Fully automated left atrium segmentation from anatomical cine long-axis MRI sequences using deep convolutional neural network with unscented Kalman filter

Zhang, Xiaoran; Noga, Michelle; Martin, David Glynn; Punithakumar, Kumaradevan

doi:10.1016/j.media.2020.101916

Cited by 20 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other methods, similar to ours, sought to segment the LA in long-axis cine images, as noted above. These include a convolutional-neural-network method with the unscented Kalman filter which yielded an excellent DSC of 0.94 ± 0.04 for 2ch and 0.94 ± 0.08 for 4ch (n = 20) [ 20 ], and a similar method with a VGG-16 framework which also yielded an excellent DSC of 0.93 ± 0.05 for 2ch and 0.95 ± 0.02 for 4ch (n = 600) [ 21 ]. However, none of these methods reported clinical metrics nor were evaluated in a clinical population.…”

Section: Discussionmentioning

confidence: 99%

“…Another limitation of this work is that total segmentation time which, while a matter of only seconds, was still longer than learning-based methods [ 20 , 21 ] which require less than a second. Although this difference in time is a pitfall, compared to human labor our method is valuable and an attractive option.…”

Section: Discussionmentioning

confidence: 99%

“…Regarding these, one method uses feature tracking to propagate LA contours, once manually initialized on end-diastolic and/or end-systolic frames [ 10 , 19 ], but this still demands user interaction. Machine learning techniques have been used to segment the LA in long-axis cine images, integrating a modified U-net based on deep convolutional neural networks with the unscented Kalman filter to impose temporal consistency in 2, 3 and 4-chamber views [ 20 ]. Another convolutional neural network architecture with a VGG-16 framework was proposed to predict a pixel-wise label map for the LA [ 21 ], but it was only trained on end-diastolic and end-systolic frames and with healthy volunteers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated left atrial time-resolved segmentation in MRI long-axis cine images using active contours

et al. 2021

View full text Add to dashboard Cite

Background Segmentation of the left atrium (LA) is required to evaluate atrial size and function, which are important imaging biomarkers for a wide range of cardiovascular conditions, such as atrial fibrillation, stroke, and diastolic dysfunction. LA segmentations are currently being performed manually, which is time-consuming and observer-dependent. Methods This study presents an automated image processing algorithm for time-resolved LA segmentation in cardiac magnetic resonance imaging (MRI) long-axis cine images of the 2-chamber (2ch) and 4-chamber (4ch) views using active contours. The proposed algorithm combines mitral valve tracking, automated threshold calculation, edge detection on a radially resampled image, edge tracking based on Dijkstra’s algorithm, and post-processing involving smoothing and interpolation. The algorithm was evaluated in 37 patients diagnosed mainly with paroxysmal atrial fibrillation. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC) and Hausdorff distance (HD), with manual segmentations in all time frames as the reference standard. For inter-observer variability analysis, a second observer performed manual segmentations at end-diastole and end-systole on all subjects. Results The proposed automated method achieved high performance in segmenting the LA in long-axis cine sequences, with a DSC of 0.96 for 2ch and 0.95 for 4ch, and an HD of 5.5 mm for 2ch and 6.4 mm for 4ch. The manual inter-observer variability analysis had an average DSC of 0.95 and an average HD of 4.9 mm. Conclusion The proposed automated method achieved performance on par with human experts analyzing MRI images for evaluation of atrial size and function.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated left atrial time-resolved segmentation in MRI long-axis cine images using active contours

et al. 2021

View full text Add to dashboard Cite

show abstract

“…15 16 17 18 20 Some researchers conducted interactive learning using CNNs into scribble-based segmentation and the spatial coordinate (x, y, w, h) of an object to generalize previous unseen objects 20 and developed CNNs to segment for the atrium and ventricle in cardiac imaging. 21 22 …”

Section: Introductionmentioning

confidence: 99%

Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging

Cho

Shim

et al. 2022

J Korean Med Sci

View full text Add to dashboard Cite

Background To propose fully automatic segmentation of left atrium using active learning with limited dataset in late gadolinium enhancement in cardiac magnetic resonance imaging (LGE-CMRI). Methods An active learning framework was developed to segment the left atrium in cardiac LGE-CMRI. Patients (n = 98) with atrial fibrillation from the Korea University Anam Hospital were enrolled. First, 20 cases were delineated for ground truths by two experts and used for training a draft model. Second, the 20 cases from the first step and 50 new cases, corrected in a human-in-the-loop manner after predicting using the draft model, were used to train the next model; all 98 cases (70 cases from the second step and 28 new cases) were trained. An additional 20 LGE-CMRI were evaluated in each step. Results The Dice coefficients for the three steps were 0.85 ± 0.06, 0.89 ± 0.02, and 0.90 ± 0.02, respectively. The biases (95% confidence interval) in the Bland-Altman plots of each step were 6.36% (−14.90–27.61), 6.21% (−9.62–22.03), and 2.68% (−8.57–13.93). Deep active learning-based annotation times were 218 ± 31 seconds, 36.70 ± 18 seconds, and 36.56 ± 15 seconds, respectively. Conclusion Deep active learning reduced annotation time and enabled efficient training on limited LGE-CMRI.

show abstract

“…Automated and accurate LA segmentation is a crucial task to aid the diagnosis and treatment for the patients with atrial fibrillation (AF) [1]- [4]. Deep learning based approaches have great potential for the LA segmentation [5], [6]. However, it is expensive and laborious to annotate large amounts of data by experienced experts for training an accurate LA segmentation model based on deep learning [7].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data

Chen

Zhang

Mohiaddin

et al. 2022

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Semi-supervised learning provides great sig-1 nificance in left atrium (LA) segmentation model learn-2 ing with insufficient labelled data. Generalising semi-3 supervised learning to cross-domain data is of high importance to further improve model robustness. However, 5 the widely existing distribution difference and sample mismatch between different data domains hinder the gener-7 alisation of semi-supervised learning. In this study, we 8 alleviate these problems by proposing an Adaptive Hier-9 archical Dual Consistency (AHDC) for the semi-supervised 10 LA segmentation on cross-domain data. The AHDC mainly 11 consists of a Bidirectional Adversarial Inference module 12 (BAI) and a Hierarchical Dual Consistency learning module 13 (HDC). The BAI overcomes the difference of distributions 14 and the sample mismatch between two different domains. It mainly learns two mapping networks adversarially to 16 obtain two matched domains through mutual adaptation. 17 The HDC investigates a hierarchical dual learning paradigm 18 for cross-domain semi-supervised segmentation based on 19 the obtained matched domains. It mainly builds two dual-20 modelling networks for mining the complementary informa-21 tion in both intra-domain and inter-domain. For the intra-22 domain learning, a consistency constraint is applied to the 23 dual-modelling targets to exploit the complementary mod-24 elling information. For the inter-domain learning, a consistency constraint is applied to the LAs modelled by two dual-26 modelling networks to exploit the complementary knowledge among different data domains. We demonstrated the 28 performance of our proposed AHDC on four 3D late gadolin-29 ium enhancement cardiac MR (LGE-CMR) datasets from

show abstract

Fully automated left atrium segmentation from anatomical cine long-axis MRI sequences using deep convolutional neural network with unscented Kalman filter

Cited by 20 publications

References 21 publications

Automated left atrial time-resolved segmentation in MRI long-axis cine images using active contours

Automated left atrial time-resolved segmentation in MRI long-axis cine images using active contours

Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging

Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data

Contact Info

Product

Resources

About