[KongchangAI]
Paper

OpDis-PS

A diffusion posterior sampling method for electrocardiographic imaging (ECGI) that explicitly models signal-dependent operator mismatch through a learnable module and corrects the forward operator, improving reconstruction accuracy for ill-posed inverse problems.

Timeline (last 90 days)

Nov 16

OpDis-PS is a diffusion posterior sampler that explicitly models the dependence between operator mismatch and the signal.

Unverified50%
Nov 16

OpDis-PS captures the mapping between mismatch and the cardiac signal through a learned module and performs posterior sampling using the corrected operator.

Unverified50%
Nov 16

OpDis-PS uses a fixed prior under all operator conditions, avoiding retraining the prior for different conditions.

Unverified50%
Nov 16

Under two mismatch conditions—lung conductivity variation and an additionally added subcutaneous fat layer—OpDis-PS achieves better reconstruction accuracy than classical regularization methods and learned predictors.

Unverified50%
Nov 16

OpDis-PS achieves the largest performance improvement on held-out cardiac pathology data.

Unverified50%
Nov 16

Current OpDis-PS research is still limited to simulated data, and validation on real clinical data is the key next step.

Unverified50%
Nov 16

OpDis-PS's strategy of "fixed prior, corrected operator" can lower the computational and data barriers to clinical deployment.

Unverified50%
Nov 16

The OpDis-PS framework can be extended to other imaging modalities that require posterior sampling, such as EEG source localization and electrical impedance tomography, and other inverse problems with model errors.

Unverified50%

All Facts (8)

Source Articles