Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical Mapping
Existing approaches to non-invasive electroanatomical mapping face a fundamental challenge: accurately representing the continuous propagation velocities crucial for cardiac arrhythmia localization. Current methods either sacrifice precision by using discrete delays or require computationally intens...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11078281/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839617267542786048 |
|---|---|
| author | Erik Engelhardt Johannes Hoffmann Moritz Boueke Lukas Elsner Marius Leye Norbert Frey Gerhard Schmidt |
| author_facet | Erik Engelhardt Johannes Hoffmann Moritz Boueke Lukas Elsner Marius Leye Norbert Frey Gerhard Schmidt |
| author_sort | Erik Engelhardt |
| collection | DOAJ |
| description | Existing approaches to non-invasive electroanatomical mapping face a fundamental challenge: accurately representing the continuous propagation velocities crucial for cardiac arrhythmia localization. Current methods either sacrifice precision by using discrete delays or require computationally intensive biophysical models that limit clinical applicability. We investigated interconnected all-pass filter networks as a novel middle ground that enables continuous, differentiable representation of cardiac propagation velocities while maintaining computational tractability. Through systematic analysis of these networks’ fundamental properties and scaling behavior, we demonstrate successful gradient-based optimization of propagation velocities in networks of up to 50 filters and 2D arrangements of <inline-formula> <tex-math notation="LaTeX">$5\times 5$ </tex-math></inline-formula> voxels using magnetocardiographic measurements, while identifying critical scaling challenges in more complex geometries. Our experiments establish that reliable convergence requires at least 32-48 magnetic sensors operating below a noise threshold of approximately <inline-formula> <tex-math notation="LaTeX">$\mathrm {7~pT/\sqrt {Hz}}$ </tex-math></inline-formula>. Runtime analysis shows linear computational scaling with system size, with GPU implementations achieving up to <inline-formula> <tex-math notation="LaTeX">$\mathrm {50 \times }$ </tex-math></inline-formula> acceleration over CPU versions, processing a realistic cardiac model with about 30000 voxels in under 5 s per epoch. These findings establish the theoretical feasibility of all-pass filter networks for cardiac propagation velocity modeling while identifying practical implementation requirements for clinical applications. This approach could reduce patient risks by eliminating invasive catheterization procedures and enable longitudinal studies and research applications not feasible with current invasive methods. |
| format | Article |
| id | doaj-art-023d51cd95e94046927e41dba173f29d |
| institution | Matheson Library |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-023d51cd95e94046927e41dba173f29d2025-07-24T23:01:43ZengIEEEIEEE Access2169-35362025-01-011312614712616610.1109/ACCESS.2025.358829311078281Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical MappingErik Engelhardt0https://orcid.org/0000-0002-7012-7707Johannes Hoffmann1https://orcid.org/0000-0001-8170-8147Moritz Boueke2https://orcid.org/0009-0002-7287-6397Lukas Elsner3Marius Leye4Norbert Frey5Gerhard Schmidt6https://orcid.org/0000-0002-6128-4831Department of Electrical and Information Engineering, Kiel University, Kiel, GermanyDepartment of Electrical and Information Engineering, Kiel University, Kiel, GermanyDepartment of Electrical and Information Engineering, Kiel University, Kiel, GermanyDepartment of Electrical and Information Engineering, Kiel University, Kiel, GermanyDepartment of Internal Medicine III, University Medical Center Heidelberg, Heidelberg, GermanyDepartment of Internal Medicine III, University Medical Center Heidelberg, Heidelberg, GermanyDepartment of Electrical and Information Engineering, Kiel University, Kiel, GermanyExisting approaches to non-invasive electroanatomical mapping face a fundamental challenge: accurately representing the continuous propagation velocities crucial for cardiac arrhythmia localization. Current methods either sacrifice precision by using discrete delays or require computationally intensive biophysical models that limit clinical applicability. We investigated interconnected all-pass filter networks as a novel middle ground that enables continuous, differentiable representation of cardiac propagation velocities while maintaining computational tractability. Through systematic analysis of these networks’ fundamental properties and scaling behavior, we demonstrate successful gradient-based optimization of propagation velocities in networks of up to 50 filters and 2D arrangements of <inline-formula> <tex-math notation="LaTeX">$5\times 5$ </tex-math></inline-formula> voxels using magnetocardiographic measurements, while identifying critical scaling challenges in more complex geometries. Our experiments establish that reliable convergence requires at least 32-48 magnetic sensors operating below a noise threshold of approximately <inline-formula> <tex-math notation="LaTeX">$\mathrm {7~pT/\sqrt {Hz}}$ </tex-math></inline-formula>. Runtime analysis shows linear computational scaling with system size, with GPU implementations achieving up to <inline-formula> <tex-math notation="LaTeX">$\mathrm {50 \times }$ </tex-math></inline-formula> acceleration over CPU versions, processing a realistic cardiac model with about 30000 voxels in under 5 s per epoch. These findings establish the theoretical feasibility of all-pass filter networks for cardiac propagation velocity modeling while identifying practical implementation requirements for clinical applications. This approach could reduce patient risks by eliminating invasive catheterization procedures and enable longitudinal studies and research applications not feasible with current invasive methods.https://ieeexplore.ieee.org/document/11078281/All-pass filter networksgradient descent optimizationcardiac propagation velocitynon-invasive electroanatomical mappingmagnetocardiographycomputational modeling |
| spellingShingle | Erik Engelhardt Johannes Hoffmann Moritz Boueke Lukas Elsner Marius Leye Norbert Frey Gerhard Schmidt Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical Mapping IEEE Access All-pass filter networks gradient descent optimization cardiac propagation velocity non-invasive electroanatomical mapping magnetocardiography computational modeling |
| title | Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical Mapping |
| title_full | Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical Mapping |
| title_fullStr | Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical Mapping |
| title_full_unstemmed | Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical Mapping |
| title_short | Gradient-Based Optimization of All-Pass Filter Networks for Non-Invasive Electroanatomical Mapping |
| title_sort | gradient based optimization of all pass filter networks for non invasive electroanatomical mapping |
| topic | All-pass filter networks gradient descent optimization cardiac propagation velocity non-invasive electroanatomical mapping magnetocardiography computational modeling |
| url | https://ieeexplore.ieee.org/document/11078281/ |
| work_keys_str_mv | AT erikengelhardt gradientbasedoptimizationofallpassfilternetworksfornoninvasiveelectroanatomicalmapping AT johanneshoffmann gradientbasedoptimizationofallpassfilternetworksfornoninvasiveelectroanatomicalmapping AT moritzboueke gradientbasedoptimizationofallpassfilternetworksfornoninvasiveelectroanatomicalmapping AT lukaselsner gradientbasedoptimizationofallpassfilternetworksfornoninvasiveelectroanatomicalmapping AT mariusleye gradientbasedoptimizationofallpassfilternetworksfornoninvasiveelectroanatomicalmapping AT norbertfrey gradientbasedoptimizationofallpassfilternetworksfornoninvasiveelectroanatomicalmapping AT gerhardschmidt gradientbasedoptimizationofallpassfilternetworksfornoninvasiveelectroanatomicalmapping |