Automated Identification of Infarcted Myocardium Tissue Characterization Using Ultrasound Images: A Review

Sudarshan, Vidya K.; Acharya, U. Rajendra; Ng, Eddie Yin-Kwee; Meng, Chou Siaw; Tan, Ru San; Ghista, Dhanjoo N.

doi:10.1109/rbme.2014.2319854

Cited by 29 publications

(16 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Echocardiographic studies were performed using a Vivid 7 system (GE Healthcare, Milwaukee, WI, USA) equipped with a 10S transducer (8)(9)(10)(11)(12). The styrofoam board was tilted to maintain the rat in the left lateral decubitus position during image acquisition.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A novel myocardium segmentation approach based on neutrosophic active contour model

Guo

Xue

et al. 2017

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“…Computer aided diagnosis (CAD) system has been developed to identify the infarcted myocardium [9] . Many approaches have been proposed to identify and track myocardial borders [10] , the ventricular cavity (i.e.…”

Section: Introductionmentioning

confidence: 99%

A novel myocardium segmentation approach based on neutrosophic active contour model

Guo

Xue

et al. 2017

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

“…This may change in the future, as researchers improve current methods or develop more reproducible methods of differentiating regions in US images. One example of this are alternative metrics that rely on tissue texture, paired with computer models to automate image assessment [66]. …”

Section: Organ-scale Imagingmentioning

confidence: 99%

Imaging the Cardiac Extracellular Matrix

Pinkert

Hortensius

Ogle

et al. 2018

Advances in Experimental Medicine and Biology

View full text Add to dashboard Cite

Cardiovascular disease is the global leading cause of death. One route to address this problem is using biomedical imaging to measure the molecules and structures that surround cardiac cells. This cellular microenvironment, known as the cardiac extracellular matrix, changes in composition and organization during most cardiac diseases and in response to many cardiac treatments. Measuring these changes with biomedical imaging can aid in understanding, diagnosing, and treating heart disease. This chapter supports those efforts by reviewing representative methods for imaging the cardiac extracellular matrix. It first describes the major biological targets of ECM imaging, including the primary imaging target of fibrillar collagen. Then it discusses the imaging methods, describing their current capabilities and limitations. It categorizes the imaging methods into two main categories: organ-scale noninvasive methods and cellular-scale invasive methods. Noninvasive methods can be used on patients, but only a few are clinically available, and others require further development to be used in the clinic. Invasive methods are the most established and can measure a variety of properties, but they cannot be used on live patients. Finally, the chapter concludes with a perspective on future directions and applications of biomedical imaging technologies.

show abstract

“…Recent works classified infarcted and healthy subjects from echocardiographic image features [8], or shape data from MR sequences [9], which led to a challenge at STACOM-MICCAI'15 [10]. Infarct prediction at the regional level was also recently proposed via simple machine learning (linear SVM on MR sequences [11] and computed tomography images [12]).…”

Section: Introductionmentioning

confidence: 99%

Infarct Localization From Myocardial Deformation: Prediction and Uncertainty Quantification by Regression From a Low-Dimensional Space

Duchateau

Craene

Allain

et al. 2016

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Diagnosing and localizing myocardial infarct is crucial for early patient management and therapy planning. We propose a new method for predicting the location of myocardial infarct from local wall deformation, which has value for risk stratification from routine examinations such as (3D) echocardiography. The pipeline combines non-linear dimensionality reduction of deformation patterns and two multi-scale kernel regressions. Confidence in the diagnosis is assessed by a map of local uncertainties, which integrates plausible infarct locations generated from the space of reduced dimensionality. These concepts were tested on 500 synthetic cases generated from a realistic cardiac electromechanical model, and 108 pairs of 3D echocardiographic sequences and delayed-enhancement magnetic resonance images from real cases. Infarct prediction is made at a spatial resolution around 4 mm, more than 10 times smaller than the current diagnosis, made regionally. Our method is accurate, and significantly outperforms the clinically-used thresholding of the deformation patterns (on real data: sensitivity/specificity of 0.828/0.804, area under the curve: 0.909 versus 0.742 for the most predictive strain component). Uncertainty adds value to refine the diagnosis and eventually re-examine suspicious cases.

show abstract

Automated Identification of Infarcted Myocardium Tissue Characterization Using Ultrasound Images: A Review

Cited by 29 publications

References 103 publications

A novel myocardium segmentation approach based on neutrosophic active contour model

A novel myocardium segmentation approach based on neutrosophic active contour model

Imaging the Cardiac Extracellular Matrix

Infarct Localization From Myocardial Deformation: Prediction and Uncertainty Quantification by Regression From a Low-Dimensional Space

Contact Info

Product

Resources

About