Medical device, machine learning, deep learning, MRI
Abstract
Magnetic resonance imaging (MRI) has been widely used in clinical diagnosis since its introduction with its high resolution and unparalleled contrast imaging of soft tissues. The traditional MRI image analysis is highly dependent on subjective judgment and has the risk of misdiagnosis. The efficiency of human relied diagnosis is still needs to be improved. In recent years, artificial intelligence technology has developed rapidly and gradually involved in MRI image analysis. For example, the image segmentation algorithm, machine learning and deep learning are increasingly widely used in MRI image processing. This paper explores the use of traditional machine learning and deep learning models in MRI and focuses on their ability to extract advanced features, and performance of lesion detection and tumour classification. The advantages and disadvantages of traditional machine learning models such as support vector machines (SVM) and random forests (RF) and their applications are discussed. The deep learning models, particularly convolutional neural networks and generative adversarial networks, this paper focus on their principles and applications to assist MRI diagnosis.
