Fetit Ahmed E, Novak Jan, Peet Andrew C, Arvanitits Theodoros N
Institute of Digital Healthcare, WMG, University of Warwick, Coventry, UK.
Birmingham Children's Hospital NHS Foundation Trust, Birmingham, UK.
NMR Biomed. 2015 Sep;28(9):1174-84. doi: 10.1002/nbm.3353. Epub 2015 Aug 9.
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.
本研究的目的是以定量方式评估常规磁共振成像（MRI）的三维纹理分析（3D TA）在儿童脑肿瘤分类中的有效性。数据集包括从48名被诊断患有脑肿瘤（髓母细胞瘤、毛细胞型星形细胞瘤和室管膜瘤）的儿童中获取的对比前T1加权和T2加权MRI序列。使用一阶、二阶和高阶统计方法对图像进行3D和2D TA。使用最具影响力的3D和2D纹理特征训练六种监督分类算法，并比较它们在使用这两种特征集对肿瘤类型进行分类时的性能。使用留一法交叉验证（LOOCV）方法以及分层10折交叉验证进行模型验证，以提供更多保证。使用McNemar检验来检验3D训练的分类器所显示的任何改进的统计显著性。与使用传统2D特征训练的模型相比，使用3D纹理特征训练的监督学习模型显示出更好的分类性能。例如，一个神经网络分类器在受试者操作特征曲线下面积（AUC）方面提高了12%，在总体分类准确率方面提高了19%。根据McNemar检验，这些改进对四个测试分类器具有统计学显著性。本研究表明，从传统T1加权和T2加权图像中提取的3D纹理特征可以改善儿童脑肿瘤的诊断分类。准确但非侵入性的诊断辅助工具的长期益处包括减少手术程序、改善手术和治疗计划以及支持与患者家属的讨论。然而，有必要将分析扩展到多中心队列，以评估所使用技术的可扩展性。
