{"id":{"repo_id":"gatech","oai_identifier":"oai:repository.gatech.edu:1853/75095"},"canonical_url":"https://search.dev.ndltd.org/etd/gatech/oai:repository.gatech.edu:1853/75095","repository":{"repo_id":"gatech","name":"Georgia Tech","base_url":"https://repository.gatech.edu/server/oai/request"},"display":{"title":"Automated precision computational image analysis and applied machine learning for experimental and clinical hematology applications","abstract":"Hematology, the study of blood and blood disorders, is a broad field of science and medicine spanning research at the cellular level to clinical treatment for patient well-being. Imaging at all scales, ranging from microscopy to diagnostic scans of the body, represents one of the best methods to investigate salient features of fundamental biology and disease. The imaging data produced is information-rich, but hematology presents with specific issues that hinder analysis, including diverse cell populations, an emphasis on fluid flow, and importance of spatial relationships. Computational pipelines for image processing coupled with applied machine learning interpretation represent a solution by providing methods that balance high-throughput automation with precise, quantitative results. To this end, this work has developed a series of computational workflows to provide greater resolution in hematology research such that more detailed experimental conclusions can be made from imaging data. In aim 1, the open source, standalone software iCLOTS (interactive cellular assay labeled observation and tracking software) has been developed and utilized to draw novel conclusions about research at the cellular level, including in patient clinical samples. This software has been distributed to the greater hematology community via website https://www.iCLOTS.org/. Aim 2 explores features of disease risk and progression in magnetic resonance imaging of the cerebrovasculature of pediatric sickle cell disease patients. The results of this work provide new methodologies for applied image processing and machine learning in hematology research, and may contribute to precision medicine efforts.","abstract_html":"Hematology, the study of blood and blood disorders, is a broad field of science and medicine spanning research at the cellular level to clinical treatment for patient well-being. Imaging at all scales, ranging from microscopy to diagnostic scans of the body, represents one of the best methods to investigate salient features of fundamental biology and disease. The imaging data produced is information-rich, but hematology presents with specific issues that hinder analysis, including diverse cell populations, an emphasis on fluid flow, and importance of spatial relationships. Computational pipelines for image processing coupled with applied machine learning interpretation represent a solution by providing methods that balance high-throughput automation with precise, quantitative results. To this end, this work has developed a series of computational workflows to provide greater resolution in hematology research such that more detailed experimental conclusions can be made from imaging data. In aim 1, the open source, standalone software iCLOTS (interactive cellular assay labeled observation and tracking software) has been developed and utilized to draw novel conclusions about research at the cellular level, including in patient clinical samples. This software has been distributed to the greater hematology community via website https://www.iCLOTS.org/. Aim 2 explores features of disease risk and progression in magnetic resonance imaging of the cerebrovasculature of pediatric sickle cell disease patients. The results of this work provide new methodologies for applied image processing and machine learning in hematology research, and may contribute to precision medicine efforts.","abstract_has_math":false,"creators":["Fay, Meredith Ellen"],"institution":"Georgia Institute of Technology","degree_name":null,"degree_level":"Doctoral","degree_discipline":null,"degree_department":"Biomedical Engineering (Joint GT/Emory Department)","school":null,"contributors":[],"advisors":["Lam, Wilbur A."],"committee_chairs":[],"committee_members":["Dyer, Eva","Gutman, David","Mitchell, Cassie S.","Ware, Russell"],"year":2023,"date_issued":"2023-04-18","date_published":"2023-04-18","updated_at":"2026-07-27T19:50:35Z","subjects":["Image processing","machine learning","hematology","software engineering"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1853/75095","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lam, Wilbur A."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Dyer, Eva","Gutman, David","Mitchell, Cassie S.","Ware, Russell"]},{"key":"dc:contributor.department","label":"Department","values":["Biomedical Engineering (Joint GT/Emory Department)"]},{"key":"dc:creator","label":"Author","values":["Fay, Meredith Ellen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-05-23T19:17:15Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-05-23T19:17:15Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-04-18"]},{"key":"dc:publisher","label":"Institution","values":["Georgia Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Text"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Image processing","machine learning","hematology","software engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1853/75095"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Hematology, the study of blood and blood disorders, is a broad field of science and medicine spanning research at the cellular level to clinical treatment for patient well-being. Imaging at all scales, ranging from microscopy to diagnostic scans of the body, represents one of the best methods to investigate salient features of fundamental biology and disease. The imaging data produced is information-rich, but hematology presents with specific issues that hinder analysis, including diverse cell populations, an emphasis on fluid flow, and importance of spatial relationships. Computational pipelines for image processing coupled with applied machine learning interpretation represent a solution by providing methods that balance high-throughput automation with precise, quantitative results. To this end, this work has developed a series of computational workflows to provide greater resolution in hematology research such that more detailed experimental conclusions can be made from imaging data. In aim 1, the open source, standalone software iCLOTS (interactive cellular assay labeled observation and tracking software) has been developed and utilized to draw novel conclusions about research at the cellular level, including in patient clinical samples. This software has been distributed to the greater hematology community via website https://www.iCLOTS.org/. Aim 2 explores features of disease risk and progression in magnetic resonance imaging of the cerebrovasculature of pediatric sickle cell disease patients. The results of this work provide new methodologies for applied image processing and machine learning in hematology research, and may contribute to precision medicine efforts."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Automated precision computational image analysis and applied machine learning for experimental and clinical hematology applications"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lam, Wilbur A."],"dc:contributor.committeemember":["Dyer, Eva","Gutman, David","Mitchell, Cassie S.","Ware, Russell"],"dc:contributor.department":["Biomedical Engineering (Joint GT/Emory Department)"],"dc:creator":["Fay, Meredith Ellen"],"dc:date.accessioned":["2024-05-23T19:17:15Z"],"dc:date.available":["2024-05-23T19:17:15Z"],"dc:date.issued":["2023-04-18"],"dc:description.abstract":["Hematology, the study of blood and blood disorders, is a broad field of science and medicine spanning research at the cellular level to clinical treatment for patient well-being. Imaging at all scales, ranging from microscopy to diagnostic scans of the body, represents one of the best methods to investigate salient features of fundamental biology and disease. The imaging data produced is information-rich, but hematology presents with specific issues that hinder analysis, including diverse cell populations, an emphasis on fluid flow, and importance of spatial relationships. Computational pipelines for image processing coupled with applied machine learning interpretation represent a solution by providing methods that balance high-throughput automation with precise, quantitative results. To this end, this work has developed a series of computational workflows to provide greater resolution in hematology research such that more detailed experimental conclusions can be made from imaging data. In aim 1, the open source, standalone software iCLOTS (interactive cellular assay labeled observation and tracking software) has been developed and utilized to draw novel conclusions about research at the cellular level, including in patient clinical samples. This software has been distributed to the greater hematology community via website https://www.iCLOTS.org/. Aim 2 explores features of disease risk and progression in magnetic resonance imaging of the cerebrovasculature of pediatric sickle cell disease patients. The results of this work provide new methodologies for applied image processing and machine learning in hematology research, and may contribute to precision medicine efforts."],"dc:description.degree":["Ph.D."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/1853/75095"],"dc:language.iso":["en_US"],"dc:publisher":["Georgia Institute of Technology"],"dc:subject":["Image processing","machine learning","hematology","software engineering"],"dc:title":["Automated precision computational image analysis and applied machine learning for experimental and clinical hematology applications"],"dc:type":["Text"],"thesis:degree_level":["Doctoral"]},"updated_at":"2026-07-27T19:50:35Z"}