{"id":{"repo_id":"utswmed","oai_identifier":"oai:utswmed-ir.tdl.org:2152.5/10820"},"canonical_url":"https://search.dev.ndltd.org/etd/utswmed/oai:utswmed-ir.tdl.org:2152.5/10820","repository":{"repo_id":"utswmed","name":"University of Texas Southwestern Medical Center","base_url":"https://utswmed-ir.tdl.org/server/oai/request"},"display":{"title":"Intelligent Automatic Treatment Planning for Radiation Therapy","abstract":"Radiation therapy (RT) utilizes high-energy radiation to disrupt the DNA of cancer cells, impeding their repair and division, ultimately causing cancer cell death. The goal of RT is to spare radiation dose to healthy cells while maintaining the dose to cancer cells. Modern RT employs advanced delivery techniques such as Intensity-modulated radiotherapy (IMRT) and volumetric-modulated arc therapy (VMAT) to precisely shape the radiation dose highly conformal to the shape of the tumor while minimizing exposure to the surrounding organs. The success of these novel delivery techniques relies on treatment planning. The current human-centered planning workflow heavily relies on human input, causing issues related to plan quality variation, planning efficiency, and elevated labor costs, ultimately affecting clinical outcomes. To overcome these challenges, this dissertation research reports the development of a novel Intelligent Automatic Treatment Planning (IATP) framework that leverages artificial intelligence (AI) techniques to achieve human-like automatic treatment planning with high-quality deliverable plans that align with physicians' clinical preferences. Following a concise background introduction to RT treatment planning in Chapter 1, Chapter 2 presents a high-level overview of the IATP framework. The subsequent chapters elaborate on the development process, with Chapters 3 and 4 focusing on the construction of a Virtual Physician Network (VPN) to model physician preferences for plan approval in Stereotactic Body Radiation Therapy (SBRT) for prostate cancer and High-Dose-Rate Brachytherapy (HDRBT) for cervical cancer, respectively. Chapters 5 and 6 present the development of the Virtual Treatment Planner Network (VTPN), trained through Deep Reinforcement Learning (DRL) for RT treatment planning in prostate cancer and Head-and-Neck (H&N) cancer. Chapter 7 outlines a fully automated workflow by integrating the VTPN with VPN, yielding a Physician-Preference-guided Virtual Treatment Planner Network (PgVTPN) to achieve treatment planning for plans meeting both dosimetric requirements and physician's preference. Chapter 8 presents the work on employing conversational AI technologies to streamline human-machine communications in treatment planning. Finally, Chapter 9 concludes the dissertation and outlines future directions for the IATP framework. Additionally, Chapters 10 and 11 extend beyond the scope of IATP work to present several research projects related to the application of AI in medical imaging.","abstract_html":"Radiation therapy (RT) utilizes high-energy radiation to disrupt the DNA of cancer cells, impeding their repair and division, ultimately causing cancer cell death. The goal of RT is to spare radiation dose to healthy cells while maintaining the dose to cancer cells. Modern RT employs advanced delivery techniques such as Intensity-modulated radiotherapy (IMRT) and volumetric-modulated arc therapy (VMAT) to precisely shape the radiation dose highly conformal to the shape of the tumor while minimizing exposure to the surrounding organs. The success of these novel delivery techniques relies on treatment planning. The current human-centered planning workflow heavily relies on human input, causing issues related to plan quality variation, planning efficiency, and elevated labor costs, ultimately affecting clinical outcomes. To overcome these challenges, this dissertation research reports the development of a novel Intelligent Automatic Treatment Planning (IATP) framework that leverages artificial intelligence (AI) techniques to achieve human-like automatic treatment planning with high-quality deliverable plans that align with physicians' clinical preferences. Following a concise background introduction to RT treatment planning in Chapter 1, Chapter 2 presents a high-level overview of the IATP framework. The subsequent chapters elaborate on the development process, with Chapters 3 and 4 focusing on the construction of a Virtual Physician Network (VPN) to model physician preferences for plan approval in Stereotactic Body Radiation Therapy (SBRT) for prostate cancer and High-Dose-Rate Brachytherapy (HDRBT) for cervical cancer, respectively. Chapters 5 and 6 present the development of the Virtual Treatment Planner Network (VTPN), trained through Deep Reinforcement Learning (DRL) for RT treatment planning in prostate cancer and Head-and-Neck (H&N) cancer. Chapter 7 outlines a fully automated workflow by integrating the VTPN with VPN, yielding a Physician-Preference-guided Virtual Treatment Planner Network (PgVTPN) to achieve treatment planning for plans meeting both dosimetric requirements and physician's preference. Chapter 8 presents the work on employing conversational AI technologies to streamline human-machine communications in treatment planning. Finally, Chapter 9 concludes the dissertation and outlines future directions for the IATP framework. Additionally, Chapters 10 and 11 extend beyond the scope of IATP work to present several research projects related to the application of AI in medical imaging.","abstract_has_math":false,"creators":["Gao, Yin"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Nguyen, Dan","Jia, Xun","Jiang, Steve B.","Wang, Jing","Park, Yang Kyun"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-06-15T19:43:20Z","date_published":"2026-06-15T19:43:20Z","updated_at":"2026-07-24T05:52:13Z","subjects":["Artificial Intelligence","Automation","Deep Learning","Radiotherapy Planning, Computer-Assisted","Treatment Outcome"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["1596185265"],"render_values":[{"text":"1596185265","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2152.5/10820","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nguyen, Dan","Jia, Xun","Jiang, Steve B.","Wang, Jing","Park, Yang