Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning

@article{Xue2020AutomatedIA,
  title={Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning},
  author={Hui Xue and Rhodri Davies and Louise A E Brown and Kristopher D Knott and Tushar Kotecha and Marianna Fontana and Sven Plein and James C. Moon and Peter Kellman},
  journal={Radiology: Artificial intelligence},
  year={2020},
  volume={2}
}
  • H. Xue, R. Davies, +6 authors P. Kellman
  • Published 2020
  • Computer Science, Medicine, Mathematics, Biology, Engineering
  • Radiology: Artificial intelligence
Purpose To develop a deep neural network–based computational workflow for inline myocardial perfusion analysis that automatically delineates the myocardium, which improves the clinical workflow and offers a “one-click” solution. Materials and Methods In this retrospective study, consecutive adenosine stress and rest perfusion scans were acquired from three hospitals between October 1, 2018 and February 27, 2019. The training and validation set included 1825 perfusion series from 1034 patients… Expand
Automated Segmental Analysis of Fully Quantitative Myocardial Blood Flow Maps by First-Pass Perfusion Cardiovascular Magnetic Resonance
TLDR
This work presents a fully automatic method of segmenting the left ventricular myocardium from MBF pixel maps, validated on a retrospective dataset of 247 clinical CMR perfusion studies, each including rest and stress images of three slice locations, performed on a 1.5T scanner. Expand
Artificial Intelligence Based Multimodality Imaging: A New Frontier in Coronary Artery Disease Management
TLDR
This study aims to provide a comprehensive overview of current and future AI applications to the field of multimodality imaging of ischemic heart disease and can assist clinicians in identifying early predictors of adverse outcome that human eyes cannot see in the fog of "big data". Expand
Landmark Detection in Cardiac MRI by Using a Convolutional Neural Network
TLDR
A CNN was developed for landmark detection on both long- and short-axis CMR images acquired with cine, LGE, and T1 mapping sequences, and the accuracy of the CNN was comparable with the interreader variation. Expand
Myocardial Perfusion Defects in Hypertrophic Cardiomyopathy Mutation Carriers
  • R. Hughes, C. Camaioni, +12 authors James C. Moon
  • Medicine
  • Journal of the American Heart Association
  • 2021
Background Impaired myocardial blood flow (MBF) in the absence of epicardial coronary disease is a feature of hypertrophic cardiomyopathy (HCM). Although most evident in hypertrophied or scarredExpand
Automated detection of left ventricle in arterial input function images for inline perfusion mapping using deep learning: A study of 15,000 patients
TLDR
This study presents a robust LV detection method using the convolutional neural network (CNN) to improve the detection of regional and global flow reduction in myocardial perfusion. Expand
Landmark detection in Cardiac Magnetic Resonance Imaging Using A Convolutional Neural Network
TLDR
This study developed, validated and deployed a CNN solution for robust landmark detection in both long and short-axis CMR images for cine, LGE and T1 mapping sequences, with the accuracy comparable to the inter-operator variation. Expand
The Prognostic Significance of Quantitative Myocardial Perfusion
TLDR
In patients with known or suspected coronary artery disease, reduced MBF and MPR measured automatically inline using artificial intelligence quantification of cardiovascular magnetic resonance perfusion mapping provides a strong, independent predictor of adverse cardiovascular outcomes. Expand

References

SHOWING 1-10 OF 83 REFERENCES
Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association.
TLDR
A remarkable committee was convened: The American Heart Association Writing Group on Myocardial Segmentation and Registration for Cardiac Imaging came to an agreement upon all aspects of nomenclature and anatomic descriptions of the heart. Expand
Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning
TLDR
This paper describes the winning solution for MICCAI 2017 Endoscopic Vision SubChallenge: Robotic Instrument Segmentation and its further refinement, and demonstrates an improvement over the state-of-the-art results using several novel deep neural network architectures. Expand
Automatic differentiation in PyTorch
TLDR
An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead. Expand
The Prognostic Significance of Quantitative Myocardial Perfusion
TLDR
In patients with known or suspected coronary artery disease, reduced MBF and MPR measured automatically inline using artificial intelligence quantification of cardiovascular magnetic resonance perfusion mapping provides a strong, independent predictor of adverse cardiovascular outcomes. Expand
  • Circulation
  • 2020
Automated detection of left ventricle in arterial input function images for inline perfusion mapping using deep learning: A study of 15,000 patients
TLDR
This study presents a robust LV detection method using the convolutional neural network (CNN) to improve the detection of regional and global flow reduction in myocardial perfusion. Expand
Focal Loss for Dense Object Detection
TLDR
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. Expand
  • 2019
Accuracy, uncertainty, and adaptability of automatic myocardial ASL segmentation using deep CNN
To apply deep convolution neural network to the segmentation task in myocardial arterial spin labeled perfusion imaging and to develop methods that measure uncertainty and that adapt the convolutionExpand
Artificial Intelligence Will Transform Cardiac Imaging—Opportunities and Challenges
TLDR
Many opportunities in cardiac imaging exist where AI will impact patients, medical staff, hospitals, commissioners and thus, the entire healthcare system, according to this perspective article. Expand
...
1
2
3
4
5
...