{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/137642"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/137642","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Towards Interpretable AI for Longitudinal Disease Monitoring and Clinical Reporting from Chest X-Rays","abstract":"Chest radiography (CXR) plays a pivotal role in diagnostic imaging for monitoring disease progression and evaluating treatment effectiveness. Despite notable advancements in machine learning, disease progression monitoring remains relatively underexplored. Challenges arise from the specificity of biomarkers that detect change, which vary in their mechanisms, manifestations, and progression rates across diseases, alongside individual variability in response to illness and the complexity of incorporating multimodal longitudinal data. Monitoring disease progression in chest imaging involves intricate tasks, such as anatomical motion estimation and image registration, which require the spatial alignment of sequential X-rays and modeling temporal dynamics. This thesis addresses these challenges by harnessing artificial intelligence techniques for effective disease progression monitoring using non-co-registered sequential CXRs. We investigate three research directions: 1) learning a disease progression model with local and global information, 2) explainable hierarchical learnable differences for disease progression monitoring, and 3) retrieval-augmented longitudinal disease report generation. The overarching goal of this thesis is to develop models that not only accurately track disease progression but also provide interpretable insights about the patient's condition. The three directions in this thesis form a unified strategy for building interpretable, temporally aware AI models that enhance disease monitoring and reporting. Together, these contributions advance early detection and informed treatment decisions, with the potential to significantly improve patient outcomes at scale.","abstract_html":"Chest radiography (CXR) plays a pivotal role in diagnostic imaging for monitoring disease progression and evaluating treatment effectiveness. Despite notable advancements in machine learning, disease progression monitoring remains relatively underexplored. Challenges arise from the specificity of biomarkers that detect change, which vary in their mechanisms, manifestations, and progression rates across diseases, alongside individual variability in response to illness and the complexity of incorporating multimodal longitudinal data. Monitoring disease progression in chest imaging involves intricate tasks, such as anatomical motion estimation and image registration, which require the spatial alignment of sequential X-rays and modeling temporal dynamics. This thesis addresses these challenges by harnessing artificial intelligence techniques for effective disease progression monitoring using non-co-registered sequential CXRs. We investigate three research directions: 1) learning a disease progression model with local and global information, 2) explainable hierarchical learnable differences for disease progression monitoring, and 3) retrieval-augmented longitudinal disease report generation. The overarching goal of this thesis is to develop models that not only accurately track disease progression but also provide interpretable insights about the patient's condition. The three directions in this thesis form a unified strategy for building interpretable, temporally aware AI models that enhance disease monitoring and reporting. Together, these contributions advance early detection and informed treatment decisions, with the potential to significantly improve patient outcomes at scale.","abstract_has_math":false,"creators":["Madu, Amarachi Blessing"],"institution":"Virginia Tech","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Computer Science & Applications","degree_department":"Computer Science and#38; Applications","school":null,"contributors":[],"advisors":[],"committee_chairs":["Lourentzou, Ismini"],"committee_members":["Moradi, Mehdi","Reddy, Chandan K.","Zhang, Liqing","Ramakrishnan, Narendran"],"year":2025,"date_issued":"2025-09-08","date_published":"2025-09-08","updated_at":"2026-07-22T22:19:15Z","subjects":["Medical Imaging","Disease Progression Monitoring","Chest X-Rays","Vision Transformers","Longitudinal Medical Imaging","Explainable AI in Healthcare"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44418"],"render_values":[{"text":"vt_gsexam:44418","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/137642","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Lourentzou, Ismini"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Moradi, Mehdi","Reddy, Chandan K.","Zhang, Liqing","Ramakrishnan, Narendran"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science and#38; Applications"]},{"key":"dc:creator","label":"Author","values":["Madu, Amarachi Blessing"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-09T08:00:40Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-09T08:00:40Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-09-08"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science & Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Medical Imaging","Disease Progression Monitoring","Chest X-Rays","Vision Transformers","Longitudinal Medical Imaging","Explainable AI in Healthcare"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44418"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/137642"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Chest radiography (CXR) plays a pivotal role in diagnostic imaging for monitoring disease progression and evaluating treatment effectiveness. Despite notable advancements in machine learning, disease progression monitoring remains relatively underexplored. Challenges arise from the specificity of biomarkers that detect change, which vary in their mechanisms, manifestations, and progression rates across diseases, alongside individual variability in response to illness and the complexity of incorporating multimodal longitudinal data. Monitoring disease progression in chest imaging involves intricate tasks, such as anatomical motion estimation and image registration, which require the spatial alignment of sequential X-rays and modeling temporal dynamics. This thesis addresses these challenges by harnessing artificial intelligence techniques for effective disease progression monitoring using non-co-registered sequential CXRs. We investigate three research directions: 1) learning a disease progression model with local and global information, 2) explainable hierarchical learnable differences for disease progression monitoring, and 3) retrieval-augmented longitudinal disease report generation. The overarching goal of this thesis is to develop models that not only accurately track disease progression but also provide interpretable insights about the patient's condition. The three directions in this thesis form a unified strategy for building interpretable, temporally aware AI models that enhance disease monitoring and reporting. Together, these contributions advance early detection and informed treatment decisions, with the potential to significantly improve patient outcomes at scale."