Qiu Shangran, Chang Gary H, Panagia Marcello, Gopal Deepa M, Au Rhoda, Kolachalama Vijaya B
Department of Physics, College of Arts and Sciences, Boston University, Boston, MA, USA.
Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA, USA.
Alzheimers Dement (Amst). 2018 Sep 28;10:737-749. doi: 10.1016/j.dadm.2018.08.013. eCollection 2018.
Our aim was to investigate if the accuracy of diagnosing mild cognitive impairment (MCI) using the Mini-Mental State Examination (MMSE) and logical memory (LM) test could be enhanced by adding MRI data.
Data of individuals with normal cognition and MCI were obtained from the National Alzheimer Coordinating Center database (n = 386). Deep learning models trained on MRI slices were combined to generate a fused MRI model using different voting techniques to predict normal cognition versus MCI. Two multilayer perceptron (MLP) models were developed with MMSE and LM test results. Finally, the fused MRI model and the MLP models were combined using majority voting.
The fusion model was superior to the individual models alone and achieved an overall accuracy of 90.9%.
This study is a proof of principle that multimodal fusion of models developed using MRI scans, MMSE, and LM test data is feasible and can better predict MCI.
我们的目的是研究通过添加MRI数据是否可以提高使用简易精神状态检查表（MMSE）和逻辑记忆（LM）测试诊断轻度认知障碍（MCI）的准确性。
从国家阿尔茨海默病协调中心数据库中获取认知正常和MCI个体的数据（n = 386）。在MRI切片上训练的深度学习模型被组合起来，使用不同的投票技术生成一个融合MRI模型，以预测正常认知与MCI。利用MMSE和LM测试结果开发了两个多层感知器（MLP）模型。最后，使用多数投票法将融合MRI模型和MLP模型进行组合。
融合模型优于单独的个体模型，总体准确率达到90.9%。
本研究证明了一个原理，即使用MRI扫描、MMSE和LM测试数据开发的模型进行多模态融合是可行的，并且可以更好地预测MCI。
