{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129604"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129604","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Improving medical report generation and evaluation through prompt engineering","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","abstract_has_math":false,"creators":["Li, Chenhao"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Kindratenko, Volodymyr"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-05","date_published":"2025-05-05","updated_at":"2026-07-22T22:25:05Z","subjects":["Medical Report Generation","Medical Report Evaluation","Prompt Engineering","Vision Language Model"],"languages":["en","eng"],"rights":["Copyright 2025 Chenhao Li"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129604","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kindratenko, Volodymyr"]},{"key":"dc:creator","label":"Author","values":["Li, Chenhao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-05-05","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Medical Report Generation","Medical Report Evaluation","Prompt Engineering","Vision Language Model"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Chenhao Li"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129604"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","The student, Chenhao Li, accepted the attached license on 2025-04-29 at 12:51.","The student, Chenhao Li, submitted this Thesis for approval on 2025-04-29 at 13:03.","This Thesis was approved for publication on 2025-05-05 at 12:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22086 on 2025-10-19 at 19:16:42","The advancement of vision language models (VLMs) has opened new avenues for automating complex clinical tasks such as medical report generation. However, challenges remain in generating clinically accurate and detailed reports and in evaluating them effectively. Our work investigates the role of prompt engineering in improving both the generation and evaluation of medical reports. We make three main contributions. First, we analyze the effect of various prompting strategies on the performance of different VLMs, including GPT-4o mini, LLaMA 11B, and LLaVA-Med. We introduce a structured prompt design based on clinically relevant anatomical checkpoints that significantly improve reports coherence and clinical fidelity. Second, we propose a novel LLM evaluation strategy that uses checkpoints to anchor the assessment of generated reports, providing an interpretable and clinically meaningful metric. Third, we explore two integrated frameworks that combine generation and evaluation, enabling iterative improvement through example-based and self-supervised prompt optimization. Experimental results on the CT-RATE dataset demonstrate that prompt engineering can substantially increase both the quality and the evaluability of medical reports. Our findings highlight the potential of prompt-based approaches as efficient and scalable alternatives to fine-tuning, bridging the gap between general-purpose models and specialized clinical applications."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Improving medical report generation and evaluation through prompt engineering"]}]}],"canonical_facts":{"dc:contributor":["Kindratenko, Volodymyr"],"dc:creator":["Li, Chenhao"],"dc:date":["2025-05-05","2025-05"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","The student, Chenhao Li, accepted the attached license on 2025-04-29 at 12:51.","The student, Chenhao Li, submitted this Thesis for approval on 2025-04-29 at 13:03.","This Thesis was approved for publication on 2025-05-05 at 12:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22086 on 2025-10-19 at 19:16:42","The advancement of vision language models (VLMs) has opened new avenues for automating complex clinical tasks such as medical report generation. However, challenges remain in generating clinically accurate and detailed reports and in evaluating them effectively. Our work investigates the role of prompt engineering in improving both the generation and evaluation of medical reports. We make three main contributions. First, we analyze the effect of various prompting strategies on the performance of different VLMs, including GPT-4o mini, LLaMA 11B, and LLaVA-Med. We introduce a structured prompt design based on clinically relevant anatomical checkpoints that significantly improve reports coherence and clinical fidelity. Second, we propose a novel LLM evaluation strategy that uses checkpoints to anchor the assessment of generated reports, providing an interpretable and clinically meaningful metric. Third, we explore two integrated frameworks that combine generation and evaluation, enabling iterative improvement through example-based and self-supervised prompt optimization. Experimental results on the CT-RATE dataset demonstrate that prompt engineering can substantially increase both the quality and the evaluability of medical reports. Our findings highlight the potential of prompt-based approaches as efficient and scalable alternatives to fine-tuning, bridging the gap between general-purpose models and specialized clinical applications."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129604"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Chenhao Li"],"dc:subject":["Medical Report Generation","Medical Report Evaluation","Prompt Engineering","Vision Language Model"],"dc:title":["Improving medical report generation and evaluation through prompt engineering"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:05Z"}