Kyun"]},{"key":"dc:creator","label":"Author","values":["Gao, Yin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-06-15T19:43:20Z","2024-05","May 2024"]},{"key":"dc:type","label":"Dc Type","values":["Thesis","text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence","Automation","Deep Learning","Radiotherapy Planning, Computer-Assisted","Treatment Outcome"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2152.5/10820","1596185265"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Radiation therapy (RT) utilizes high-energy radiation to disrupt the DNA of cancer cells, impeding their repair and division, ultimately causing cancer cell death. The goal of RT is to spare radiation dose to healthy cells while maintaining the dose to cancer cells. Modern RT employs advanced delivery techniques such as Intensity-modulated radiotherapy (IMRT) and volumetric-modulated arc therapy (VMAT) to precisely shape the radiation dose highly conformal to the shape of the tumor while minimizing exposure to the surrounding organs. The success of these novel delivery techniques relies on treatment planning. The current human-centered planning workflow heavily relies on human input, causing issues related to plan quality variation, planning efficiency, and elevated labor costs, ultimately affecting clinical outcomes. To overcome these challenges, this dissertation research reports the development of a novel Intelligent Automatic Treatment Planning (IATP) framework that leverages artificial intelligence (AI) techniques to achieve human-like automatic treatment planning with high-quality deliverable plans that align with physicians' clinical preferences. Following a concise background introduction to RT treatment planning in Chapter 1, Chapter 2 presents a high-level overview of the IATP framework. The subsequent chapters elaborate on the development process, with Chapters 3 and 4 focusing on the construction of a Virtual Physician Network (VPN) to model physician preferences for plan approval in Stereotactic Body Radiation Therapy (SBRT) for prostate cancer and High-Dose-Rate Brachytherapy (HDRBT) for cervical cancer, respectively. Chapters 5 and 6 present the development of the Virtual Treatment Planner Network (VTPN), trained through Deep Reinforcement Learning (DRL) for RT treatment planning in prostate cancer and Head-and-Neck (H&N) cancer. Chapter 7 outlines a fully automated workflow by integrating the VTPN with VPN, yielding a Physician-Preference-guided Virtual Treatment Planner Network (PgVTPN) to achieve treatment planning for plans meeting both dosimetric requirements and physician's preference. Chapter 8 presents the work on employing conversational AI technologies to streamline human-machine communications in treatment planning. Finally, Chapter 9 concludes the dissertation and outlines future directions for the IATP framework. Additionally, Chapters 10 and 11 extend beyond the scope of IATP work to present several research projects related to the application of AI in medical imaging."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Intelligent Automatic Treatment Planning for Radiation Therapy"]}]}],"canonical_facts":{"dc:contributor":["Nguyen, Dan","Jia, Xun","Jiang, Steve B.","Wang, Jing","Park, Yang Kyun"],"dc:creator":["Gao, Yin"],"dc:date":["2026-06-15T19:43:20Z","2024-05","May 2024"],"dc:description":["Radiation therapy (RT) utilizes high-energy radiation to disrupt the DNA of cancer cells, impeding their repair and division, ultimately causing cancer cell death. The goal of RT is to spare radiation dose to healthy cells while maintaining the dose to cancer cells. Modern RT employs advanced delivery techniques such as Intensity-modulated radiotherapy (IMRT) and volumetric-modulated arc therapy (VMAT) to precisely shape the radiation dose highly conformal to the shape of the tumor while minimizing exposure to the surrounding organs. The success of these novel delivery techniques relies on treatment planning. The current human-centered planning workflow heavily relies on human input, causing issues related to plan quality variation, planning efficiency, and elevated labor costs, ultimately affecting clinical outcomes. To overcome these challenges, this dissertation research reports the development of a novel Intelligent Automatic Treatment Planning (IATP) framework that leverages artificial intelligence (AI) techniques to achieve human-like automatic treatment planning with high-quality deliverable plans that align with physicians' clinical preferences. Following a concise background introduction to RT treatment planning in Chapter 1, Chapter 2 presents a high-level overview of the IATP framework. The subsequent chapters elaborate on the development process, with Chapters 3 and 4 focusing on the construction of a Virtual Physician Network (VPN) to model physician preferences for plan approval in Stereotactic Body Radiation Therapy (SBRT) for prostate cancer and High-Dose-Rate Brachytherapy (HDRBT) for cervical cancer, respectively. Chapters 5 and 6 present the development of the Virtual Treatment Planner Network (VTPN), trained through Deep Reinforcement Learning (DRL) for RT treatment planning in prostate cancer and Head-and-Neck (H&N) cancer. Chapter 7 outlines a fully automated workflow by integrating the VTPN with VPN, yielding a Physician-Preference-guided Virtual Treatment Planner Network (PgVTPN) to achieve treatment planning for plans meeting both dosimetric requirements and physician's preference. Chapter 8 presents the work on employing conversational AI technologies to streamline human-machine communications in treatment planning. Finally, Chapter 9 concludes the dissertation and outlines future directions for the IATP framework. Additionally, Chapters 10 and 11 extend beyond the scope of IATP work to present several research projects related to the application of AI in medical imaging."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2152.5/10820","1596185265"],"dc:language":["en"],"dc:subject":["Artificial Intelligence","Automation","Deep Learning","Radiotherapy Planning, Computer-Assisted","Treatment Outcome"],"dc:title":["Intelligent Automatic Treatment Planning for Radiation Therapy"],"dc:type":["Thesis","text"]},"updated_at":"2026-07-24T05:52:13Z"}