Cargando…
Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children
Brain tumours are the most common solid tumours in children, representing 20% of all cancers. The most frequent posterior fossa tumours are medulloblastomas, pilocytic astrocytomas and ependymomas. Texture analysis (TA) of MR images can be used to support the diagnosis of these tumours by providing...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Blackwell Publishing Ltd
2014
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4529665/ https://www.ncbi.nlm.nih.gov/pubmed/24729528 http://dx.doi.org/10.1002/nbm.3099 |
_version_ | 1782384813580222464 |
---|---|
author | Orphanidou-Vlachou, Eleni Vlachos, Nikolaos Davies, Nigel P Arvanitis, Theodoros N Grundy, Richard G Peet, Andrew C |
author_facet | Orphanidou-Vlachou, Eleni Vlachos, Nikolaos Davies, Nigel P Arvanitis, Theodoros N Grundy, Richard G Peet, Andrew C |
author_sort | Orphanidou-Vlachou, Eleni |
collection | PubMed |
description | Brain tumours are the most common solid tumours in children, representing 20% of all cancers. The most frequent posterior fossa tumours are medulloblastomas, pilocytic astrocytomas and ependymomas. Texture analysis (TA) of MR images can be used to support the diagnosis of these tumours by providing additional quantitative information. MaZda software was used to perform TA on T(1)- and T(2)-weighted images of children with pilocytic astrocytomas, medulloblastomas and ependymomas of the posterior fossa, who had MRI at Birmingham Children's Hospital prior to treatment. The region of interest was selected on three slices per patient in Image J, using thresholding and manual outlining. TA produced 279 features, which were reduced using principal component analysis (PCA). The principal components (PCs) explaining 95% of the variance were used in a linear discriminant analysis (LDA) and a probabilistic neural network (PNN) to classify the cases, using DTREG statistics software. PCA of texture features from both T(1)- and T(2)-weighted images yielded 13 PCs to explain >95% of the variance. The PNN classifier for T(1)-weighted images achieved 100% accuracy on training the data and 90% on leave-one-out cross-validation (LOOCV); for T(2)-weighted images, the accuracy was 100% on training the data and 93.3% on LOOCV. A PNN classifier with T(1) and T(2) PCs achieved 100% accuracy on training the data and 85.8% on LOOCV. LDA classification accuracies were noticeably poorer. The features found to hold the highest discriminating potential were all co-occurrence matrix derived, where adjacent pixels had highly correlated intensities. This study shows that TA can be performed on standard T(1)- and T(2)-weighted images of childhood posterior fossa tumours using readily available software to provide high diagnostic accuracy. Discriminatory features do not correspond to those used in the clinical interpretation of the images and therefore provide novel tumour information. Copyright © 2014 John Wiley & Sons, Ltd. |
format | Online Article Text |
id | pubmed-4529665 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2014 |
publisher | Blackwell Publishing Ltd |
record_format | MEDLINE/PubMed |
spelling | pubmed-45296652015-08-13 Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children Orphanidou-Vlachou, Eleni Vlachos, Nikolaos Davies, Nigel P Arvanitis, Theodoros N Grundy, Richard G Peet, Andrew C NMR Biomed Research Articles Brain tumours are the most common solid tumours in children, representing 20% of all cancers. The most frequent posterior fossa tumours are medulloblastomas, pilocytic astrocytomas and ependymomas. Texture analysis (TA) of MR images can be used to support the diagnosis of these tumours by providing additional quantitative information. MaZda software was used to perform TA on T(1)- and T(2)-weighted images of children with pilocytic astrocytomas, medulloblastomas and ependymomas of the posterior fossa, who had MRI at Birmingham Children's Hospital prior to treatment. The region of interest was selected on three slices per patient in Image J, using thresholding and manual outlining. TA produced 279 features, which were reduced using principal component analysis (PCA). The principal components (PCs) explaining 95% of the variance were used in a linear discriminant analysis (LDA) and a probabilistic neural network (PNN) to classify the cases, using DTREG statistics software. PCA of texture features from both T(1)- and T(2)-weighted images yielded 13 PCs to explain >95% of the variance. The PNN classifier for T(1)-weighted images achieved 100% accuracy on training the data and 90% on leave-one-out cross-validation (LOOCV); for T(2)-weighted images, the accuracy was 100% on training the data and 93.3% on LOOCV. A PNN classifier with T(1) and T(2) PCs achieved 100% accuracy on training the data and 85.8% on LOOCV. LDA classification accuracies were noticeably poorer. The features found to hold the highest discriminating potential were all co-occurrence matrix derived, where adjacent pixels had highly correlated intensities. This study shows that TA can be performed on standard T(1)- and T(2)-weighted images of childhood posterior fossa tumours using readily available software to provide high diagnostic accuracy. Discriminatory features do not correspond to those used in the clinical interpretation of the images and therefore provide novel tumour information. Copyright © 2014 John Wiley & Sons, Ltd. Blackwell Publishing Ltd 2014-06 2014-04-13 /pmc/articles/PMC4529665/ /pubmed/24729528 http://dx.doi.org/10.1002/nbm.3099 Text en © 2014 The Authors. NMR in Biomedicine published by John Wiley & Sons Ltd. http://creativecommons.org/licenses/by/4.0/ This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Articles Orphanidou-Vlachou, Eleni Vlachos, Nikolaos Davies, Nigel P Arvanitis, Theodoros N Grundy, Richard G Peet, Andrew C Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children |
title | Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children |
title_full | Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children |
title_fullStr | Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children |
title_full_unstemmed | Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children |
title_short | Texture analysis of T(1)- and T(2)-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children |
title_sort | texture analysis of t(1)- and t(2)-weighted mr images and use of probabilistic neural network to discriminate posterior fossa tumours in children |
topic | Research Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4529665/ https://www.ncbi.nlm.nih.gov/pubmed/24729528 http://dx.doi.org/10.1002/nbm.3099 |
work_keys_str_mv | AT orphanidouvlachoueleni textureanalysisoft1andt2weightedmrimagesanduseofprobabilisticneuralnetworktodiscriminateposteriorfossatumoursinchildren AT vlachosnikolaos textureanalysisoft1andt2weightedmrimagesanduseofprobabilisticneuralnetworktodiscriminateposteriorfossatumoursinchildren AT daviesnigelp textureanalysisoft1andt2weightedmrimagesanduseofprobabilisticneuralnetworktodiscriminateposteriorfossatumoursinchildren AT arvanitistheodorosn textureanalysisoft1andt2weightedmrimagesanduseofprobabilisticneuralnetworktodiscriminateposteriorfossatumoursinchildren AT grundyrichardg textureanalysisoft1andt2weightedmrimagesanduseofprobabilisticneuralnetworktodiscriminateposteriorfossatumoursinchildren AT peetandrewc textureanalysisoft1andt2weightedmrimagesanduseofprobabilisticneuralnetworktodiscriminateposteriorfossatumoursinchildren |