Deep Adaptive Electrocardiographic Imaging with Generative Forward Model for Error Reduction

Toloubidokhti, Maryam; Gyawali, Prashnna Kumar; Gharbia, Omar A.; Jiang, Xiajun; Font, Jaume Coll; Bergquist, Jake A; Zenger, Brian; Good, Wilson W.; Brooks, Dana H.; MacLeod, Rob S.; Wang, Linwei

doi:10.1007/978-3-030-78710-3_45

Cited by 2 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In controlled simulation experiments and invivo real data experiments, we demonstrate that the presented method allowed reduction of errors in the mechanistic forward operator and recognition of the sources of errors. Furthermore, we demonstrated that the presented method improved the accuracy of the reconstructed heart-surface potential, in comparison to DAECGI as described in [20].…”

Section: Introductionmentioning

confidence: 82%

“…We demonstrate this novel concept on the reconstruction of cardiac electrical potential from body surface potential [7,8]. A similar motivation was pursued in a previous work in this specific application (DAECGI) [20], where a conditional generative model was developed to learn the forward operator as a function of known geometry underlying the operator and an unknown latent variable. As a result, the generative model is not hybrid with the mechanistic forward operator, but mimics the mechanistic operator with a fully data-driven neural function of the input geometry.…”

Section: Introductionmentioning

confidence: 87%

“…Real Data : We evaluated the trained IMRE on human data samples of bodysurface recordings of two CRT patients [16,2], given the ground-truth of the pacing location. We compared the performance of IMRE with DAECGI [20], and the initial forward operators H i generated with SCIRun software.…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Interpretable Modeling and Reduction of Unknown Errors in Mechanistic Operators

Toloubidokhti

Kumar

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Prior knowledge about the imaging physics provides a mechanistic forward operator that plays an important role in image reconstruction, although myriad sources of possible errors in the operator could negatively impact the reconstruction solutions. In this work, we propose to embed the traditional mechanistic forward operator inside a neural function, and focus on modeling and correcting its unknown errors in an interpretable manner. This is achieved by a conditional generative model that transforms a given mechanistic operator with unknown errors, arising from a latent space of self-organizing clusters of potential sources of error generation. Once learned, the generative model can be used in place of a fixed forward operator in any traditional optimizationbased reconstruction process where, together with the inverse solution, the error in prior mechanistic forward operator can be minimized and the potential source of error uncovered. We apply the presented method to the reconstruction of heart electrical potential from body surface potential. In controlled simulation experiments and in-vivo real data experiments, we demonstrate that the presented method allowed reduction of errors in the physics-based forward operator and thereby delivered inverse reconstruction of heart-surface potential with increased accuracy.

show abstract

Section: Introductionmentioning

confidence: 82%

Section: Introductionmentioning

confidence: 87%

See 1 more Smart Citation

Interpretable Modeling and Reduction of Unknown Errors in Mechanistic Operators

Toloubidokhti

Kumar

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…We and others have developed methods for correcting the heart position using augmented parameterizations of heart position; [2,3,12,13] ric accuracy is necessary to produce robust solutions. Although this study was limited to translations of heart position, extensions would be straightforward for additional positional parameters e.g., rotations.…”

Section: Discussionmentioning

confidence: 99%

Heart Position Uncertainty Quantification in the Inverse Problem of ECGI

Bergquist¹,

Rupp²,

Busatto³

et al. 2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Electrocardiographic imaging (ECGI) is a clinical and research tool for noninvasive diagnosis of cardiac electrical dysfunction. The position of the heart within the torso is both an input and common source of error in ECGI. Many studies have sought to improve cardiac localization accuracy, however, few have examined quantitatively the effects of uncertainty in the position of the heart within the torso. Recently developed uncertainty quantification (UQ) tools enable the robust application of UQ to ECGI reconstructions. In this study, we developed an ECGI formulation, which for the first time, directly incorporated uncertainty in the heart position. The result is an ECGI solution that is robust to variation in heart position. Using data from two Langendorff experimental preparations, each with 120 heartbeats distributed across three activation sequences, we found that as heart position uncertainty increased above ±10 mm, the solution quality of the ECGI degraded. However, even at large heart position uncertainty (±40 mm) our novel UQ-ECGI formulation produced reasonable solutions (root mean squared error < 1 mV, spatial correlation >0.6, temporal correlation >0.75).

show abstract

Deep Adaptive Electrocardiographic Imaging with Generative Forward Model for Error Reduction

Cited by 2 publications

References 15 publications

Interpretable Modeling and Reduction of Unknown Errors in Mechanistic Operators

Interpretable Modeling and Reduction of Unknown Errors in Mechanistic Operators

Heart Position Uncertainty Quantification in the Inverse Problem of ECGI

Contact Info

Product

Resources

About