MuTGAN: Simultaneous Segmentation and Quantification of Myocardial Infarction Without Contrast Agents via Joint Adversarial Learning

Xu, Chenchu; Xu, Lei; Brahm, Gary; Zhang, Heye; Li, Shuo

doi:10.1007/978-3-030-00934-2_59

Cited by 25 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For automatic segmentation and classification of images from patients with cardiac diseases associated with structural remodeling, a variational autoencoder (VAE) model based on 3D convolutional layers was introduced by Biffi et al [317]. A multitask generative adversarial networks was proposed by Xu et al [318] as a contrast-free, stable and automatic clinical tool to segment and quantify myocardial infarction simultaneously. In [319], a task driven generative adversarial network is introduced to achieve simultaneous image synthesis and automatic multi-organ segmentation on X-ray images.…”

Section: Emergent Architectures: the Generative Adversarial Networkmentioning

confidence: 99%

Deep Learning in the Biomedical Applications: Recent and Future Status

2019

View full text Add to dashboard Cite

Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.

show abstract

Section: Emergent Architectures: the Generative Adversarial Networkmentioning

confidence: 99%

Deep Learning in the Biomedical Applications: Recent and Future Status

2019

View full text Add to dashboard Cite

show abstract

“…To assess the joint configuration of many label variables, the method of semantic segmentation using adversarial networks (GAN) [17] was proposed to produce label maps that cannot be distinguished from ground-truth. The adversarial theory has extended to prostate cancer detection [18], brain MRI segmentation [19], and quantification of myocardial infarction [20]. All these works have gained different levels of improvement, which proves the effectiveness of adversarial learning.…”

Section: A Related Workmentioning

confidence: 99%

S³egANet: 3D Spinal Structures Segmentation via Adversarial Nets

Wei

Cong

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

3D spinal structures segmentation is crucial to reduce the time-consumption issue and provide quantitative parameters for disease treatment and surgical operation. However, the most related studies of spinal structures segmentation are based on 2D or 3D single structure segmentation. Due to the high complexity of spinal structures, the segmentation of 3D multiple spinal structures with consistently reliable and high accuracy is still a significant challenge. We developed and validated a relatively complete solution for the simultaneous 3D semantic segmentation of multiple spinal structures at the voxel level named as the S 3 egANet. Firstly, S 3 egANet explicitly solved the high variety and variability of complex 3D spinal structures through a multi-modality autoencoder module that was capable of extracting fine-grained structural information. Secondly, S 3 egANet adopted a cross-modality voxel fusion module to incorporate comprehensive spatial information from multi-modality MRI images. Thirdly, we presented a multi-stage adversarial learning strategy to achieve high accuracy and reliability segmentation of multiple spinal structures simultaneously. Extensive experiments on MRI images of 90 patients demonstrated that S 3 egANet achieved mean Dice coefficient of 88.3% and mean Sensitivity of 91.45%, which revealed its effectiveness and potential as a clinical tool.

show abstract

“…Specifically in cardiac imaging, GANs have been used for tasks such as image synthesis, for example CMR image synthesis using a Cycle-GAN based on CT scans [3]. Work on image segmentation in cardiology using GANs include quantification of myocardial infarction by Xu et al [13]. GANs have also been used in identifying cardiac images with incomplete information using SCGANs by Zhang et al [14].…”

Section: Related Workmentioning

confidence: 99%

Conditional Generative Adversarial Networks for the Prediction of Cardiac Contraction from Individual Frames

Ossenberg-Engels

Grau

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

Cardiac anatomy and function are interrelated in many ways, and these relations can be affected by multiple pathologies. In particular, this applies to ventricular shape and mechanical deformation. We propose a machine learning approach to capture these interactions by using a conditional Generative Adversarial Network (cGAN) to predict cardiac deformation from individual Cardiac Magnetic Resonance (CMR) frames, learning a deterministic mapping between end-diastolic (ED) to end-systolic (ES) CMR short-axis frames. We validate the predicted images by quantifying the difference with real images using mean squared error (MSE) and structural similarity index (SSIM), as well as the Dice coefficient between their respective endo-and epicardial segmentations, obtained with an additional U-Net. We evaluate the ability of the network to learn "healthy" deformations by training it on ∼33,500 image pairs from ∼12,000 subjects, and testing on a separate test set of ∼4,500 image pairs from the UK Biobank study. Mean MSE, SSIM and Dice scores were 0.0026 ±0.0013, 0.89 ±0.032 and 0.89 ±0.059 respectively. We subsequently re-trained the network on specific patient group data, showing that the network is capable of extracting physiologically meaningful differences between patient populations suggesting promising applications on pathological data.

show abstract

MuTGAN: Simultaneous Segmentation and Quantification of Myocardial Infarction Without Contrast Agents via Joint Adversarial Learning

Cited by 25 publications

References 10 publications

Deep Learning in the Biomedical Applications: Recent and Future Status

Deep Learning in the Biomedical Applications: Recent and Future Status

S³egANet: 3D Spinal Structures Segmentation via Adversarial Nets

Conditional Generative Adversarial Networks for the Prediction of Cardiac Contraction from Individual Frames

Contact Info

Product

Resources

About

MuTGAN: Simultaneous Segmentation and Quantification of Myocardial Infarction Without Contrast Agents via Joint Adversarial Learning

Cited by 25 publications

References 10 publications

Deep Learning in the Biomedical Applications: Recent and Future Status

Deep Learning in the Biomedical Applications: Recent and Future Status

S3egANet: 3D Spinal Structures Segmentation via Adversarial Nets

Conditional Generative Adversarial Networks for the Prediction of Cardiac Contraction from Individual Frames

Contact Info

Product

Resources

About

S³egANet: 3D Spinal Structures Segmentation via Adversarial Nets