ECG Inverse Problem

Okamoto, Yoshiwo; He, Bin

doi:10.1002/9780471740360.ebs0654

Cited by 2 publications

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 2: Build "coefficient" layer and "merge" layer to obtain matrix B by and build "coefficient" layer and "merge" layer to obtain the matrix U by . Build the "thresholds" layer to update this layer's output by (7). Step 3: Repeat step2 until the corresponding number of iterations Output: Start training and adjust T, learning step, epoch size, batch-size and other parameters.…”

Section: Ista-net Modelmentioning

confidence: 99%

“…In this paper, a neural network is built based on ISTA algorithm. The torso volume conductor model is used as a part of the neural network module to ensure the reliability of the results and the neural network method is used to converge the parameters [7]. The experimental result shows that it has a significant effect on the cardiac potential reconstruction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New ISTA-net Solution to Inverse Problem of Electrocardiology

Wang¹,

Wei-qi²,

Liu³

2019

Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)

View full text Add to dashboard Cite

In this paper, we combined the traditional ISTA approach with deep learning, transferred the application domain from image inverse problem to ECG inverse problem because of its excellent performance to propose a new ISTA-net method to solve the inverse problem of ECG. The proposed method has quick convergence speed, steady performance and good extend capability. We created the ISTA-net algorithm model based on the ECG physical model, and transformed it into a neural network structure to achieve automatic parameter selection and more accurate result. We use a real human model on the ECGsim software to obtain the simulated potentials on the cardiac surface and body surface to train our model. The result of our experiment confirms that the proposed method has a better performance in reconstructing epicardial surface potentials distribution compared with the common regularization method like TTLS, Tikhonov, TSVD method.

show abstract

Section: Ista-net Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%