Ortiz Andrés, Munilla Jorge, Martínez-Ibañez Manuel, Górriz Juan M, Ramírez Javier, Salas-Gonzalez Diego
Department of Communications Engineering, Universidad de Málaga, Malaga, Spain.
Department of Signal Theory, Networking and Communications, University of Granada, Granada, Spain.
Front Neuroinform. 2019 Jul 2;13:48. doi: 10.3389/fninf.2019.00048. eCollection 2019.
Computer aided diagnosis systems based on brain imaging are an important tool to assist in the diagnosis of Parkinson's disease, whose ultimate goal is the detection by automatic recognizing of patterns that characterize the disease. In recent times Convolutional Neural Networks (CNN) have proved to be amazingly useful for that task. The drawback, however, is that 3D brain images contain a huge amount of information that leads to complex CNN architectures. When these architectures become too complex, classification performances often degrades because the limitations of the training algorithm and overfitting. Thus, this paper proposes the use of isosurfaces as a way to reduce such amount of data while keeping the most relevant information. These isosurfaces are then used to implement a classification system which uses two of the most well-known CNN architectures, LeNet and AlexNet, to classify DaTScan images with an average accuracy of 95.1% and AUC = 97%, obtaining comparable (slightly better) values to those obtained for most of the recently proposed systems. It can be concluded therefore that the computation of isosurfaces reduces the complexity of the inputs significantly, resulting in high classification accuracies with reduced computational burden.
基于脑成像的计算机辅助诊断系统是协助诊断帕金森病的重要工具，其最终目标是通过自动识别该疾病的特征模式来进行检测。近年来，卷积神经网络（CNN）已被证明在这项任务中非常有用。然而，缺点是3D脑图像包含大量信息，这导致CNN架构复杂。当这些架构变得过于复杂时，由于训练算法的局限性和过拟合，分类性能往往会下降。因此，本文提出使用等值面作为减少数据量同时保留最相关信息的一种方法。然后，这些等值面被用于实现一个分类系统，该系统使用两种最著名的CNN架构LeNet和AlexNet对DaTScan图像进行分类，平均准确率为95.1%，AUC = 97%，获得了与最近提出的大多数系统相当（略好）的值。因此可以得出结论，等值面的计算显著降低了输入的复杂性，从而在减轻计算负担的情况下实现了高分类准确率。
