Deep Learning Techniques to Classify and Analyze Medical Imaging Data
Dharm Singh Jat, Chucknorris Garikayi Madamombe · Intelligent Systems · 2019
The use of deep learning techniques predominantly the Convolutional Neural Networks (CNNs) has been used in various disciplines in recent years. CNNs have shown an essential ability to automatically extract large volumes of information from big data. The use of CNNs has significantly proved to be useful especially in classifying natural images. Nonetheless, there has been a major barrier in implementing CNNs in the medical domain due to lack of proper available data for training. As a result, generic imaging standards like ImageNet have been widely used in the medical domain. However, these generic imaging benchmarks are not so perfect as compared to the use of CNNs. The main aim of this chapter is review the existing deep learning techniques to classify and analyze medical imaging data. In this chapter, a comparative analysis of LeNet, AlexNet, and GoogLeNet was done. Furthermore, this review looked at the literature on classifying medicinal anatomy images using CNNs. Based on the various studies the CNNs architecture has better performance with the other architectures in classifying medical images.