An overview of neural networks for medical image recognition

¹ Federal State Autonomous Educational Institution of Higher Education «Northern (Arctic) Federal University named after M.V. Lomonosov», Northern Dvina embankment, 17, 163002 Arkhangelsk, Russia
² Belarusian-Russian University, Mira Avenue, 43, 212000 Mogilev, Belarus

^* Corresponding author: vygovskaya-natalya@mail.ru

Abstract

Medical image recognition plays a crucial role in computer diagnostics and has been greatly enhanced by the advancements in deep learning techniques, particularly neural networks. This article provides a comprehensive review of the application of neural networks in medical image recognition, highlighting their advantages and disadvantages. Neural networks, inspired by the functioning of the human brain, consist of interconnected artificial neurons organized in layers. Through the learning process, neural networks can analyze and classify medical images, enabling accurate diagnosis and treatment. The article explores the fundamental components of neural networks, including neurons, weights, and activation functions, and explains the training process using algorithms like backpropagation. It also discusses various types of neural networks commonly used in image recognition tasks, such as Convolutional Neural Networks (CNN) for processing images and Recurrent Neural Networks (RNN) for analyzing sequential data. By examining research examples from different medical fields, this review demonstrates the effectiveness of neural networks in medical image recognition and their potential to revolutionize healthcare by improving diagnostic accuracy and patient outcomes.