Automated Quality Assessment of Structural Magnetic Resonance Brain Images Based on a Supervised Machine Learning Algorithm.
Automated Quality Assessment of Structural Magnetic Resonance Brain Images Based on a Supervised Machine Learning Algorithm.
复制标题
DOI：
10.3389/fninf.2016.00052
复制
发表时间：
2016
影响因子：
3.5
通讯作者：
Mattay VS
中科院分区：
文献类型：
--
作者：
Pizarro RA;Cheng X;Barnett A;Lemaitre H;Verchinski BA;Goldman AL;Xiao E;Luo Q;Berman KF;Callicott JH;Weinberger DR;Mattay VS
高分辨率三维磁共振成像（3D-MRI）越来越多地用于描述神经精神疾病的形态学变化。不幸的是，由于I型和II型错误，伪影经常损害3D-MRI的效用，产生不可复制的结果。因此，在使用之前筛选3d - mri的伪影是至关重要的。目前，质量评估涉及对3D-MRI体积的切片视觉检查，这是一个既主观又耗时的过程。3D-MRI质量评定的自动化可以提高手术的效率和可重复性。本研究是首次将支持向量机（SVM）算法应用于结构脑图像的质量评估，使用内部开发的全局和感兴趣区域（ROI）自动图像质量特征。支持向量机是一种有监督的机器学习算法，它可以根据从学习数据集中获得的知识来预测测试数据集的类别。通过比较SVM预测的质量标签和研究者确定的质量标签，评估了自动支持向量机方法的性能（准确性）。使用SVM方法从我们的数据库中对1457个3D-MRI体积进行分类的准确率约为80%。这些结果是有希望的，并说明了使用支持向量机作为3D-MRI自动质量评估工具的可能性。
High-resolution three-dimensional magnetic resonance imaging (3D-MRI) is being increasingly used to delineate morphological changes underlying neuropsychiatric disorders. Unfortunately, artifacts frequently compromise the utility of 3D-MRI yielding irreproducible results, from both type I and type II errors. It is therefore critical to screen 3D-MRIs for artifacts before use. Currently, quality assessment involves slice-wise visual inspection of 3D-MRI volumes, a procedure that is both subjective and time consuming. Automating the quality rating of 3D-MRI could improve the efficiency and reproducibility of the procedure. The present study is one of the first efforts to apply a support vector machine (SVM) algorithm in the quality assessment of structural brain images, using global and region of interest (ROI) automated image quality features developed in-house. SVM is a supervised machine-learning algorithm that can predict the category of test datasets based on the knowledge acquired from a learning dataset. The performance (accuracy) of the automated SVM approach was assessed, by comparing the SVM-predicted quality labels to investigator-determined quality labels. The accuracy for classifying 1457 3D-MRI volumes from our database using the SVM approach is around 80%. These results are promising and illustrate the possibility of using SVM as an automated quality assessment tool for 3D-MRI.
登录
查看更多内容
影响因子：
4.8
作者：
GARDNER, EA;ELLIS, JH;CARSON, PL
通讯作者：
CARSON, PL
影响因子：
5.7
作者：
Jubault, Thomas;Gagnon, Jean-Francois;Monchi, Oury
通讯作者：
Monchi, Oury
影响因子：
5.7
作者：
Fischl, Bruce
通讯作者：
Fischl, Bruce
影响因子：
4.8
作者：
Burges, CJC
通讯作者：
Burges, CJC
影响因子：
--
作者：
Goldman, Aaron L.;Pezawas, Lukas;Doz, Priv;Mattay, Venkata S.;Fischl, Bruce;Verchinski, Beth A.;Chen, Qiang;Weinberger, Daniel R.;Meyer-Lindenberg, Andreas
通讯作者：
Meyer-Lindenberg, Andreas