{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53174"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53174","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"LEARNING-BASED SAMPLING AND RECONSTRUCTION METHODS FOR ACCELERATED MRI AND X-RAY CT","abstract":"Thesis (Ph.D.)--Michigan State University. Computational Mathematics, Science and Engineering - Doctor of Philosophy, 2026","abstract_html":"Thesis (Ph.D.)--Michigan State University. Computational Mathematics, Science and Engineering - Doctor of Philosophy, 2026","abstract_has_math":false,"creators":["Gautam, Siddhant"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Ravishankar, Saiprasad"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:41Z","subjects":["Electrical engineering"],"languages":["eng"],"rights":["Attribution 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53174","local:Gautam_grad.msu_0128D_22214"],"render_values":[{"text":"etd:53174","href":null,"code":true},{"text":"local:Gautam_grad.msu_0128D_22214","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/b6zr-e475","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/b6zr-e475","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_53174","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ravishankar, Saiprasad"]},{"key":"dc:creator","label":"Author","values":["Gautam, Siddhant"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53174","local:Gautam_grad.msu_0128D_22214","https://doi.org/doi:10.25335/b6zr-e475"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Computational Mathematics, Science and Engineering - Doctor of Philosophy, 2026","Modern medical imaging systems such as magnetic resonance imaging (MRI) and X-ray computed tomography (CT) are essential for non-invasive visualization of anatomical structures and dynamic physiological processes. However, these imaging modalities are fundamentally limited by acquisition speed, measurement corruption, and computational reconstruction challenges. In this thesis, we develop learning-based approaches for improved imaging with a focus on adaptive acquisition and robust reconstruction. We propose scan-adaptive MRI undersampling techniques that tailor sampling patterns to individual scans rather than relying on fixed or population-based strategies. For static imaging, we introduce a framework for learning scan-specific Cartesian sampling patterns using a neighbor-based optimization approach. This framework is extended to dynamic MRI by developing efficient sampling optimization techniques and spatiotemporal reconstruction methods. In addition, we investigate robust feature learning methods for dynamic X-ray tomography under unknown noise and scatter corruption. These methods leverage deep learning to improve reconstruction quality by learning representations that are resilient to measurement imperfections. Overall, this thesis demonstrates that adaptive sampling and learning-based reconstruction can significantly improve imaging performance across multiple modalities.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (134 p.) : ill."]},{"key":"dc:title","label":"Title","values":["LEARNING-BASED SAMPLING AND RECONSTRUCTION METHODS FOR ACCELERATED MRI AND X-RAY CT"]}]}],"canonical_facts":{"dc:contributor":["Ravishankar, Saiprasad"],"dc:creator":["Gautam, Siddhant"],"dc:date":["2026"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Computational Mathematics, Science and Engineering - Doctor of Philosophy, 2026","Modern medical imaging systems such as magnetic resonance imaging (MRI) and X-ray computed tomography (CT) are essential for non-invasive visualization of anatomical structures and dynamic physiological processes. However, these imaging modalities are fundamentally limited by acquisition speed, measurement corruption, and computational reconstruction challenges. In this thesis, we develop learning-based approaches for improved imaging with a focus on adaptive acquisition and robust reconstruction. We propose scan-adaptive MRI undersampling techniques that tailor sampling patterns to individual scans rather than relying on fixed or population-based strategies. For static imaging, we introduce a framework for learning scan-specific Cartesian sampling patterns using a neighbor-based optimization approach. This framework is extended to dynamic MRI by developing efficient sampling optimization techniques and spatiotemporal reconstruction methods. In addition, we investigate robust feature learning methods for dynamic X-ray tomography under unknown noise and scatter corruption. These methods leverage deep learning to improve reconstruction quality by learning representations that are resilient to measurement imperfections. Overall, this thesis demonstrates that adaptive sampling and learning-based reconstruction can significantly improve imaging performance across multiple modalities.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (134 p.) : ill."],"dc:identifier":["etd:53174","local:Gautam_grad.msu_0128D_22214","https://doi.org/doi:10.25335/b6zr-e475"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution 4.0 International"],"dc:subject":["Electrical engineering"],"dc:title":["LEARNING-BASED SAMPLING AND RECONSTRUCTION METHODS FOR ACCELERATED MRI AND X-RAY CT"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:41Z"}