101
|
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. 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.
Collapse
|
102
|
Hagiwara A, Fujita S, Ohno Y, Aoki S. Variability and Standardization of Quantitative Imaging: Monoparametric to Multiparametric Quantification, Radiomics, and Artificial Intelligence. Invest Radiol 2020; 55:601-616. [PMID: 32209816 PMCID: PMC7413678 DOI: 10.1097/rli.0000000000000666] [Citation(s) in RCA: 73] [Impact Index Per Article: 18.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2020] [Accepted: 01/28/2020] [Indexed: 12/19/2022]
Abstract
Radiological images have been assessed qualitatively in most clinical settings by the expert eyes of radiologists and other clinicians. On the other hand, quantification of radiological images has the potential to detect early disease that may be difficult to detect with human eyes, complement or replace biopsy, and provide clear differentiation of disease stage. Further, objective assessment by quantification is a prerequisite of personalized/precision medicine. This review article aims to summarize and discuss how the variability of quantitative values derived from radiological images are induced by a number of factors and how these variabilities are mitigated and standardization of the quantitative values are achieved. We discuss the variabilities of specific biomarkers derived from magnetic resonance imaging and computed tomography, and focus on diffusion-weighted imaging, relaxometry, lung density evaluation, and computer-aided computed tomography volumetry. We also review the sources of variability and current efforts of standardization of the rapidly evolving techniques, which include radiomics and artificial intelligence.
Collapse
Affiliation(s)
- Akifumi Hagiwara
- From the Department of Radiology, Juntendo University School of Medicine, Tokyo
| | | | - Yoshiharu Ohno
- Department of Radiology, Fujita Health University School of Medicine, Toyoake, Aichi, Japan
| | - Shigeki Aoki
- From the Department of Radiology, Juntendo University School of Medicine, Tokyo
| |
Collapse
|
103
|
Beer JC, Tustison NJ, Cook PA, Davatzikos C, Sheline YI, Shinohara RT, Linn KA. Longitudinal ComBat: A method for harmonizing longitudinal multi-scanner imaging data. Neuroimage 2020; 220:117129. [PMID: 32640273 PMCID: PMC7605103 DOI: 10.1016/j.neuroimage.2020.117129] [Citation(s) in RCA: 103] [Impact Index Per Article: 25.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2020] [Revised: 06/24/2020] [Accepted: 06/29/2020] [Indexed: 12/19/2022] Open
Abstract
While aggregation of neuroimaging datasets from multiple sites and scanners can yield increased statistical power, it also presents challenges due to systematic scanner effects. This unwanted technical variability can introduce noise and bias into estimation of biological variability of interest. We propose a method for harmonizing longitudinal multi-scanner imaging data based on ComBat, a method originally developed for genomics and later adapted to cross-sectional neuroimaging data. Using longitudinal cortical thickness measurements from 663 participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, we demonstrate the presence of additive and multiplicative scanner effects in various brain regions. We compare estimates of the association between diagnosis and change in cortical thickness over time using three versions of the ADNI data: unharmonized data, data harmonized using cross-sectional ComBat, and data harmonized using longitudinal ComBat. In simulation studies, we show that longitudinal ComBat is more powerful for detecting longitudinal change than cross-sectional ComBat and controls the type I error rate better than unharmonized data with scanner included as a covariate. The proposed method would be useful for other types of longitudinal data requiring harmonization, such as genomic data, or neuroimaging studies of neurodevelopment, psychiatric disorders, or other neurological diseases.
Collapse
Affiliation(s)
- Joanne C Beer
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE) Center, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, United States.
| | - Nicholas J Tustison
- Department of Radiology and Medical Imaging, University of Virginia, United States
| | - Philip A Cook
- Center for Neuromodulation in Depression and Stress, Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, United States
| | - Christos Davatzikos
- Center for Biomedical Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, United States
| | - Yvette I Sheline
- Center for Neuromodulation in Depression and Stress, Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, United States; Department of Neurology, Perelman School of Medicine, University of Pennsylvania, United States
| | - Russell T Shinohara
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE) Center, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, United States; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, United States
| | - Kristin A Linn
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE) Center, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, United States.
