Martinez-Murcia F J, Górriz J M, Ramírez J, Moreno-Caballero M, Gómez-Río M
Signal Processing and Biomedical Applications Research Group, Department of Signal Theory, Networking and Communications, University of Granada, Granada 18071, Spain.
Department of Nuclear Medicine, Virgen de las Nieves Hospital, Granada 18071, Spain.
Med Phys. 2014 Jan;41(1):012502. doi: 10.1118/1.4845115.
A novel approach to a computer aided diagnosis system for the Parkinson's disease is proposed. This tool is intended as a supporting tool for physicians, based on fully automated methods that lead to the classification of (123)I-ioflupane SPECT images.
(123)I-ioflupane images from three different databases are used to train the system. The images are intensity and spatially normalized, then subimages are extracted and a 3D gray-level co-occurrence matrix is computed over these subimages, allowing the characterization of the texture using Haralick texture features. Finally, different discrimination estimation methods are used to select a feature vector that can be used to train and test the classifier.
Using the leave-one-out cross-validation technique over these three databases, the system achieves results up to a 97.4% of accuracy, and 99.1% of sensitivity, with positive likelihood ratios over 27.
The system presents a robust feature extraction method that helps physicians in the diagnosis task by providing objective, operator-independent textural information about (123)I-ioflupane images, commonly used in the diagnosis of the Parkinson's disease. Textural features computation has been optimized by using a subimage selection algorithm, and the discrimination estimation methods used here makes the system feature-independent, allowing us to extend it to other databases and diseases.
提出一种用于帕金森病计算机辅助诊断系统的新方法。该工具旨在作为医生的辅助工具，基于全自动方法对（123）I-碘氟烷单光子发射计算机断层扫描（SPECT）图像进行分类。
使用来自三个不同数据库的（123）I-碘氟烷图像训练该系统。对图像进行强度和空间归一化，然后提取子图像，并在这些子图像上计算三维灰度共生矩阵，从而使用哈拉里克纹理特征对纹理进行表征。最后，使用不同的判别估计方法选择可用于训练和测试分类器的特征向量。
在这三个数据库上使用留一法交叉交叉交叉交叉验证技术，该系统的准确率高达97.4%，灵敏度为99.1%，阳性似然比超过27。
该系统提出了一种强大的特征提取方法，通过提供关于（123）I-碘氟烷图像的客观、与操作员无关的纹理信息，帮助医生完成诊断任务，这种图像常用于帕金森病的诊断。通过使用子图像选择算法优化了纹理特征计算，这里使用的判别估计方法使系统与特征无关，从而使我们能够将其扩展到其他数据库和疾病。
