CURRENT CONVOLUTIONAL NEURAL NETWORK ARCHITECTURES FOR DIAGNOSING MEDICAL IMAGES

Abstract

This work shows the current architectures of convolutional neural networks for diagnosing medical images in the lungs and brain, the algorithms are implemented in the Python programming language using the libraries for working with neural networks. It presents the results of comparing time and resources needed for model training which demonstrate a higher accuracy of
early diagnosis achieved by using the current architectures of convolutional neural networks.