Three-dimensional textural features of conventional MRI improve diagnostic classification of childhood brain tumours

Research output: Contribution to journalArticlepeer-review

Standard

Three-dimensional textural features of conventional MRI improve diagnostic classification of childhood brain tumours. / Fetit, Ahmed-Elsayed; Novak, Jan; Peet, Andrew; Arvanitis, Theodoros.

In: NMR in biomedicine, Vol. 28, No. 9, 01.09.2015, p. 1174-1184.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{3d71896e1df04df59ee8d7f5eb2dd269,
title = "Three-dimensional textural features of conventional MRI improve diagnostic classification of childhood brain tumours",
abstract = "The aim of this study was to assess the efficacy of three‐dimensional texture analysis (3D TA) of conventional MR images for the classification of childhood brain tumours in a quantitative manner. The dataset comprised pre‐contrast T1‐ and T2‐weighted MRI series obtained from 48 children diagnosed with brain tumours (medulloblastoma, pilocytic astrocytoma and ependymoma). 3D and 2D TA were carried out on the images using first‐, second‐ and higher order statistical methods. Six supervised classification algorithms were trained with the most influential 3D and 2D textural features, and their performances in the classification of tumour types, using the two feature sets, were compared. Model validation was carried out using the leave‐one‐out cross‐validation (LOOCV) approach, as well as stratified 10‐fold cross‐validation, in order to provide additional reassurance. McNemar's test was used to test the statistical significance of any improvements demonstrated by 3D‐trained classifiers. Supervised learning models trained with 3D textural features showed improved classification performances to those trained with conventional 2D features. For instance, a neural network classifier showed 12% improvement in area under the receiver operator characteristics curve (AUC) and 19% in overall classification accuracy. These improvements were statistically significant for four of the tested classifiers, as per McNemar's tests. This study shows that 3D textural features extracted from conventional T1‐ and T2‐weighted images can improve the diagnostic classification of childhood brain tumours. Long‐term benefits of accurate, yet non‐invasive, diagnostic aids include a reduction in surgical procedures, improvement in surgical and therapy planning, and support of discussions with patients' families. It remains necessary, however, to extend the analysis to a multicentre cohort in order to assess the scalability of the techniques used. ",
keywords = "3D texture analysis, T1- and T2-weighted MRI, paediatric brain tumours, classification, machine learning",
author = "Ahmed-Elsayed Fetit and Jan Novak and Andrew Peet and Theodoros Arvanitis",
year = "2015",
month = sep,
day = "1",
doi = "10.1002/nbm.3353",
language = "English",
volume = "28",
pages = "1174--1184",
journal = "NMR in biomedicine",
issn = "0952-3480",
publisher = "Wiley",
number = "9",

}

RIS

TY - JOUR

T1 - Three-dimensional textural features of conventional MRI improve diagnostic classification of childhood brain tumours

AU - Fetit, Ahmed-Elsayed

AU - Novak, Jan

AU - Peet, Andrew

AU - Arvanitis, Theodoros

PY - 2015/9/1

Y1 - 2015/9/1

N2 - The aim of this study was to assess the efficacy of three‐dimensional texture analysis (3D TA) of conventional MR images for the classification of childhood brain tumours in a quantitative manner. The dataset comprised pre‐contrast T1‐ and T2‐weighted MRI series obtained from 48 children diagnosed with brain tumours (medulloblastoma, pilocytic astrocytoma and ependymoma). 3D and 2D TA were carried out on the images using first‐, second‐ and higher order statistical methods. Six supervised classification algorithms were trained with the most influential 3D and 2D textural features, and their performances in the classification of tumour types, using the two feature sets, were compared. Model validation was carried out using the leave‐one‐out cross‐validation (LOOCV) approach, as well as stratified 10‐fold cross‐validation, in order to provide additional reassurance. McNemar's test was used to test the statistical significance of any improvements demonstrated by 3D‐trained classifiers. Supervised learning models trained with 3D textural features showed improved classification performances to those trained with conventional 2D features. For instance, a neural network classifier showed 12% improvement in area under the receiver operator characteristics curve (AUC) and 19% in overall classification accuracy. These improvements were statistically significant for four of the tested classifiers, as per McNemar's tests. This study shows that 3D textural features extracted from conventional T1‐ and T2‐weighted images can improve the diagnostic classification of childhood brain tumours. Long‐term benefits of accurate, yet non‐invasive, diagnostic aids include a reduction in surgical procedures, improvement in surgical and therapy planning, and support of discussions with patients' families. It remains necessary, however, to extend the analysis to a multicentre cohort in order to assess the scalability of the techniques used.

AB - The aim of this study was to assess the efficacy of three‐dimensional texture analysis (3D TA) of conventional MR images for the classification of childhood brain tumours in a quantitative manner. The dataset comprised pre‐contrast T1‐ and T2‐weighted MRI series obtained from 48 children diagnosed with brain tumours (medulloblastoma, pilocytic astrocytoma and ependymoma). 3D and 2D TA were carried out on the images using first‐, second‐ and higher order statistical methods. Six supervised classification algorithms were trained with the most influential 3D and 2D textural features, and their performances in the classification of tumour types, using the two feature sets, were compared. Model validation was carried out using the leave‐one‐out cross‐validation (LOOCV) approach, as well as stratified 10‐fold cross‐validation, in order to provide additional reassurance. McNemar's test was used to test the statistical significance of any improvements demonstrated by 3D‐trained classifiers. Supervised learning models trained with 3D textural features showed improved classification performances to those trained with conventional 2D features. For instance, a neural network classifier showed 12% improvement in area under the receiver operator characteristics curve (AUC) and 19% in overall classification accuracy. These improvements were statistically significant for four of the tested classifiers, as per McNemar's tests. This study shows that 3D textural features extracted from conventional T1‐ and T2‐weighted images can improve the diagnostic classification of childhood brain tumours. Long‐term benefits of accurate, yet non‐invasive, diagnostic aids include a reduction in surgical procedures, improvement in surgical and therapy planning, and support of discussions with patients' families. It remains necessary, however, to extend the analysis to a multicentre cohort in order to assess the scalability of the techniques used.

KW - 3D texture analysis

KW - T1- and T2-weighted MRI

KW - paediatric brain tumours

KW - classification

KW - machine learning

U2 - 10.1002/nbm.3353

DO - 10.1002/nbm.3353

M3 - Article

VL - 28

SP - 1174

EP - 1184

JO - NMR in biomedicine

JF - NMR in biomedicine

SN - 0952-3480

IS - 9

ER -