that similar aspects of tumour texture are enhanced by MR images obtained at different hospitals. Our results also suggest that the availability of equally represented classes has enabled SVM to better characterize the data points. The findings of the study presented here support the use of 3D TA on conventional MR images to aid diagnostic classification of paediatric brain tumours.

AB - Brain tumours are the most common solid cancers in children in the UK and are the most common cause of cancer deaths in this age group. Despite current advances in MRI, non-invasive diagnosis of paediatric brain tumours has yet to find its way into routine clinical practice. Radiomics, the high-throughput extraction and analysis of quantitative image features (e.g. texture), offers potential solutions for tumour characterization and decision support. In the search for diagnostic oncological markers, the primary aim of this work was to study the application of MRI texture analysis (TA) for the classification of paediatric brain tumours. A multicentre study was carried out, within a supervised classification framework, on clinical MR images, and a support vector machine (SVM) was trained with 3D textural attributes obtained from conventional MRI. To determine the cross-centre transferability of TA, an assessment of how SVM performs on unseen datasets was carried out through rigorous pairwise testing. The study also investigated the nature of features that are most likely to train classifiers that can generalize well with the data. Finally, the issue of class imbalance, which arises due to some tumour types being more common than others, was explored. For each of the tests carried out through pairwise testing, the optimal area under the receiver operating characteristic curve ranged between 76% and 86%, suggesting that the model was able to capture transferable tumour information. Feature selection results suggest that similar aspects of tumour texture are enhanced by MR images obtained at different hospitals. Our results also suggest that the availability of equally represented classes has enabled SVM to better characterize the data points. The findings of the study presented here support the use of 3D TA on conventional MR images to aid diagnostic classification of paediatric brain tumours.

KW - Journal Article

U2 - 10.1002/nbm.3781

DO - 10.1002/nbm.3781

M3 - Article

C2 - 29073725

VL - 31

JO - NMR in biomedicine

JF - NMR in biomedicine

SN - 0952-3480

IS - 1

M1 - e3781

ER -