Segmenting Atrial Fibrosis from Late Gadolinium-Enhanced Cardiac MRI by Deep-Learned Features with Stacked Sparse Auto-Encoders

Yang, Guang; Zhuang, Xiahai; Khan, Habib; Haldar, Shouvik; Nyktari, Eva; Ye, Xujiong; Slabaugh, Greg; Wong, Tom; Mohiaddin, Raad H.; Keegan, Jennifer; Firmin, David

doi:10.1007/978-3-319-60964-5_17

Cited by 13 publications

(22 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…SSAE is a deep neural network composed of multiple stacked sparse auto-encoders (SAEs) [37], and it has been applied in tissue segmentation in late gadolinium-enhanced cardiac MRI images (such as atrial scarring segmentation [38], atrial fibrosis segmentation [39], left atrium segmentation [40]), nuclei patch classification on breast cancer histopathology images [41], brain tissue segmentation in visible human images [42], or other applications (such as hyperspectral imagery classification [43] and building extraction from LiDAR and optical images [44]). Figure 3 shows a SSAE network with three hidden layers, where a SAE aims to learn features that form a good sparse representation of its input.…”

Section: Proposed Methodsmentioning

confidence: 99%

Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor

Niu

Lan²,

Wang³

2019

Sensors

View full text Add to dashboard Cite

Automatic detection of left ventricle myocardium is essential to subsequent cardiac image registration and tissue segmentation. However, it is considered challenging mainly because of the complex and varying shape of the myocardium and surrounding tissues across slices and phases. In this study, a hybrid model is proposed to detect myocardium in cardiac magnetic resonance (MR) images combining region proposal and deep feature classification and regression. The model firstly generates candidate regions using new structural similarity-enhanced supervoxel over-segmentation plus hierarchical clustering. Then it adopts a deep stacked sparse autoencoder (SSAE) network to learn the discriminative deep feature to represent the regions. Finally, the features are fed to train a novel nonlinear within-class neighborhood preserved soft margin support vector (C-SVC) classifier and multiple-output support vector ( ε -SVR) regressor for refining the location of myocardium. To improve the stability and generalization, the model also takes hard negative sample mining strategy to fine-tune the SSAE and the classifier. The proposed model with impacts of different components were extensively evaluated and compared to related methods on public cardiac data set. Experimental results verified the effectiveness of proposed integrated components, and demonstrated that it was robust in myocardium localization and outperformed the state-of-the-art methods in terms of typical metrics. This study would be beneficial in some cardiac image processing such as region-of-interest cropping and left ventricle volume measurement.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor

Niu

Lan²,

Wang³

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…They achieved 90 ± 0.12% Dice score for blood pool segmentation and 78 ± 0.08% Dice score for fibrosis segmentation. In their subsequent study (86), by finetuning the sparse auto-encoder parameters, the accuracy was improved to 82 ± 0.05% Dice score for fibrosis segmentation.…”

Section: Atrial Wall and Scar Segmentationmentioning

confidence: 99%

Mini Review: Deep Learning for Atrial Segmentation From Late Gadolinium-Enhanced MRIs

Jamart

Xiong

Talou

et al. 2020

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Segmentation and 3D reconstruction of the human atria is of crucial importance for precise diagnosis and treatment of atrial fibrillation, the most common cardiac arrhythmia. However, the current manual segmentation of the atria from medical images is a time-consuming, labor-intensive, and error-prone process. The recent emergence of artificial intelligence, particularly deep learning, provides an alternative solution to the traditional methods that fail to accurately segment atrial structures from clinical images. This has been illustrated during the recent 2018 Atrial Segmentation Challenge for which most of the challengers developed deep learning approaches for atrial segmentation, reaching high accuracy (>90% Dice score). However, as significant discrepancies exist between the approaches developed, many important questions remain unanswered, such as which deep learning architectures and methods to ensure reliability while achieving the best performance. In this paper, we conduct an in-depth review of the current state-of-the-art of deep learning approaches for atrial segmentation from late gadolinium-enhanced MRIs, and provide critical insights for overcoming the main hindrances faced in this task.

show abstract

“…Inspired by similar work in the literature for scar segmentation (e.g. [24,18,25]), the segmentation outcomes, obtained with both Protocol 1 and Protocol 2, were quantitatively evaluated with respect to the GT in terms of pixel classification accuracy (Acc), sensitivity (Se), and specificity (Sp):…”

Section: Discussionmentioning

confidence: 99%

“…Similarly, clustering techniques such as GMM need to the define the number of GMM classes, which is not always trivial [38,39]. With respect to other DL-based methodologies, such as [24,18,25], our approach directly provided the segmentation mask without requiring (i) pre-processing to extract and (ii) post processing to merge superpixels or patches from the LV myocardial region. This was achieved by exploiting a fully-convolutional architecture instead of an architecture based on CNNs with fully-connected layers for classification tasks.…”

Section: Discussionmentioning

confidence: 99%

“…Despite the potentiality of DL for medical-image segmentation, few DL-based attempts at scar segmentation from CMR-LGE images can be found in the literature. These attempts include [24,18], that exploit CNNs for superpixels-based feature extraction and sparse auto-encoders for superpixel classification (i.e., each superpixel is classified as scar tissue or healthy myocardial tissue). Additionally, in [25] CNN-based image features were extracted from image square patches, and the features from one patch were classified with fully-connected layers while the output class was assigned to the central pixel of the patch.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and testing of a deep learning-based strategy for scar segmentation on CMR-LGE images

Moccia

Banali

Martini

et al. 2018

Magn Reson Mater Phy

View full text Add to dashboard Cite

Object: The aim of this paper is to investigate the use of fully-convolutional neural networks (FCNNs) to segment scar tissue in the left ventricle from cardiac magnetic resonance with late gadolinium enhancement (CMR-LGE) images. Methods: A successful FCNN in the literature (the ENet) was modified and trained to provide scar-tissue segmentation. Two segmentation protocols (Protocol 1 and Protocol 2) were investigated, the latter limiting the scar-segmentation search area to the left ventricular myocardial tissue region. CMR-LGE from 30 patients with ischemicheart disease were retrospectively analyzed, for a total of 250 images, presenting high variability in terms of scar dimension and location. Segmentation results were assessed against manual scar-tissue tracing using one-patient-out cross validation. Results: Protocol 2 outperformed Protocol 1 significantly (p-value < 0.05), with median sensitivity and Dice similarity coefficient equal to 88.07% (inter-quartile range (IQR) = 18.84%) and 71.25% (IQR = 31.82%), respectively. Discussion: Both segmentation protocols were able to detect scar tissues in the CMR-LGE images but higher performance was achieved when limiting the search area to the myocardial region. The findings of this paper represent an encouraging starting point for the use of FCNNs for the automatic segmentation of nonviable scar tissue from CMR-LGE images.

show abstract

Segmenting Atrial Fibrosis from Late Gadolinium-Enhanced Cardiac MRI by Deep-Learned Features with Stacked Sparse Auto-Encoders

Cited by 13 publications

References 37 publications

Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor

Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor

Mini Review: Deep Learning for Atrial Segmentation From Late Gadolinium-Enhanced MRIs

Development and testing of a deep learning-based strategy for scar segmentation on CMR-LGE images

Contact Info

Product

Resources

About