Dual Attention U-Net for Multi-sequence Cardiac MR Images Segmentation

Yu, Hong; Zha, Sen; Huangfu, Yubin; Chen, Chen; Ding, Meng; Li, Jiangyun

doi:10.1007/978-3-030-65651-5_11

Cited by 4 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, USTB adopted the elastic-transform, grid-distortion and optical-distortion to transform the training images nonrigidly. Experiments showed that this augmentation improved the Dice score by about 8% for scar segmentation (Yu et al, 2020).…”

Section: Data Augmentationmentioning

confidence: 97%

“…Note that the team abbreviations in the remaining of this paper refer both to the teams and their corresponding methods, as listed in Table 4. USTB (Yu et al, 2020) is not listed here as they did not provide open source code of their algorithm.…”

Section: Participantsmentioning

confidence: 99%

“…To reduce the complexity from background, all the teams cropped ROIs from the original images prior to the MyoPS. For example, USTB cropped ROIs of 256×256 pixel (Yu et al, 2020), and FZU cropped a small ROI and resized into images of 128×128 pixel (Zhang et al, 2020c). Another method was to perform a coarse segmentation on the images, to localize the position of LV, and then extract ROIs automatically.…”

Section: Preprocessingmentioning

confidence: 99%

See 2 more Smart Citations

MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images

Li¹,

Wu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on myocardium is the key to this assessment. This work defines a new task of medical image analysis, i.e., to perform myocardial pathology segmentation (MyoPS) combining threesequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. The challenge provided 45 paired and pre-aligned CMR images, allowing algorithms to combine the complementary information from the three CMR sequences for pathology segmentation. In this article, we provide details of the challenge, survey the works from fifteen participants and interpret their methods according to five aspects, i.e., preprocessing, data augmentation, learning strategy, model architecture and post-processing. In addition, we analyze the results with respect to different factors, in order to examine the key obstacles and explore potential of solutions, as well as to provide a benchmark for future research. We conclude that while promising results have been reported, the research is still in the early stage, and more in-depth exploration is needed before a successful application to the clinics. Note that MyoPS data and evaluation tool continue to be publicly available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/myops20/).

show abstract

Section: Data Augmentationmentioning

confidence: 97%

Section: Participantsmentioning

confidence: 99%

Section: Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images

Li¹,

Wu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Most of them roughly crops the training images to generate the center of heart. For example, USTB [20] simply crops the images into the ROI with 256 × 256 pixels. Besides, several teams employs prior segmentation network to automatically localize the position of LV and myocardium for ROI extraction.…”

Section: Myops: Myocardial Pathology Segmentation From Multi-sequence...mentioning

confidence: 99%

“…Online transformation mainly contains several conventional augmentation schemes, such as randomly rotation, scaling, shifting, brightness, non-rigid transformations and contrast adjustment. For example, USTB [20] transforms the original images non-rigidly with elastictransform, grid-distortion and optical-distortion. Offline augmentation mainly refers to data generation.…”

Section: Myops: Myocardial Pathology Segmentation From Multi-sequence...mentioning

confidence: 99%

Multi-Modality Cardiac Image Analysis with Deep Learning

Li¹,

Wu²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Accurate cardiac computing, analysis and modeling from multi-modality images are important for the diagnosis and treatment of cardiac disease. Late gadolinium enhancement magnetic resonance imaging (LGE MRI) is a promising technique to visualize and quantify myocardial infarction (MI) and atrial scars. Automating quantification of MI and atrial scars can be challenging due to the low image quality and complex enhancement patterns of LGE MRI. Moreover, compared with the other sequences LGE MRIs with gold standard labels are particularly limited, which represents another obstacle for developing novel algorithms for automatic segmentation and quantification of LGE MRIs. This chapter aims to summarize the state-of-the-art and our recent advanced contributions on deep learning based multi-modality cardiac image analysis. Firstly, we introduce two benchmark works for multi-sequence cardiac MRI based myocardial and pathology segmentation. Secondly, two novel frameworks for left atrial scar segmentation and quantification from LGE MRI were presented. Thirdly, we present three unsupervised domain adaptation techniques for cross-modality cardiac image segmentation.

show abstract

Myocardial Pathology Segmentation of Multi-modal Cardiac MR Images with a Simple but Efficient Siamese U-shaped Network

Wang

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Dual Attention U-Net for Multi-sequence Cardiac MR Images Segmentation

Cited by 4 publications

References 15 publications

MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images

MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images

Multi-Modality Cardiac Image Analysis with Deep Learning

Myocardial Pathology Segmentation of Multi-modal Cardiac MR Images with a Simple but Efficient Siamese U-shaped Network

Contact Info

Product

Resources

About