Big Medical Image Analysis: Alzheimer’s Disease Classification Using Convolutional Autoencoder

Abstract

Deep learning-based analysis is a noticeable topic in recent years. The enormous success of deep learning is now combined with big data analytics to provide an open platform to the health care industry for a better diagnosis of any disease. In this paper, we described the convolutional autoencoder technique that reduces the complexity of radiologists through a brief study of Alzheimer's MRI data which led to a rise in data-driven medical research for a better diagnosis. In this research, we have compared the effects of two techniques: convolutional autoencoder (CANN) and independent component analysis (ICA), and discovered that CANN has a higher accuracy of 98.8% and outperforms ICA models in terms of convergence speed.