APCP-NET: Aggregated Parallel Cross-Scale Pyramid Network for CMR Segmentation

Li, Caizi; Tong, Qianqian; Liao, Xiangyun; Si, Weixin; Chen, Shu; Wang, Qiong; Yuan, Zhiyong

doi:10.1109/isbi.2019.8759147

Cited by 6 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2019)). From this comparison, one can see that top algorithms are the ensemble method proposed by Isensee et al (2017) and the twostage method proposed by Li et al (2019a), both of which are based on FCNs. In particular, compared to the traditional level-set method (Tziritas and Grinias, 2017), both methods achieved considerably higher accuracy even for the more challenging segmentation of the left ventricular myocardium (Myo), indicating the power of deep learning based approaches.…”

Section: Ventricle Segmentationmentioning

confidence: 99%

Section: Ventricle Segmentationmentioning

confidence: 99%

“…Multi-stage networks: Recently, there is a growing interest in applying neural networks in a multi-stage pipeline which breaks down the segmentation problem into subtasks (Vigneault et al, 2018;Zheng et al, 2018;Li et al, 2019a;Tan et al, 2017;Liao et al, 2019). For example, Zheng et al (2018); Li et al (2019a) proposed a regionof-interest (ROI) localization network followed by a segmentation network. Likewise, Vigneault et al (2018) proposed a network called Omega-Net which consists of a U-net for cardiac chamber localization, a learnable transformation module to normalize image orientation and a series of U-nets for finegrained segmentation.…”

Section: Ventricle Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Cardiac Image Segmentation: A Review

Chen

Qiu

et al. 2020

Front. Cardiovasc. Med.

608

383

View full text Add to dashboard Cite

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound (US) and major anatomical structures of interest (ventricles, atria and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

show abstract

Section: Ventricle Segmentationmentioning

confidence: 99%

Section: Ventricle Segmentationmentioning

confidence: 99%

Section: Ventricle Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Cardiac Image Segmentation: A Review

Chen

Qiu

et al. 2020

Front. Cardiovasc. Med.

608

383

View full text Add to dashboard Cite

show abstract

“…Since InlineVF is proprietary, we are unable to fully evaluate the mechanism by which such overestimations may occur, although approaches to modify or exclude inaccurate labels may further improve the performance of future models. Fourth, although higher pixel-wise agreement has been reported using previous deep learning approaches, 18,[27][28][29][30][31] we note that the majority of such models were trained using hand-labeled segmentations provided on standardized image sets, which may not be directly comparable to our UK Biobank test set images. Owing to absence of pretrained weights or incompatibility of older models with our codebase, we were unable to directly compare the performance of ML4H seg with previous models within our test set.…”

Section: Discussionmentioning

confidence: 71%

Deep learning to estimate cardiac magnetic resonance–derived left ventricular mass

Khurshid

Friedman

Achille

et al. 2021

Cardiovascular Digital Health Journal

View full text Add to dashboard Cite

BACKGROUND Cardiac magnetic resonance (CMR) is the gold standard for left ventricular hypertrophy (LVH) diagnosis. CMR-derived LV mass can be estimated using proprietary algorithms (eg, Inli-neVF), but their accuracy and availability may be limited. OBJECTIVETo develop an open-source deep learning model to estimate CMR-derived LV mass.METHODS Within participants of the UK Biobank prospective cohort undergoing CMR, we trained 2 convolutional neural networks to estimate LV mass. The first (ML4H reg ) performed regression informed by manually labeled LV mass (available in 5065 individuals), while the second (ML4H seg ) performed LV segmentation informed by InlineVF (version D13A) contours. We compared ML4H reg , ML4H seg , and InlineVF against manually labeled LV mass within an independent holdout set using Pearson correlation and mean absolute error (MAE). We assessed associations between CMR-derived LVH and prevalent cardiovascular disease using logistic regression adjusted for age and sex. RESULTSWe generated CMR-derived LV mass estimates within 38,574 individuals. Among 891 individuals in the holdout set, ML4H seg reproduced manually labeled LV mass more accurately (r 5 0.864, 95% confidence interval [CI] 0.847-0.880; MAE 10.41 g, 95% CI 9.82-10.99) than ML4H reg (r 5 0.843, 95% CI 0.823-0.861; MAE 10.51, 95% CI 9.86-11.15, P 5 .01) and InlineVF (r 5 0.795, 95% CI 0.770-0.818; MAE 14.30, 95% CI 13.46-11.01, P , .01). LVH defined using ML4H seg demonstrated the strongest associations with hypertension (odds ratio 2.76, 95% CI 2.51-3.04), atrial fibrillation (1.75, 95% CI 1.37-2.20), and heart failure (4.67, 95% CI 3.28-6.49). CONCLUSIONS ML4Hseg is an open-source deep learning model providing automated quantification of CMR-derived LV mass. Deep learning models characterizing cardiac structure may facilitate broad cardiovascular discovery.

show abstract

“…However, in the existing convolutional networks used for cardiac MRI segmentation, including U-Net, the skip connection between an encoder and a decoder path fuses features using the same resolution [20]. Therefore, these methods lack robustness, which has led to poor segmentation results and particularly ineffective segmentation of the RV.…”

Section: Introductionmentioning

confidence: 99%

MFAUNet: Multiscale feature attentive U‐Net for cardiac MRI structural segmentation

Peng

Guo

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

The accurate and robust automatic segmentation of cardiac structures in magnetic resonance imaging (MRI) is significant in calculating cardiac clinical functional indices, and diagnosing heart diseases. Most U‐Net based methods use pooling, transposed convolution, and skip connection operations to integrate the multiscale features for improved segmentation in cardiac MRI. However, this architecture lacks adequate semantic connection between the channel and spatial information, and robustness in segmenting objects with significant shape variations. In this paper, a new multiscale feature attentive U‐Net for cardiac MRI structural segmentation method is proposed. An attention mechanism is adopted after concatenating the multi‐level features to aggregate different scale features and determine on which features to focus. Cascade and parallel dilated convolution is also employed in the decoder blocks and skip connection is employed to enhance the ability of sensing receptive fields for multiscale context information. Furthermore, deep supervision approach with a loss function that combines the dice and cross‐entropy losses to reduce overfitting and ensure better prediction is introduced. The proposed method was evaluated on three public cardiac datasets. The experimental results indicate that the method achieved competitive segmentation performance with the three datasets, which verifies the robustness and generalisability of the proposed network. In comparison with conventional U‐Net methods, the model leverages attention mechanism and dilated convolution block, which increases the semantic connection between the channel and the spatial information, and improves the robustness of the right ventricle segmentation performance. From the view of the Dice scores and segmentation results, the multiscale feature attentive U‐Net method is one of effective methods in segmenting cardiac MRI structures.

show abstract

APCP-NET: Aggregated Parallel Cross-Scale Pyramid Network for CMR Segmentation

Cited by 6 publications

References 6 publications

Deep Learning for Cardiac Image Segmentation: A Review

Deep Learning for Cardiac Image Segmentation: A Review

Deep learning to estimate cardiac magnetic resonance–derived left ventricular mass

MFAUNet: Multiscale feature attentive U‐Net for cardiac MRI structural segmentation

Contact Info

Product

Resources

About