论文标题
Biceph-Net：使用2D-MRI扫描和深层相似性学习的强大而轻的框架，用于诊断阿尔茨海默氏病
Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning
论文作者
论文摘要
阿尔茨海默氏病（AD）是一种神经退行性疾病，是老年人群死亡的重要原因之一。已经提出了许多深度学习技术，用于使用磁共振成像（MRI）扫描来诊断AD。使用从3D MRI扫描中提取的2D切片预测AD是有挑战性的，因为丢失了切片间信息。为此，我们提出了一个新颖且轻巧的框架，该框架使用2D MRI扫描进行了对AD诊断的“ Biceph-Net”，该扫描既可以模拟s板内和衬板间信息。 Biceph-NET已被实验证明可以执行类似于其他时空神经网络，同时在计算上更有效。与使用2D MRI切片的Vanilla 2D卷积神经网络（CNN）相比，二心网络的性能也优越。 Biceph-Net还具有基于邻域的模型解释功能，可以利用该功能来了解网络做出的分类决策。 Biceph-NET在实验上实现了认知正常（CN）vs AD的分类100％的测试准确性，轻度认知障碍（MCI）vs AD的测试精度为98.16％，CN与MCI与AD的测试精度为97.80％。
Alzheimer's Disease (AD) is a neurodegenerative disease that is one of the significant causes of death in the elderly population. Many deep learning techniques have been proposed to diagnose AD using Magnetic Resonance Imaging (MRI) scans. Predicting AD using 2D slices extracted from 3D MRI scans is challenging as the inter-slice information gets lost. To this end, we propose a novel and lightweight framework termed 'Biceph-Net' for AD diagnosis using 2D MRI scans that model both the intra-slice and inter-slice information. Biceph-Net has been experimentally shown to perform similar to other Spatio-temporal neural networks while being computationally more efficient. Biceph-Net is also superior in performance compared to vanilla 2D convolutional neural networks (CNN) for AD diagnosis using 2D MRI slices. Biceph-Net also has an inbuilt neighbourhood-based model interpretation feature that can be exploited to understand the classification decision taken by the network. Biceph-Net experimentally achieves a test accuracy of 100% in the classification of Cognitively Normal (CN) vs AD, 98.16% for Mild Cognitive Impairment (MCI) vs AD, and 97.80% for CN vs MCI vs AD.
