Automatic high-resolution infarct detection using volumetric multiphase dual-energy CT

Sandfort, Veit; Kwan, Alan C.; Elumogo, Comfort; Vigneault, Davis M.; Symons, Rolf; Pourmorteza, Amir; Rice, Kelly A.; Davies-Venn, Cynthia; Ahlman, Mark A.; Liu, Chia Ying; Zimmerman, Stefan L.; Bluemke, David A.

doi:10.1016/j.jcct.2017.04.006

Cited by 8 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies only focus on one of them. In specific, for scar segmentation the most widespread methods are mainly based on thresholding, such as n-SD and full-width-at-half-maximum (FWHM) (Karim et al, 2016;Sandfort et al, 2017). It is mostly attribute to the relatively evident intensity contrast between scarring areas and background inside the myocardium.…”

Section: State-of-the-art Myocardial Pathology Segmentationmentioning

confidence: 99%

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: State-of-the-art Myocardial Pathology Segmentationmentioning

confidence: 99%

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

“…A large number of approaches on MyoPS solely focus on one type of pathologies, i.e., either scars or edema. For instance, Sandfort et al (2017) and Kolipaka et al (2005) proposed threshold-based methods to perform scar segmentation, while Kadir et al (2010) developed similar method for edema segmentation. Besides, given the difficulty in mining multi-sequence information, most of the reported algorithms barely employed a single sequence for MyoPS, especially LGE CMR which probably contains the most information (Rajiah et al, 2013), in spite of the drawback of injecting contrast agents.…”

Section: T1 Mapping Cmr Bssfp Cmrmentioning

confidence: 99%

“…For myocardial pathology segmentation, there exists a series of conventional algorithms. For example, Kolipaka et al (2005) and Sandfort et al (2017) utilized threshold methods for scar segmentation based on the intensity differences between healthy and diseased myocardium. Kadir et al (2010) combined the threshold segmentation with a morphological filtering algorithm for edema segmentation.…”

Section: Myocardial Pathology Segmentationmentioning

confidence: 99%

MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images

Qiu¹,

Li²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Myocardial pathology segmentation (MyoPS) can be a prerequisite for the accurate diagnosis and treatment planning of myocardial infarction. However, achieving this segmentation is challenging, mainly due to the inadequate and indistinct information from an image. In this work, we develop an end-to-end deep neural network, referred to as MyoPS-Net, to flexibly combine five-sequence cardiac magnetic resonance (CMR) images for MyoPS. To extract precise and adequate information, we design an effective yet flexible architecture to extract and fuse cross-modal features. This architecture can tackle different numbers of CMR images and complex combinations of modalities, with output branches targeting specific pathologies. To impose anatomical knowledge on the segmentation results, we first propose a module to regularize myocardium consistency and localize the pathologies, and then introduce an inclusiveness loss to utilize relations between myocardial scars and edema. We evaluated the proposed MyoPS-Net on two datasets, i.e., a private one consisting of 50 paired multi-sequence CMR images and a public one from MICCAI2020 MyoPS Challenge. Experimental results showed that MyoPS-Net could achieve state-of-the-art performance in various scenarios. Note that in practical clinics, the subjects may not have full sequences, such as missing LGE CMR or mapping CMR scans. We therefore conducted extensive experiments to investigate the performance of the proposed method in dealing with such complex combinations of different CMR sequences. Results proved the superiority and generalizability of MyoPS-Net, and more importantly, indicated a practical clinical application.

show abstract

“…Because of the superior spectral abilities already cited, PC CT is expected to exploit current dual-energy techniques for cardiovascular applications within cardiology. For example, virtual monochromatic images optimize the visibility of coronary stenosis (60) and infarcted myocardium (61,62); virtual noncalcium images improve visualization of the coronary artery thresholds from each other, photon counts within each energy bin are obtained (33).…”

Section: Cardiac Applications Of Pc Ctmentioning

confidence: 99%

Next-Generation Hardware Advances in CT: Cardiac Applications

Kwan¹,

Pourmorteza²,

Stutman

et al. 2021

Radiology

Self Cite

View full text Add to dashboard Cite

Automatic high-resolution infarct detection using volumetric multiphase dual-energy CT

Cited by 8 publications

References 22 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

MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images

Next-Generation Hardware Advances in CT: Cardiac Applications

Contact Info

Product

Resources

About