Robust Image-Based Estimation of Cardiac Tissue Parameters and Their Uncertainty from Noisy Data

Neumann, Dominik; Mansi, Tommaso; Georgescu, Bogdan; Kamen, Ali; Kayvanpour, Elham; Amr, Ali; Sedaghat‐Hamedani, Farbod; Haas, Jan; Katus, Hugo A.; Meder, Benjamin; Hornegger, Joachim; Comanicìu, Dorin

doi:10.1007/978-3-319-10470-6_2

Cited by 17 publications

(21 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probabilistic methods were used on imaging and clinical data to estimate the tissue parameters required by computational cardiac models [19], [20]. The provided range of uncertainty may serve for a better evaluation of cardiac [21] or respiratory motion [22], or the confidence in a statistical shape model with partial observations [23].…”

Section: B Uncertainty In the Predictionmentioning

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

Section: B Uncertainty In the Predictionmentioning

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

show abstract

“…In opposition to past methodologies, this strategy does not depend on approximations of the forward model (resp. back likelihood) utilizing diminished request models [53], [54] (resp. meager lattice strategies [55]).…”

Section: Introductionmentioning

confidence: 99%

A Survey on Medical Image Segmentation Methods with Different Modalitites

Sumithra¹,

Malathi²

2018

IJERT

View full text Add to dashboard Cite

-This paper shows a review on the offered methods for segmentation of brain tumor magnetic resonance imaging (MRI) and computed tomography (CT) images. Segmentation of brain MRI and CT images are broadly used as a preprocessing, for research that inhabit study and mechanization, in the domain of medical image processing. MRI and CT images segmentation is difficult job because of the same characteristics between hard and soft group of muscle anatomy in the brain image. Also the many parts of identical space present in an image differentiate with the image partition and direction. The selection of an suitable type for segmentation that is build up on the image featue. This review has been done in the point of view of authorize the mixture of a segmentation type for MRI and CT images. This review is differentiated based on the methods processed in segmentation.

show abstract

“…The gradients necessary for these optimizations were calculated using direct differentiation or finite difference . More recent efforts include the use of global optimization methods: in particular, genetic algorithms, a Monte Carlo method, subplex algorithm, and parameter sweeps . Finally, reduced order unscented Kalman filtering has also been successfully applied as a data assimilation tool for patient‐specific model creation …”

Section: Introductionmentioning

confidence: 99%

High‐resolution data assimilation of cardiac mechanics applied to a dyssynchronous ventricle

Balaban

Finsberg

Odland

et al. 2017

Numer Methods Biomed Eng

View full text Add to dashboard Cite

The objective of this transformative action research project was to explore and develop sustainable methods to promote female empowerment through science education in rural, disadvantaged sectors of South Africa. In an attempt to achieve this we collaborated with local community members to develop and implement a contextualized science curriculum at a school in the aforementioned setting. As soon as the project was launched it became increasingly clear that although the ideology of 'empowerment through science education' seemed a promising venture, it could also be an extremely complex and often frustrating undertaking. This was especially true when working within an unfamiliar cultural setting. Numerous challenges, such as the lack of teacher motivation, malnutrition amongst the learners, and conflicts stemming from differences between the indigenous knowledge and the western concept of science, greatly impeded the delivery of quality education in the area. These challenges had to be addressed both in pedagogical and practical terms before any attempt towards libratory education could be made. This article sheds light on the complex inter-relationship between the human factor and the organizational and physical infrastructure at a school. It begins with a brief description of the local context and goes on to identify the theoretical underpinnings and chosen methodology for the project. The article concludes with a review of the complexities involved in possible attempts to initiate and foster educational and social transformations in a rural South African setting. We contend that it is essential to first be thoroughly familiar with the background, culture, and needs of any community before any attempts are made towards social justice.

show abstract

Robust Image-Based Estimation of Cardiac Tissue Parameters and Their Uncertainty from Noisy Data

Cited by 17 publications

References 14 publications

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

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

A Survey on Medical Image Segmentation Methods with Different Modalitites

High‐resolution data assimilation of cardiac mechanics applied to a dyssynchronous ventricle

Contact Info

Product

Resources

About