{"id":{"repo_id":"carleton","oai_identifier":"oai:carleton.scholaris.ca:20.500.14718/41340"},"canonical_url":"https://search.dev.ndltd.org/etd/carleton/oai:carleton.scholaris.ca:20.500.14718/41340","repository":{"repo_id":"carleton","name":"Carleton University","base_url":"https://carleton.scholaris.ca/server/oai/request"},"display":{"title":"Investigation of Machine-Learning Techniques for Pulmonary Artery Pressure Estimation from Electrical Impedance Tomography Images","abstract":"Pulmonary artery pressure (PAP) is measured for the diagnosis and monitoring of pathologies such as congestive heart failure. Unfortunately, current modalities used for PAP measurements have disadvantages which reduce their use. One proposal to address these issues is the measurement of PAP using a continuous and non-invasive imaging modality - electrical impedance tomography (EIT). Previous work used a model-based algorithm relying on the known association between thoracic conductivity changes and PAP. This thesis attempted to improve these results by predicting PAP using neural networks (NN). Multiple NN architectures were trained and tested on a dataset of eight cardiac failure patients, and their prediction methodologies were analyzed. The resulting NN models performed well on seen patients, but failed to generalize well on unseen patients. The results present the possibility that NNs may be able to predict PAP given a more expansive dataset.","abstract_html":"Pulmonary artery pressure (PAP) is measured for the diagnosis and monitoring of pathologies such as congestive heart failure. Unfortunately, current modalities used for PAP measurements have disadvantages which reduce their use. One proposal to address these issues is the measurement of PAP using a continuous and non-invasive imaging modality - electrical impedance tomography (EIT). Previous work used a model-based algorithm relying on the known association between thoracic conductivity changes and PAP. This thesis attempted to improve these results by predicting PAP using neural networks (NN). Multiple NN architectures were trained and tested on a dataset of eight cardiac failure patients, and their prediction methodologies were analyzed. The resulting NN models performed well on seen patients, but failed to generalize well on unseen patients. The results present the possibility that NNs may be able to predict PAP given a more expansive dataset.","abstract_has_math":false,"creators":["Fuller, Zachary Flynn"],"institution":"Carleton University","degree_name":"Master of Applied Science (M.App.Sc.)","degree_level":"Master's","degree_discipline":"Engineering, Biomedical","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-24T01:34:34Z","subjects":[],"languages":["en"],"rights":["Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2024-15860"],"render_values":[{"text":"10.22215/etd/2024-15860","href":"https://doi.org/10.22215/etd/2024-15860","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14718/41340","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Fuller, Zachary Flynn"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-04-08T20:17:14Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-04-08T20:17:14Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["Carleton University"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering, Biomedical"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Applied Science (M.App.Sc.)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2024-15860"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14718/41340"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Pulmonary artery pressure (PAP) is measured for the diagnosis and monitoring of pathologies such as congestive heart failure. Unfortunately, current modalities used for PAP measurements have disadvantages which reduce their use. One proposal to address these issues is the measurement of PAP using a continuous and non-invasive imaging modality - electrical impedance tomography (EIT). Previous work used a model-based algorithm relying on the known association between thoracic conductivity changes and PAP. This thesis attempted to improve these results by predicting PAP using neural networks (NN). Multiple NN architectures were trained and tested on a dataset of eight cardiac failure patients, and their prediction methodologies were analyzed. The resulting NN models performed well on seen patients, but failed to generalize well on unseen patients. The results present the possibility that NNs may be able to predict PAP given a more expansive dataset."]},{"key":"dc:title","label":"Title","values":["Investigation of Machine-Learning Techniques for Pulmonary Artery Pressure Estimation from Electrical Impedance Tomography Images"]}]}],"canonical_facts":{"dc:creator":["Fuller, Zachary Flynn"],"dc:date.accessioned":["2025-04-08T20:17:14Z"],"dc:date.available":["2025-04-08T20:17:14Z"],"dc:date.issued":["2024"],"dc:description.abstract":["Pulmonary artery pressure (PAP) is measured for the diagnosis and monitoring of pathologies such as congestive heart failure. Unfortunately, current modalities used for PAP measurements have disadvantages which reduce their use. One proposal to address these issues is the measurement of PAP using a continuous and non-invasive imaging modality - electrical impedance tomography (EIT). Previous work used a model-based algorithm relying on the known association between thoracic conductivity changes and PAP. This thesis attempted to improve these results by predicting PAP using neural networks (NN). Multiple NN architectures were trained and tested on a dataset of eight cardiac failure patients, and their prediction methodologies were analyzed. The resulting NN models performed well on seen patients, but failed to generalize well on unseen patients. The results present the possibility that NNs may be able to predict PAP given a more expansive dataset."],"dc:identifier.doi":["10.22215/etd/2024-15860"],"dc:identifier.uri":["https://hdl.handle.net/20.500.14718/41340"],"dc:language.iso":["en"],"dc:publisher":["Carleton University"],"dc:rights":["Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"dc:title":["Investigation of Machine-Learning Techniques for Pulmonary Artery Pressure Estimation from Electrical Impedance Tomography Images"],"dc:type":["thesis"],"thesis:degree_discipline":["Engineering, Biomedical"],"thesis:degree_level":["Master's"],"thesis:degree_name":["Master of Applied Science (M.App.Sc.)"]},"updated_at":"2026-07-24T01:34:34Z"}