Department of Computer Science, Middlesex University, London NW4 4BT, UK.
Neurosurgery Centre, Navy General Hospital, Beijing, China.
Comput Methods Programs Biomed. 2017 Jan;138:49-56. doi: 10.1016/j.cmpb.2016.10.007. Epub 2016 Oct 20.
While computerised tomography (CT) may have been the first imaging tool to study human brain, it has not yet been implemented into clinical decision making process for diagnosis of Alzheimer's disease (AD). On the other hand, with the nature of being prevalent, inexpensive and non-invasive, CT does present diagnostic features of AD to a great extent. This study explores the significance and impact on the application of the burgeoning deep learning techniques to the task of classification of CT brain images, in particular utilising convolutional neural network (CNN), aiming at providing supplementary information for the early diagnosis of Alzheimer's disease. Towards this end, three categories of CT images (N = 285) are clustered into three groups, which are AD, lesion (e.g. tumour) and normal ageing. In addition, considering the characteristics of this collection with larger thickness along the direction of depth (z) (~3-5 mm), an advanced CNN architecture is established integrating both 2D and 3D CNN networks. The fusion of the two CNN networks is subsequently coordinated based on the average of Softmax scores obtained from both networks consolidating 2D images along spatial axial directions and 3D segmented blocks respectively. As a result, the classification accuracy rates rendered by this elaborated CNN architecture are 85.2%, 80% and 95.3% for classes of AD, lesion and normal respectively with an average of 87.6%. Additionally, this improved CNN network appears to outperform the others when in comparison with 2D version only of CNN network as well as a number of state of the art hand-crafted approaches. As a result, these approaches deliver accuracy rates in percentage of 86.3, 85.6 ± 1.10, 86.3 ± 1.04, 85.2 ± 1.60, 83.1 ± 0.35 for 2D CNN, 2D SIFT, 2D KAZE, 3D SIFT and 3D KAZE respectively. The two major contributions of the paper constitute a new 3-D approach while applying deep learning technique to extract signature information rooted in both 2D slices and 3D blocks of CT images and an elaborated hand-crated approach of 3D KAZE.
虽然计算机断层扫描（CT）可能是最早用于研究人脑的成像工具，但它尚未应用于阿尔茨海默病（AD）的诊断决策过程。另一方面，由于 CT 具有普遍性、廉价性和非侵入性，因此在很大程度上具有 AD 的诊断特征。本研究探讨了将新兴的深度学习技术应用于 CT 脑图像分类任务的意义和影响，特别是利用卷积神经网络（CNN），旨在为阿尔茨海默病的早期诊断提供补充信息。为此，将 285 张 CT 图像（N=285）分为三组，分别为 AD、病变（如肿瘤）和正常老化。此外，考虑到该集合在深度方向（z）上的厚度较大（~3-5mm）的特点，建立了一种结合 2D 和 3D CNN 网络的先进 CNN 架构。然后，根据从两个网络分别沿空间轴向整合 2D 图像和 3D 分段块获得的 Softmax 得分的平均值，协调两个 CNN 网络的融合。结果，这种精心设计的 CNN 架构的分类准确率分别为 AD、病变和正常组的 85.2%、80%和 95.3%，平均为 87.6%。此外，与仅 2D 版本的 CNN 网络以及一些最新的手工制作方法相比，这种改进后的 CNN 网络似乎表现更好。因此，这些方法的准确率分别为 86.3%、85.6±1.10%、86.3±1.04%、85.2±1.60%、83.1±0.35%，用于 2D CNN、2D SIFT、2D KAZE、3D SIFT 和 3D KAZE。本文的两个主要贡献构成了一种新的 3D 方法，同时应用深度学习技术从 CT 图像的 2D 切片和 3D 块中提取特征信息，以及一种精心制作的 3D KAZE 方法。
Comput Methods Programs Biomed. 2016-10-20
Int J Neural Syst. 2020-6
Neuroinformatics. 2018-10
Biomed Res Int. 2017
Neural Netw. 2020-3-28
Diagnostics (Basel). 2025-5-15
Health Inf Sci Syst. 2025-5-20
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024-12-25
J Abdom Wall Surg. 2024-9-6
Zotero 插件