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Chest X-rays (CXRs) are among the most common tools clinicians use to detect and monitor chest diseases, such as infections and heart conditions. However, comparing past and present X-rays to assess how a disease evolves over time remains time-consuming, increasing the risk of delayed diagnosis or treatment, especially in regions with radiologist shortages. This can lead to poor disease management if conditions are not detected early or if progression is inadequately monitored. Detecting change is inherently challenging: disease progression is patient-specific, often subtle, and further complicated when multiple data types, such as CXRs and reports, must be integrated. This thesis explores artificial intelligence (AI) methods to support clinicians in monitoring disease progression more efficiently and effectively. It focuses on three directions: (1) learning disease progression models that capture both local and global information, (2) developing explainable, hierarchical approaches for detecting clinically meaningful differences, and (3) improving report generation to reflect disease progression and patient history. The goal is to build reliable, interpretable tools that enable earlier diagnosis, better treatment decisions, and improved patient care. By designing AI systems that reason about a patient's condition over time, this work aims to advance clinical practice and improve medical outcomes."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Towards Interpretable AI for Longitudinal Disease Monitoring and Clinical Reporting from Chest X-Rays"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Lourentzou, Ismini"],"dc:contributor.committeemember":["Moradi, Mehdi","Reddy, Chandan K.","Zhang, Liqing","Ramakrishnan, Narendran"],"dc:contributor.department":["Computer Science and#38; Applications"],"dc:creator":["Madu, Amarachi Blessing"],"dc:date.accessioned":["2025-09-09T08:00:40Z"],"dc:date.available":["2025-09-09T08:00:40Z"],"dc:date.issued":["2025-09-08"],"dc:description.abstract":["Chest radiography (CXR) plays a pivotal role in diagnostic imaging for monitoring disease progression and evaluating treatment effectiveness. Despite notable advancements in machine learning, disease progression monitoring remains relatively underexplored. Challenges arise from the specificity of biomarkers that detect change, which vary in their mechanisms, manifestations, and progression rates across diseases, alongside individual variability in response to illness and the complexity of incorporating multimodal longitudinal data. Monitoring disease progression in chest imaging involves intricate tasks, such as anatomical motion estimation and image registration, which require the spatial alignment of sequential X-rays and modeling temporal dynamics. This thesis addresses these challenges by harnessing artificial intelligence techniques for effective disease progression monitoring using non-co-registered sequential CXRs. We investigate three research directions: 1) learning a disease progression model with local and global information, 2) explainable hierarchical learnable differences for disease progression monitoring, and 3) retrieval-augmented longitudinal disease report generation. The overarching goal of this thesis is to develop models that not only accurately track disease progression but also provide interpretable insights about the patient's condition. The three directions in this thesis form a unified strategy for building interpretable, temporally aware AI models that enhance disease monitoring and reporting. Together, these contributions advance early detection and informed treatment decisions, with the potential to significantly improve patient outcomes at scale."],"dc:description.abstractgeneral":["Chest X-rays (CXRs) are among the most common tools clinicians use to detect and monitor chest diseases, such as infections and heart conditions. However, comparing past and present X-rays to assess how a disease evolves over time remains time-consuming, increasing the risk of delayed diagnosis or treatment, especially in regions with radiologist shortages. This can lead to poor disease management if conditions are not detected early or if progression is inadequately monitored. Detecting change is inherently challenging: disease progression is patient-specific, often subtle, and further complicated when multiple data types, such as CXRs and reports, must be integrated. This thesis explores artificial intelligence (AI) methods to support clinicians in monitoring disease progression more efficiently and effectively. It focuses on three directions: (1) learning disease progression models that capture both local and global information, (2) developing explainable, hierarchical approaches for detecting clinically meaningful differences, and (3) improving report generation to reflect disease progression and patient history. The goal is to build reliable, interpretable tools that enable earlier diagnosis, better treatment decisions, and improved patient care. By designing AI systems that reason about a patient's condition over time, this work aims to advance clinical practice and improve medical outcomes."],"dc:description.degree":["Doctor of Philosophy"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:44418"],"dc:identifier.uri":["https://hdl.handle.net/10919/137642"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Medical Imaging","Disease Progression Monitoring","Chest X-Rays","Vision Transformers","Longitudinal Medical Imaging","Explainable AI in Healthcare"],"dc:title":["Towards Interpretable AI for Longitudinal Disease Monitoring and Clinical Reporting from Chest X-Rays"],"dc:type":["Dissertation"],"thesis:degree_discipline":["Computer Science & Applications"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:15Z"}