Dpto., TSyCeIT, ETSIT, Universidad de Valladolid, Paseo de Belén 15, Valladolid, 47011, Spain.
Laboratory for Cognitive and Computational Neuroscience, Center for Biomedical Technology, Campus Montegancedo, Pozuelo de Alarcón, Madrid, 28223, Spain; Experimental Psychology, Department of the Complutense, University of Madrid, Spain.
Artif Intell Med. 2020 Jul;107:101924. doi: 10.1016/j.artmed.2020.101924. Epub 2020 Jul 2.
The early detection of Alzheimer's disease can potentially make eventual treatments more effective. This work presents a deep learning model to detect early symptoms of Alzheimer's disease using synchronization measures obtained with magnetoencephalography. The proposed model is a novel deep learning architecture based on an ensemble of randomized blocks formed by a sequence of 2D-convolutional, batch-normalization and pooling layers. An important challenge is to avoid overfitting, as the number of features is very high (25755) compared to the number of samples (132 patients). To address this issue the model uses an ensemble of identical sub-models all sharing weights, with a final stage that performs an average across sub-models. To facilitate the exploration of the feature space, each sub-model receives a random permutation of features. The features correspond to magnetic signals reflecting neural activity and are arranged in a matrix structure interpreted as a 2D image that is processed by 2D convolutional networks. The proposed detection model is a binary classifier (disease/non-disease), which compared to other deep learning architectures and classic machine learning classifiers, such as random forest and support vector machine, obtains the best classification performance results with an average F1-score of 0.92. To perform the comparison a strict validation procedure is proposed, and a thorough study of results is provided.
阿尔茨海默病的早期检测可能会使最终的治疗更加有效。这项工作提出了一种使用脑磁图获得的同步测量来检测阿尔茨海默病早期症状的深度学习模型。所提出的模型是一种新颖的深度学习架构，基于由二维卷积、批量归一化和池化层组成的随机块序列的随机块集合。一个重要的挑战是避免过拟合，因为特征的数量（25755）与样本数量（132 名患者）相比非常高。为了解决这个问题，模型使用共享权重的相同子模型的集合，最后一个阶段对子模型进行平均。为了方便对特征空间的探索，每个子模型都接收特征的随机排列。特征对应于反映神经活动的磁信号，并排列在矩阵结构中，解释为 2D 图像，然后由 2D 卷积网络进行处理。所提出的检测模型是一个二进制分类器（疾病/非疾病），与其他深度学习架构和经典机器学习分类器（如随机森林和支持向量机）相比，该模型的分类性能最好，平均 F1 得分为 0.92。为了进行比较，提出了严格的验证程序，并提供了结果的详细研究。
