Artificial Intelligence and Texture Analysis in Cardiac Imaging
- PDF / 592,801 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 42 Downloads / 177 Views
CARDIAC PET, CT, AND MRI (P SCHOENHAGEN AND P-H CHEN, SECTION EDITORS)
Artificial Intelligence and Texture Analysis in Cardiac Imaging Manoj Mannil 1,2
&
Matthias Eberhard 1 & Jochen von Spiczak 1 & Walter Heindel 2 & Hatem Alkadhi 1 & Bettina Baessler 1
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Purpose of Review The aim of this structured review is to summarize the current research applications and opportunities arising from artificial intelligence (AI) and texture analysis with regard to cardiac imaging. Recent Findings Current research findings suggest tremendous potential for AI in cardiac imaging, especially with regard to objective image analyses, overcoming the limitations of an observer-dependent subjective image interpretation. Researchers have used this technique across multiple imaging modalities, for instance to detect myocardial scars in cardiac MR imaging, to predict contrast enhancement in non-contrast studies, and to improve image acquisition and reconstruction. Summary AI in medical imaging has the potential to provide novel, much-needed applications for improving patient care pertaining to the cardiovascular system. While several shortcomings are still present in the current methodology, AI may serve as a resourceful assistant to radiologists and clinicians alike. Keywords Artificial intelligence . Radiomics . Texture analysis . Cardiac imaging . CT . MRI
Introduction Artificial Intelligence in Medical Imaging Artificial intelligence (AI) refers to a general field of computer science dedicated to the creation of systems performing tasks that usually require human intelligence such as visual perception or decision-making.1 AI is a general term encompassing different technologies. Machine learning (ML), for instance, describes a subset of AI that includes approaches to learn from data without computers
being explicitly programmed. ML incorporates artificial neural networks (ANN), which are computational models/ algorithms that imitate the architecture of biological neural networks [1]. ANN architecture is structured in layers composed of interconnected nodes. Each node of the network performs a weighted sum of the input data, which is subsequently passed on to an activation function. Weights are dynamically optimized during the training phase. There are input and output layers, which receive data and produce the results of data processing, and there are hidden layers, which extract patterns within the data [2].
1
https://www.oxfordreference.com/view/10.1093/oi/authority. 20110803095426960
This article is part of the Topical Collection on Cardiac PET, CT, and MRI * Manoj Mannil [email protected]
Hatem Alkadhi [email protected]
Matthias Eberhard [email protected]
Bettina Baessler [email protected]
Jochen von Spiczak [email protected] Walter Heindel [email protected]
1
Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
2
University Cli
Data Loading...
