Computer-aided classification of multi-types of dementia via convolutional neural networks

With millions of people suffering from dementia worldwide, the global prevalence of dementia has a significant impact on the patients' lives, their caregivers' physical and emotional states, and the global economy. Early diagnosis of dementia helps in finding suitable therapies that reduce or even prevent further deterioration of patients' cognitive abilities. In recent years, state-of-the-art literature has proposed various computer-aided diagnosis systems based on 3-dimensional brain imagery analysis to identify early symptoms of dementia. These systems aim to assist radiologists in increasing the accuracy of diagnoses and reducing false positives. However, the early diagnosis of dementia is a challenging task due to the image quality, noise, and human brain irregularities. The state-of-the-art has focused on differentiating multi-stages of Alzheimer's disease, however, the diagnosis of various types of dementia is still a gap. This paper proposes a deep learning-based computer-aided diagnosis approach for the early detection of multi-type of dementia. To show the performance of the proposed CAD algorithm, three conventional CAD methods are implemented for comparison. The proposed algorithm yields a 74.93% accuracy in early diagnosis of multi-type of dementia and outperforms the state of the art CAD methods.