{"id":{"repo_id":"washington","oai_identifier":"oai:digital.lib.washington.edu:1773/53894"},"canonical_url":"https://search.dev.ndltd.org/etd/washington/oai:digital.lib.washington.edu:1773/53894","repository":{"repo_id":"washington","name":"University of Washington","base_url":"https://digital.lib.washington.edu/server/oai/request"},"display":{"title":"Universal Atrial Coordinate (UAC) for Wall Motion Deep Learning","abstract":"Atrial fibrillation (AF), the most common persistent arrhythmia, increases stroke risk through altered left atrial (LA) wall motion and blood stagnation in the left atrial appendage (LAA). Standard scores like CHA₂DS₂-VASc overlook patient-specific motion patterns, while AF's episodic nature and anatomical variability hinder consistent analysis. This thesis presents a standardized framework for LA wall motion analysis using 4D cardiac CT in both sinus rhythm (SR) and AF. LA geometries were segmented, temporally aligned via Coherent Point Drift (CPD) registration, and mapped to a 2D Universal Atrial Coordinate (UAC) system. Wall motion, quantified from Signed Distance Fields (SDF) and decomposed via fast Fourier transform (FFT), showed coordinated low-frequency contraction in SR and reduced amplitude with higher-frequency content in AF. The framework enables anatomy-independent motion comparison and has the potential to predict AF signatures using SR data alone.","abstract_html":"Atrial fibrillation (AF), the most common persistent arrhythmia, increases stroke risk through altered left atrial (LA) wall motion and blood stagnation in the left atrial appendage (LAA). Standard scores like CHA₂DS₂-VASc overlook patient-specific motion patterns, while AF's episodic nature and anatomical variability hinder consistent analysis. This thesis presents a standardized framework for LA wall motion analysis using 4D cardiac CT in both sinus rhythm (SR) and AF. LA geometries were segmented, temporally aligned via Coherent Point Drift (CPD) registration, and mapped to a 2D Universal Atrial Coordinate (UAC) system. Wall motion, quantified from Signed Distance Fields (SDF) and decomposed via fast Fourier transform (FFT), showed coordinated low-frequency contraction in SR and reduced amplitude with higher-frequency content in AF. The framework enables anatomy-independent motion comparison and has the potential to predict AF signatures using SR data alone.","abstract_has_math":false,"creators":["Gupta, Akshay"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Dabiri, Dana"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-10-02","date_published":"2025-10-02","updated_at":"2026-07-24T05:58:12Z","subjects":["Arrythmia","Atrial Fibrillaiton","Computational Fluid Dynamics","Left Atrium","Signed Distance Field","Sinus Rhythm","Mechanical engineering","Aerospace engineering","Biomedical engineering"],"languages":["en_US"],"rights":["CC BY"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1773/53894","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Dabiri, Dana"]},{"key":"dc:creator","label":"Author","values":["Gupta, Akshay"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-10-02T16:03:34Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-10-02"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Arrythmia","Atrial Fibrillaiton","Computational Fluid Dynamics","Left Atrium","Signed Distance Field","Sinus Rhythm","Mechanical engineering","Aerospace engineering","Biomedical engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["CC BY"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["Gupta_washington_0250O_28869.pdf"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1773/53894"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Master's)--University of Washington, 2025"]},{"key":"dc:description.abstract","label":"Abstract","values":["Atrial fibrillation (AF), the most common persistent arrhythmia, increases stroke risk through altered left atrial (LA) wall motion and blood stagnation in the left atrial appendage (LAA). Standard scores like CHA₂DS₂-VASc overlook patient-specific motion patterns, while AF's episodic nature and anatomical variability hinder consistent analysis. This thesis presents a standardized framework for LA wall motion analysis using 4D cardiac CT in both sinus rhythm (SR) and AF. LA geometries were segmented, temporally aligned via Coherent Point Drift (CPD) registration, and mapped to a 2D Universal Atrial Coordinate (UAC) system. Wall motion, quantified from Signed Distance Fields (SDF) and decomposed via fast Fourier transform (FFT), showed coordinated low-frequency contraction in SR and reduced amplitude with higher-frequency content in AF. The framework enables anatomy-independent motion comparison and has the potential to predict AF signatures using SR data alone."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Universal Atrial Coordinate (UAC) for Wall Motion Deep Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Dabiri, Dana"],"dc:creator":["Gupta, Akshay"],"dc:date.accessioned":["2025-10-02T16:03:34Z"],"dc:date.issued":["2025-10-02"],"dc:description":["Thesis (Master's)--University of Washington, 2025"],"dc:description.abstract":["Atrial fibrillation (AF), the most common persistent arrhythmia, increases stroke risk through altered left atrial (LA) wall motion and blood stagnation in the left atrial appendage (LAA). Standard scores like CHA₂DS₂-VASc overlook patient-specific motion patterns, while AF's episodic nature and anatomical variability hinder consistent analysis. This thesis presents a standardized framework for LA wall motion analysis using 4D cardiac CT in both sinus rhythm (SR) and AF. LA geometries were segmented, temporally aligned via Coherent Point Drift (CPD) registration, and mapped to a 2D Universal Atrial Coordinate (UAC) system. Wall motion, quantified from Signed Distance Fields (SDF) and decomposed via fast Fourier transform (FFT), showed coordinated low-frequency contraction in SR and reduced amplitude with higher-frequency content in AF. The framework enables anatomy-independent motion comparison and has the potential to predict AF signatures using SR data alone."],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["Gupta_washington_0250O_28869.pdf"],"dc:identifier.uri":["https://hdl.handle.net/1773/53894"],"dc:language.iso":["en_US"],"dc:rights":["CC BY"],"dc:subject":["Arrythmia","Atrial Fibrillaiton","Computational Fluid Dynamics","Left Atrium","Signed Distance Field","Sinus Rhythm","Mechanical engineering","Aerospace engineering","Biomedical engineering"],"dc:title":["Universal Atrial Coordinate (UAC) for Wall Motion Deep Learning"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T05:58:12Z"}