Cargando…
MRI features predict p53 status in lower-grade gliomas via a machine-learning approach
BACKGROUND: P53 mutation status is a pivotal biomarker for gliomas. Here, we developed a machine-learning model to predict p53 status in lower-grade gliomas based on radiomic features extracted from conventional magnetic resonance (MR) images. METHODS: Preoperative MR images were retrospectively obt...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5842645/ https://www.ncbi.nlm.nih.gov/pubmed/29527478 http://dx.doi.org/10.1016/j.nicl.2017.10.030 |
_version_ | 1783304942482620416 |
---|---|
author | Li, Yiming Qian, Zenghui Xu, Kaibin Wang, Kai Fan, Xing Li, Shaowu Jiang, Tao Liu, Xing Wang, Yinyan |
author_facet | Li, Yiming Qian, Zenghui Xu, Kaibin Wang, Kai Fan, Xing Li, Shaowu Jiang, Tao Liu, Xing Wang, Yinyan |
author_sort | Li, Yiming |
collection | PubMed |
description | BACKGROUND: P53 mutation status is a pivotal biomarker for gliomas. Here, we developed a machine-learning model to predict p53 status in lower-grade gliomas based on radiomic features extracted from conventional magnetic resonance (MR) images. METHODS: Preoperative MR images were retrospectively obtained from 272 patients with primary grade II/III gliomas. The patients were randomly allocated in a 2:1 ratio to a training (n = 180) or validation (n = 92) set. A total of 431 radiomic features were extracted from each patient. The lest absolute shrinkage and selection operator (LASSO) method was used for feature selection and radiomic signature construction. Subsequently, a machine-learning model to predict p53 status was established using the selected features and a Support Vector Machine classifier. The predictive performance of all individual features and the model was calculated using receiver operating characteristic curves in both the training and validation sets. RESULTS: The p53-related radiomic signature was built using the LASSO algorithm; this procedure consisted of four first-order statistics or related wavelet features (including Maximum, Median, Minimum, and Uniformity), a shape and size-based feature (Spherical Disproportion), and ten textural features or related wavelet features (including Correlation, Run Percentage, and Sum Entropy). The prediction accuracies based on the area under the curve were 89.6% in the training set and 76.3% in the validation set, which were better than individual features. CONCLUSIONS: These results demonstrate that MR image texture features are predictive of p53 mutation status in lower-grade gliomas. Thus, our procedure can be conveniently used to facilitate presurgical molecular pathological diagnosis. |
format | Online Article Text |
id | pubmed-5842645 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-58426452018-03-09 MRI features predict p53 status in lower-grade gliomas via a machine-learning approach Li, Yiming Qian, Zenghui Xu, Kaibin Wang, Kai Fan, Xing Li, Shaowu Jiang, Tao Liu, Xing Wang, Yinyan Neuroimage Clin Regular Article BACKGROUND: P53 mutation status is a pivotal biomarker for gliomas. Here, we developed a machine-learning model to predict p53 status in lower-grade gliomas based on radiomic features extracted from conventional magnetic resonance (MR) images. METHODS: Preoperative MR images were retrospectively obtained from 272 patients with primary grade II/III gliomas. The patients were randomly allocated in a 2:1 ratio to a training (n = 180) or validation (n = 92) set. A total of 431 radiomic features were extracted from each patient. The lest absolute shrinkage and selection operator (LASSO) method was used for feature selection and radiomic signature construction. Subsequently, a machine-learning model to predict p53 status was established using the selected features and a Support Vector Machine classifier. The predictive performance of all individual features and the model was calculated using receiver operating characteristic curves in both the training and validation sets. RESULTS: The p53-related radiomic signature was built using the LASSO algorithm; this procedure consisted of four first-order statistics or related wavelet features (including Maximum, Median, Minimum, and Uniformity), a shape and size-based feature (Spherical Disproportion), and ten textural features or related wavelet features (including Correlation, Run Percentage, and Sum Entropy). The prediction accuracies based on the area under the curve were 89.6% in the training set and 76.3% in the validation set, which were better than individual features. CONCLUSIONS: These results demonstrate that MR image texture features are predictive of p53 mutation status in lower-grade gliomas. Thus, our procedure can be conveniently used to facilitate presurgical molecular pathological diagnosis. Elsevier 2017-10-29 /pmc/articles/PMC5842645/ /pubmed/29527478 http://dx.doi.org/10.1016/j.nicl.2017.10.030 Text en © 2017 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Regular Article Li, Yiming Qian, Zenghui Xu, Kaibin Wang, Kai Fan, Xing Li, Shaowu Jiang, Tao Liu, Xing Wang, Yinyan MRI features predict p53 status in lower-grade gliomas via a machine-learning approach |
title | MRI features predict p53 status in lower-grade gliomas via a machine-learning approach |
title_full | MRI features predict p53 status in lower-grade gliomas via a machine-learning approach |
title_fullStr | MRI features predict p53 status in lower-grade gliomas via a machine-learning approach |
title_full_unstemmed | MRI features predict p53 status in lower-grade gliomas via a machine-learning approach |
title_short | MRI features predict p53 status in lower-grade gliomas via a machine-learning approach |
title_sort | mri features predict p53 status in lower-grade gliomas via a machine-learning approach |
topic | Regular Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5842645/ https://www.ncbi.nlm.nih.gov/pubmed/29527478 http://dx.doi.org/10.1016/j.nicl.2017.10.030 |
work_keys_str_mv | AT liyiming mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT qianzenghui mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT xukaibin mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT wangkai mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT fanxing mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT lishaowu mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT jiangtao mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT liuxing mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach AT wangyinyan mrifeaturespredictp53statusinlowergradegliomasviaamachinelearningapproach |