Relevance of Machine Learning to Cardiovascular Imaging

Relevance of Machine Learning to Cardiovascular Imaging

Sumesh Sasidharan, M. Yousuf Salmasi, Selene Pirola, Omar A. Jarral
Copyright: © 2021 |Pages: 22
DOI: 10.4018/978-1-7998-5071-7.ch003
(Individual Chapters)
No Current Special Offers


Artificial intelligence (AI) broadly concerns analytical algorithms that iteratively learn from big datasets, allowing computers to find concealed insights. These encompass a range of operations comprising several terms, including machine learning(ML), cognitive learning, deep learning, and reinforcement learning-based methods that can be used to incorporate and comprehend complex biomedical and healthcare data in scenarios where traditional statistical approaches cannot be implemented. For cardiovascular imaging in particular, machine learning guarantees to be a transformative tool that can address many unmet needs for patient-specific management, accurate prediction of disease progression, and the tracking of identifiable biomarkers of disease processes. In this chapter, the authors discuss fundamentals of machine learning algorithms for image analysis in the cardiovascular system by evaluating the need for ML in this field and examining the potential obstacles and challenges of implementation in the context of three common imaging modalities used in cardiovascular medicine.
Chapter Preview

Evolution Of Machine Learning In Clinical Imaging

Because of the large number of cardiac images that are routinely acquired with a wide range of modalities (Levin, 2019), there has been a surge in research applying deep learning in the cardiac domain (Figure 1). In this chapter, the authors aim to present an introduction to the basic concepts of deep learning and their possibilities, and offer a review of the state-of-the-art of machine learning reported in works on cardiovascular image analysis.

Before the advent of deep learning, a wealth of techniques had been developed to extract clinically relevant information from cardiovascular images. Machine learning algorithms currently in use normally require significant manual adjustment to convert an input image into the desired output (Polonsky, 2010). Although many conventional techniques showed promising results in challenging settings, they were often not robust yet for a routine clinical environment. Many have now been replaced, either in performance or in efficiency, by deep learning-based methods.

Complete Chapter List

Search this Book: