Deep learning in spatiotemporal cardiac imaging: A review of methodologies and clinical usability

Hernandez, Karen Andrea Lara; Rienmüller, Theresa Margarethe; Baumgartner, Daniela; Baumgartner, Christian

doi:10.1016/j.compbiomed.2020.104200

Cited by 37 publications

(23 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MOCOnet also holds promise for stress T1 mapping applications (9)(10)(11)38) which may be subject to greater motion artefact. With the rapidly evolving field of deep learning, further research can be done to assess potential benefits of incorporating a more diverse variety of learning-based registration methods (23,43) into a quality-control driven pipeline (44)(45)(46) to verify the registration accuracy on-the-fly including the R 2 maps. With further work, MOCOnet together with T1 protocol quality assurance (47,48) and automated myocardial segmentation (45) could ultimately lead to a comprehensive framework for robust T1 mapping for clinical use.…”

Section: Discussionmentioning

confidence: 99%

MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks

Gonzales

Zhang

Papież

et al. 2021

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Background: Quantitative cardiovascular magnetic resonance (CMR) T1 mapping has shown promise for advanced tissue characterisation in routine clinical practise. However, T1 mapping is prone to motion artefacts, which affects its robustness and clinical interpretation. Current methods for motion correction on T1 mapping are model-driven with no guarantee on generalisability, limiting its widespread use. In contrast, emerging data-driven deep learning approaches have shown good performance in general image registration tasks. We propose MOCOnet, a convolutional neural network solution, for generalisable motion artefact correction in T1 maps.Methods: The network architecture employs U-Net for producing distance vector fields and utilises warping layers to apply deformation to the feature maps in a coarse-to-fine manner. Using the UK Biobank imaging dataset scanned at 1.5T, MOCOnet was trained on 1,536 mid-ventricular T1 maps (acquired using the ShMOLLI method) with motion artefacts, generated by a customised deformation procedure, and tested on a different set of 200 samples with a diverse range of motion. MOCOnet was compared to a well-validated baseline multi-modal image registration method. Motion reduction was visually assessed by 3 human experts, with motion scores ranging from 0% (strictly no motion) to 100% (very severe motion).Results: MOCOnet achieved fast image registration (<1 second per T1 map) and successfully suppressed a wide range of motion artefacts. MOCOnet significantly reduced motion scores from 37.1±21.5 to 13.3±10.5 (p < 0.001), whereas the baseline method reduced it to 15.8±15.6 (p < 0.001). MOCOnet was significantly better than the baseline method in suppressing motion artefacts and more consistently (p = 0.007).Conclusion: MOCOnet demonstrated significantly better motion correction performance compared to a traditional image registration approach. Salvaging data affected by motion with robustness and in a time-efficient manner may enable better image quality and reliable images for immediate clinical interpretation.

show abstract

Section: Discussionmentioning

confidence: 99%

MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks

Gonzales

Zhang

Papież

et al. 2021

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“…After that, a weighted sum of the inputs is calculated. The cost function is then transferred to a kernel function, which generates an output [34]. In the diagnosis of chest diseases, different types of CNN architectures, including AlexNet, VGGNet, GoogLeNet, ResNet to DenseNet, have achieved tremendous success.…”

Section: Deep Learning Methodologymentioning

confidence: 99%

Using Machine Learning via Deep Learning Algorithms to Diagnose the Lung Disease Based on Chest Imaging: A Survey

Ahmed

Kadhem

2021

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

<p class="0abstract"><strong>—</strong> Chest imaging diagnostics is crucial in the medical area due to many serious lung diseases like cancers and nodules and particularly with the current pandemic of Covid-19. Machine learning approaches yield prominent results toward the task of diagnosis. Recently, deep learning methods are utilized and recommended by many studies in this domain. The research aims to critically examine the newest lung disease detection procedures using deep learning algorithms that use X-ray and CT scan datasets. Here, the most recent studies in this area (2015-2021) have been reviewed and summarized to provide an overview of the most appropriate methods that should be used or developed in future works, what limitations should be considered, and at what level these techniques help physicians in identifying the disease with better accuracy. The lack of various standard datasets, the huge training set, the high dimensionality of data, and the independence of features have been the main limitations based on the literature. However, different architectures of deep learning are used by many researchers but, Convolutional Neural Networks (CNN) are still state-of-art techniques in dealing with image datasets.</p>

show abstract

“…Guo et al (16) focused on automated segmentation of left ventricular (LV) in temporal cardiac image sequences. Recently, temporal consistency has been explored in other cardiac imaging modalities including MRI, CT, and ultrasound (US), which is detailed in Hernandez et al (17). As far as we know, the effectiveness of temporal consistency has not been explored currently for MYO segmentation of CMR sequences.…”

Section: Introductionmentioning

confidence: 99%

Myocardial Segmentation of Cardiac MRI Sequences With Temporal Consistency for Coronary Artery Disease Diagnosis

Chen¹,

Xu²,

Zeng³

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Coronary artery disease (CAD) is the most common cause of death globally, and its diagnosis is usually based on manual myocardial (MYO) segmentation of MRI sequences. As manual segmentation is tedious, time-consuming, and with low replicability, automatic MYO segmentation using machine learning techniques has been widely explored recently. However, almost all the existing methods treat the input MRI sequences independently, which fails to capture the temporal information between sequences, e.g., the shape and location information of the myocardium in sequences along time. In this article, we propose a MYO segmentation framework for sequence of cardiac MRI (CMR) scanning images of the left ventricular (LV) cavity, right ventricular (RV) cavity, and myocardium. Specifically, we propose to combine conventional neural networks and recurrent neural networks to incorporate temporal information between sequences to ensure temporal consistency. We evaluated our framework on the automated cardiac diagnosis challenge (ACDC) dataset. The experiment results demonstrate that our framework can improve the segmentation accuracy by up to 2% in the Dice coefficient.

show abstract

Deep learning in spatiotemporal cardiac imaging: A review of methodologies and clinical usability

Cited by 37 publications

References 46 publications

MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks

MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks

Using Machine Learning via Deep Learning Algorithms to Diagnose the Lung Disease Based on Chest Imaging: A Survey

Myocardial Segmentation of Cardiac MRI Sequences With Temporal Consistency for Coronary Artery Disease Diagnosis

Contact Info

Product

Resources

About