Artificial Intelligence/Machine Learning in Nuclear Medicine

초록

Artificial intelligence (AI) including machine learning and deep learning methods has become one of the core technology among the most recent developments in the field of medical imaging. Traditional, quantitative image analysis has been indispensable to investigate clinical significance of nuclear medicine molecular imaging in patients with various neurodegenerative diseases. Of the AI techniques, deep learning is consisted of the artificial neural networks with multiple convolutional layers and nodes. Unlike machine learning, deep learning performs the feature extraction and learning based on a cascade of multiple layers of nonlinear processing units. High-quality data and labels are most important to improve the performance of deep learning models. In this chapter, we will focus on various methods of deep learning which has been applied to positron emission tomography/computed tomography (PET/CT) imaging of neurodegenerative diseases. This will include the classification of disease, segmentation of region-of-interest, image generation, image processing, and low-dose imaging. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

키워드