{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/144486"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/144486","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Multi-Dimensional Evaluation Metrics for Chest X-Ray Reports","abstract":"In the past few years, there has been abundant research in using machine learning to generate high quality radiology reports using the large MIMIC-CXR chest x-ray dataset. However, there has been little work focused on evaluating the quality of generated reports from a clinical perspective, where accuracy is the most important factor. Current evaluation metrics evaluate reports in one dimension. This work proposes the use of multiple dimensions (factual correctness, comprehensiveness, style, and overall quality) to better capture evaluation preferences of a clinical text generating model where preferences can differ based on the use case. This work also presents a dataset of radiologist rating annotations for generated and reference chest x-ray radiology reports. Lastly, it also creates an improved metric for the readability dimension by adding context awareness of frequent and acceptable medical terminology.","abstract_html":"In the past few years, there has been abundant research in using machine learning to generate high quality radiology reports using the large MIMIC-CXR chest x-ray dataset. However, there has been little work focused on evaluating the quality of generated reports from a clinical perspective, where accuracy is the most important factor. Current evaluation metrics evaluate reports in one dimension. This work proposes the use of multiple dimensions (factual correctness, comprehensiveness, style, and overall quality) to better capture evaluation preferences of a clinical text generating model where preferences can differ based on the use case. This work also presents a dataset of radiologist rating annotations for generated and reference chest x-ray radiology reports. Lastly, it also creates an improved metric for the readability dimension by adding context awareness of frequent and acceptable medical terminology.","abstract_has_math":false,"creators":["Rawat, Saumya"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Szolovits, Peter"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:20:46Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/144486","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Szolovits, Peter"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Rawat, Saumya"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-08-29T15:50:46Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-29T15:50:46Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/144486"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In the past few years, there has been abundant research in using machine learning to generate high quality radiology reports using the large MIMIC-CXR chest x-ray dataset. However, there has been little work focused on evaluating the quality of generated reports from a clinical perspective, where accuracy is the most important factor. Current evaluation metrics evaluate reports in one dimension. This work proposes the use of multiple dimensions (factual correctness, comprehensiveness, style, and overall quality) to better capture evaluation preferences of a clinical text generating model where preferences can differ based on the use case. This work also presents a dataset of radiologist rating annotations for generated and reference chest x-ray radiology reports. Lastly, it also creates an improved metric for the readability dimension by adding context awareness of frequent and acceptable medical terminology."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Multi-Dimensional Evaluation Metrics for Chest X-Ray Reports"]}]}],"canonical_facts":{"dc:contributor.advisor":["Szolovits, Peter"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Rawat, Saumya"],"dc:date.accessioned":["2022-08-29T15:50:46Z"],"dc:date.available":["2022-08-29T15:50:46Z"],"dc:date.issued":["2022-05"],"dc:description.abstract":["In the past few years, there has been abundant research in using machine learning to generate high quality radiology reports using the large MIMIC-CXR chest x-ray dataset. However, there has been little work focused on evaluating the quality of generated reports from a clinical perspective, where accuracy is the most important factor. Current evaluation metrics evaluate reports in one dimension. This work proposes the use of multiple dimensions (factual correctness, comprehensiveness, style, and overall quality) to better capture evaluation preferences of a clinical text generating model where preferences can differ based on the use case. This work also presents a dataset of radiologist rating annotations for generated and reference chest x-ray radiology reports. Lastly, it also creates an improved metric for the readability dimension by adding context awareness of frequent and acceptable medical terminology."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/144486"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Multi-Dimensional Evaluation Metrics for Chest X-Ray Reports"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:20:46Z"}