Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach

Duan, Jinming; Bello, Ghalib; Schlemper, Jo; Bai, Wenjia; Dawes, Timothy J W; Biffi, Carlo; Marvao, Antonio de; Doumou, Georgia; O’Regan, Declan P.; Rueckert, Daniel

doi:10.48550/arxiv.1808.08578

Cited by 3 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the anatomical rationality of the segmentation results, some researchers try to combine the anatomical knowledge into CNNs. In 2018, Duan et al 24 combined a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline. A fully convolutional network (FCN) was applied to learn segmentation and landmark localization tasks.…”

Section: Cardiac Segmentation Methods Based On Traditional Algorithmmentioning

confidence: 99%

Cardiac Segmentation Method Based on Domain Knowledge

et al. 2022

View full text Add to dashboard Cite

Echocardiography plays an important role in the clinical diagnosis of cardiovascular diseases. Cardiac function assessment by echocardiography is a crucial process in daily cardiology. However, cardiac segmentation in echocardiography is a challenging task due to shadows and speckle noise. The traditional manual segmentation method is a time-consuming process and limited by inter-observer variability. In this paper, we present a fast and accurate echocardiographic automatic segmentation framework based on Convolutional neural networks (CNN). We propose FAUet, a segmentation method serially integrated U-Net with coordinate attention mechanism and domain feature loss from VGG19 pre-trained on the ImageNet dataset. The coordinate attention mechanism can capture long-range dependencies along one spatial direction and meanwhile preserve precise positional information along the other spatial direction. And the domain feature loss is more concerned with the topology of cardiac structures by exploiting their higher-level features. In this research, we use a two-dimensional echocardiogram (2DE) of 88 patients from two devices, Philips Epiq 7C and Mindray Resona 7T, to segment the left ventricle (LV), interventricular septal (IVS), and posterior left ventricular wall (PLVW). We also draw the gradient weighted class activation mapping (Grad-CAM) to improve the interpretability of the segmentation results. Compared with the traditional U-Net, the proposed segmentation method shows better performance. The mean Dice Score Coefficient (Dice) of LV, IVS, and PLVW of FAUet can achieve 0.932, 0.848, and 0.868, and the average Dice of the three objects can achieve 0.883. Statistical analysis showed that there is no significant difference between the segmentation results of the two devices. The proposed method can realize fast and accurate segmentation of 2DE with a low time cost. Combining coordinate attention module and feature loss with the original U-Net framework can significantly increase the performance of the algorithm.

show abstract

Section: Cardiac Segmentation Methods Based On Traditional Algorithmmentioning

confidence: 99%

Cardiac Segmentation Method Based on Domain Knowledge

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Khened et al [6] adopted a densely connected CNN model with inception block to segment 2D cardiac MRI. There are also other researchers interesting on the ventricles, myocardium and other tissues MR segmentation [7][8][9][10][11][12][13]. Their methods are mostly based on CNN.…”

Section: Introductionmentioning

confidence: 99%

An Automatic Cardiac Segmentation Framework Based on Multi-sequence MR Image

Liu

Wang

et al. 2020

Statistical Atlases and Computational Models of the Heart. Multi-Sequence CMR Segmentation, CRT-EPiggy and LV Full Quantificati

View full text Add to dashboard Cite

LGE CMR is an efficient technology for detecting infarcted myocardium. An efficient and objective ventricle segmentation method in LGE can benefit the location of the infarcted myocardium. In this paper, we proposed an automatic framework for LGE image segmentation. There are just 5 labeled LGE volumes with about 15 slices of each volume. We adopted histogram match, an invariant of rotation registration method, on the other labeled modalities to achieve effective augmentation of the training data. A CNN segmentation model was trained based on the augmented training data by leave-one-out strategy. The predicted result of the model followed a connected component analysis for each class to remain the largest connected component as the final segmentation result. Our model was evaluated by the 2019 Multi-sequence Cardiac MR Segmentation Challenge. The mean testing result of 40 testing volumes on Dice score, Jaccard score, Surface distance, and Hausdorff distance is 0.8087, 0.6976, 2.8727mm, and 15.6387mm, respectively. The experiment result shows a satisfying performance of the proposed framework. Code is available at https://github.com/Suiiyu/MS-CMR2019.

show abstract

An Automatic Cardiac Segmentation Framework based on Multi-sequence MR Image

Liu

Wang

et al. 2019

Preprint

View full text Add to dashboard Cite

Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach

Cited by 3 publications

References 29 publications

Cardiac Segmentation Method Based on Domain Knowledge

Cardiac Segmentation Method Based on Domain Knowledge

An Automatic Cardiac Segmentation Framework Based on Multi-sequence MR Image

An Automatic Cardiac Segmentation Framework based on Multi-sequence MR Image

Contact Info

Product

Resources

About