Classification of CT brain images based on deep learning networks

Gao, Xiaohong W. ORCID:, Hui, Rui and Tian, Zengmin (2017) Classification of CT brain images based on deep learning networks. Computer Methods and Programs in Biomedicine, 138 (2017) . pp. 49-56. ISSN 0169-2607 [Article] (doi:10.1016/j.cmpb.2016.10.007)

PDF - Final accepted version (with author's formatting)
Available under License Creative Commons Attribution-NonCommercial-NoDerivatives 4.0.

Download (1MB) | Preview


While Computerised Tomography (CT) may have been the first imag-ing tool to study human brain, it has not yet been implemented into clinical decision making process for diagnosis of Alzheimers 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 ex-tent. 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 di-agnosis of Alzheimers 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 character-istics of this collection with larger thickness along the direction of depth (z) (∼3-5mm), 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 ac-curacy 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, 2DKAZE, 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

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 20744
Notes on copyright: © 2016 This manuscript version is made available under the CC-BY-NC-ND 4.0 license
Useful Links:
Depositing User: Xiaohong Gao
Date Deposited: 17 Oct 2016 11:11
Last Modified: 09 Jun 2021 19:22

Actions (login required)

View Item View Item


Activity Overview

Additional statistics are available via IRStats2.