Department of Instrument Science and Engineering, School of EIEE, Shanghai Jiao Tong University, Shanghai, 200240, China.
Department of Instrument Science and Engineering, School of EIEE, Shanghai Jiao Tong University, Shanghai, 200240, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China; Shanghai Engineering Research Center for Intelligent Diagnosis and Treatment Instrument, Shanghai Jiao Tong University, China.
J Neurosci Methods. 2019 Jul 15;323:108-118. doi: 10.1016/j.jneumeth.2019.05.006. Epub 2019 May 25.
Hippocampus is one of the first structures affected by neurodegenerative diseases such as Alzheimer's disease (AD) and mild cognitive impairment (MCI). Hippocampal atrophy can be evaluated in terms of hippocampal volumes and shapes using structural MR images. However, the shape and volume features from hippocampus mask have limited discriminative information for AD diagnosis. In addition, extraction of these features is independent of classification model, resulting to sub-optimal performance for disease diagnosis.
This paper proposes a hybrid convolutional and recurrent neural network for more detailed hippocampus analysis using structural MR images in AD. The DenseNets are constructed on the decomposed image patches of internal and external hippocampus to learn the intensity and shape features. Recurrent neural network (RNN) is cascaded to combine the features from the left and right hippocampus and learn the high-level features for disease classification.
Our proposed method is evaluated with the baseline MR images of 807 subjects including 194 AD, 397 MCI and 216 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experiments show the proposed method achieves AUC (area under ROC curve) of 91.0%, 75.8% and 74.6% for classifications of AD vs. NC, MCI vs. NC and pMCI vs. sMCI, respectively.
The proposed method achieves better performance than the volume and shape analysis methods.
A hybrid convolutional and recurrent neural network was proposed by combining DenseNets and bidirectional gated recurrent unit (BGRU) for hippocampus analysis and AD diagnosis. Results show its promising performance.
海马体是受神经退行性疾病（如阿尔茨海默病（AD）和轻度认知障碍（MCI））影响的首批结构之一。可以使用结构磁共振成像（MR）图像从体积和形状方面评估海马体萎缩。然而，来自海马体掩模的形状和体积特征对于 AD 诊断的区分信息有限。此外，这些特征的提取独立于分类模型，因此对于疾病诊断的性能不佳。
本文提出了一种混合卷积和递归神经网络，用于使用 AD 中的结构 MR 图像进行更详细的海马体分析。在内部和外部海马体的分解图像块上构建密集网络，以学习强度和形状特征。递归神经网络（RNN）级联以结合左右海马体的特征，并学习用于疾病分类的高级特征。
我们的方法使用来自阿尔茨海默病神经影像学倡议（ADNI）数据库的 807 名受试者的基线 MR 图像进行了评估，其中包括 194 名 AD、397 名 MCI 和 216 名正常对照（NC）。实验表明，该方法在 AD 与 NC、MCI 与 NC 和 pMCI 与 sMCI 的分类中分别达到了 91.0%、75.8%和 74.6%的 AUC（ROC 曲线下面积）。
该方法的性能优于体积和形状分析方法。
通过结合密集网络和双向门控循环单元（BGRU），提出了一种混合卷积和递归神经网络用于海马体分析和 AD 诊断。结果表明其具有良好的性能。