| | | |
Collapse
|
104
|
Martin-Isla C, Campello VM, Izquierdo C, Raisi-Estabragh Z, Baeßler B, Petersen SE, Lekadir K. Image-Based Cardiac Diagnosis With Machine Learning: A Review. Front Cardiovasc Med 2020; 7:1. [PMID: 32039241 PMCID: PMC6992607 DOI: 10.3389/fcvm.2020.00001] [Citation(s) in RCA: 81] [Impact Index Per Article: 20.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2019] [Accepted: 01/06/2020] [Indexed: 01/28/2023] Open
Abstract
Cardiac imaging plays an important role in the diagnosis of cardiovascular disease (CVD). Until now, its role has been limited to visual and quantitative assessment of cardiac structure and function. However, with the advent of big data and machine learning, new opportunities are emerging to build artificial intelligence tools that will directly assist the clinician in the diagnosis of CVDs. This paper presents a thorough review of recent works in this field and provide the reader with a detailed presentation of the machine learning methods that can be further exploited to enable more automated, precise and early diagnosis of most CVDs.
Collapse
Affiliation(s)
- Carlos Martin-Isla
- Departament de Matemàtiques & Informàtica, Universitat de Barcelona, Barcelona, Spain
| | - Victor M Campello
- Departament de Matemàtiques & Informàtica, Universitat de Barcelona, Barcelona, Spain
| | - Cristian Izquierdo
- Departament de Matemàtiques & Informàtica, Universitat de Barcelona, Barcelona, Spain
| | - Zahra Raisi-Estabragh
- Barts Heart Centre, Barts Health NHS Trust, London, United Kingdom.,William Harvey Research Institute, Queen Mary University of London, London, United Kingdom
| | - Bettina Baeßler
- Department of Diagnostic & Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
| | - Steffen E Petersen
- Barts Heart Centre, Barts Health NHS Trust, London, United Kingdom.,William Harvey Research Institute, Queen Mary University of London, London, United Kingdom
| | - Karim Lekadir
- Departament de Matemàtiques & Informàtica, Universitat de Barcelona, Barcelona, Spain
| |
Collapse
|
105
|
Schilling KG, Landman BA. AI in MRI: A case for grassroots deep learning. Magn Reson Imaging 2019; 64:1-3. [PMID: 31283972 PMCID: PMC8278255 DOI: 10.1016/j.mri.2019.07.004] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2019] [Accepted: 07/05/2019] [Indexed: 02/07/2023]
Affiliation(s)
- Kurt G Schilling
- Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Bennett A Landman
- Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Electrical Engineering, Vanderbilt University, Nashville, TN, USA.
| |
Collapse
|
106
|
van Zijl P, Knutsson L. In vivo magnetic resonance imaging and spectroscopy. Technological advances and opportunities for applications continue to abound. JOURNAL OF MAGNETIC RESONANCE (SAN DIEGO, CALIF. : 1997) 2019; 306:55-65. [PMID: 31377150 PMCID: PMC6703925 DOI: 10.1016/j.jmr.2019.07.034] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/17/2019] [Revised: 06/19/2019] [Accepted: 07/08/2019] [Indexed: 05/07/2023]
Abstract
Over the past decades, the field of in vivo magnetic resonance (MR) has built up an impressive repertoire of data acquisition and analysis technologies for anatomical, functional, physiological, and molecular imaging, the description of which requires many book volumes. As such it is impossible for a few authors to have an authoritative overview of the field and for a brief article to be inclusive. We will therefore focus mainly on data acquisition and attempt to give some insight into the principles underlying current advanced methods in the field and the potential for further innovation. In our view, the foreseeable future is expected to show continued rapid progress, for instance in imaging of microscopic tissue properties in vivo, assessment of functional and anatomical connectivity, higher resolution physiologic and metabolic imaging, and even imaging of receptor binding. In addition, acquisition speed and information content will continue to increase due to the continuous development of approaches for parallel imaging (including simultaneous multi-slice imaging), compressed sensing, and MRI fingerprinting. Finally, artificial intelligence approaches are becoming more realistic and will have a tremendous effect on both acquisition and analysis strategies. Together, these developments will continue to provide opportunity for scientific discovery and, in combination with large data sets from other fields such as genomics, allow the ultimate realization of precision medicine in the clinic.
Collapse
Affiliation(s)
- Peter van Zijl
- Department of Radiology, Johns Hopkins University, F.M. Kirby Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, MD, USA.
| | - Linda Knutsson
- Department of Medical Radiation Physics, Lund University, Lund, Sweden
| |
Collapse
|