Ecole Polytechnique de Montreal, University of Montreal, 2900, boul. Edouard-Montpetit, Campus de l'Universite de Montreal, 2500, chemin de Polytechnique, Montreal, Quebec, H3T 1J4, Canada.
Artif Intell Med. 2012 Oct;56(2):99-107. doi: 10.1016/j.artmed.2012.07.002. Epub 2012 Sep 25.
To determine scoliosis curve types using non invasive surface acquisition, without prior knowledge from X-ray data.
Classification of scoliosis deformities according to curve type is used in the clinical management of scoliotic patients. In this work, we propose a robust system that can determine the scoliosis curve type from non invasive acquisition of the 3D back surface of the patients. The 3D image of the surface of the trunk is divided into patches and local geometric descriptors characterizing the back surface are computed from each patch and constitute the features. We reduce the dimensionality by using principal component analysis and retain 53 components using an overlap criterion combined with the total variance in the observed variables. In this work, a multi-class classifier is built with least-squares support vector machines (LS-SVM). The original LS-SVM formulation was modified by weighting the positive and negative samples differently and a new kernel was designed in order to achieve a robust classifier. The proposed system is validated using data from 165 patients with different scoliosis curve types. The results of our non invasive classification were compared with those obtained by an expert using X-ray images.
The average rate of successful classification was computed using a leave-one-out cross-validation procedure. The overall accuracy of the system was 95%. As for the correct classification rates per class, we obtained 96%, 84% and 97% for the thoracic, double major and lumbar/thoracolumbar curve types, respectively.
This study shows that it is possible to find a relationship between the internal deformity and the back surface deformity in scoliosis with machine learning methods. The proposed system uses non invasive surface acquisition, which is safe for the patient as it involves no radiation. Also, the design of a specific kernel improved classification performance.
利用非侵入性表面采集技术，在不依赖 X 射线数据的情况下确定脊柱侧弯曲线类型。
脊柱侧弯畸形的分类根据曲线类型在脊柱侧弯患者的临床管理中使用。在这项工作中，我们提出了一个强大的系统，可以从患者非侵入性采集的 3D 背部表面确定脊柱侧弯曲线类型。躯干表面的 3D 图像被分为斑块，从每个斑块计算出表征背部表面的局部几何描述符，并构成特征。我们使用主成分分析降低维度，并使用重叠标准和观察变量的总方差保留 53 个分量。在这项工作中，使用最小二乘支持向量机（LS-SVM）构建多类分类器。原始 LS-SVM 公式通过对正例和负例进行不同的加权和设计新的核函数进行修改，以实现鲁棒的分类器。该系统使用来自具有不同脊柱侧弯曲线类型的 165 名患者的数据进行验证。我们的非侵入性分类结果与专家使用 X 射线图像获得的结果进行了比较。
使用留一法交叉验证程序计算平均分类成功率。该系统的整体准确率为 95%。至于每类的正确分类率，我们分别获得了胸弯、双主弯和胸腰弯曲线类型的 96%、84%和 97%。
这项研究表明，使用机器学习方法可以在脊柱侧弯中找到内部畸形和背部表面畸形之间的关系。所提出的系统使用非侵入性表面采集，对患者是安全的，因为它不涉及辐射。此外，特定核函数的设计提高了分类性能。
