Abstract
Alzheimer’s disease is one of the major challenges of population ageing, and diagnosis and prediction of the disease through various biomarkers is the key. While the application of deep learning as imaging technologies has recently expanded across the medical industry, empirical design of these technologies is very difficult. The main reason for this problem is that the performance of the Convolutional Neural Networks (CNN) differ greatly depending on the statistical distribution of the input dataset. Different hyperparameters also greatly affect the convergence of the CNN models. With this amount of information, selecting appropriate parameters for the network structure has became a large research area. Genetic Algorithm (GA), is a very popular technique to automatically select a high-performance network architecture. In this paper, we show the possibility of optimising the network architecture using GA, where its search space includes both network structure configuration and hyperparameters. To verify the performance of our Algorithm, we used an amyloid brain image dataset that is used for Alzheimer’s disease diagnosis. As a result, our algorithm outperforms Genetic CNN by 11.73% on a given classification task.
Highlights
Alzheimer’s disease (AD) is the most common cause of dementia, and is one of the major problems of global population ageing
We show that our version of genetic algorithm is capable of finding the best-performing Convolutional Neural Networks (CNN) architecture, including activation function and optimisation algorithm, which is specific for the given input dataset
Using the relevant equation from Genetic-CNN, we can calculate the number of bits that is required to encode the network
Summary
Alzheimer’s disease (AD) is the most common cause of dementia, and is one of the major problems of global population ageing. With advances in relevant technologies, there is ongoing research into the diagnosis and treatment of dementia. As well as the tau (τ) protein, is considered as one of the main causes of AD because this protein is found in brains of the majority of patients with AD. Standard Uptake Value Ratio (SUVR) [2], is a classical, quantitative analysis method, to analyse Positron Emission Tomography-Computed Tomography (PET/CT). This method calculates the ratio of two mean activity concentrations of Region of Interest (RoI) or Volume of Interest (VoI), and the reference region. Generalising the threshold for the diagnosis is impossible due to the noise and inconsistency of devices
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.