Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic Review

Radiology reports, as a means of inter-physician and physician-to-patient communication, contain key findings and interpretations from imaging studies that guide diagnosis and treatment. Recent advancements in Artificial Intelligence (AI) technologies and the growing volume of clinical data necessit...

Full description

Saved in:
Bibliographic Details
Main Authors: Umay Kulsoom, Frank G. Glavin, Malika Bendechache
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11050386/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427199871942656
author Umay Kulsoom
Frank G. Glavin
Malika Bendechache
author_facet Umay Kulsoom
Frank G. Glavin
Malika Bendechache
author_sort Umay Kulsoom
collection DOAJ
description Radiology reports, as a means of inter-physician and physician-to-patient communication, contain key findings and interpretations from imaging studies that guide diagnosis and treatment. Recent advancements in Artificial Intelligence (AI) technologies and the growing volume of clinical data necessitate efficient approaches for effective data utilisation. Integrating AI technologies can improve data analysis, enhance diagnostic accuracy, and streamline clinical workflows, reducing the burden on physicians. This Systematic Literature Review (SLR) examines the state-of-the-art of Natural Language Processing (NLP) and Machine Learning (ML) techniques, reviewing their diverse applications in radiology report processing, with a focus on automated disease diagnosis. We explored the commonly used approaches and their impact on diagnostic accuracy. We also looked into the availability of publicly accessible datasets that can be used for ML research within the radiology domain. Despite the promising advancements, challenges remain, such as data quality issues, interpretability of models and integrations of these technologies into clinical workflows. This review provides a thorough overview of the current research in this field by analysing existing findings and highlighting areas of improvement. The goal is to provide insights that can inform future studies in report analysis and improve the use of AI techniques in radiology.
format Article
id doaj-art-5b9065e35ded4509aa9d9882c35b9d74
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5b9065e35ded4509aa9d9882c35b9d742025-08-20T03:29:06ZengIEEEIEEE Access2169-35362025-01-011311221511225410.1109/ACCESS.2025.358272811050386Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic ReviewUmay Kulsoom0https://orcid.org/0000-0002-9264-1512Frank G. Glavin1https://orcid.org/0000-0003-3363-2090Malika Bendechache2https://orcid.org/0000-0003-0069-1860School of Computer Science, University of Galway, Galway, IrelandSchool of Computer Science, University of Galway, Galway, IrelandSchool of Computer Science, University of Galway, Galway, IrelandRadiology reports, as a means of inter-physician and physician-to-patient communication, contain key findings and interpretations from imaging studies that guide diagnosis and treatment. Recent advancements in Artificial Intelligence (AI) technologies and the growing volume of clinical data necessitate efficient approaches for effective data utilisation. Integrating AI technologies can improve data analysis, enhance diagnostic accuracy, and streamline clinical workflows, reducing the burden on physicians. This Systematic Literature Review (SLR) examines the state-of-the-art of Natural Language Processing (NLP) and Machine Learning (ML) techniques, reviewing their diverse applications in radiology report processing, with a focus on automated disease diagnosis. We explored the commonly used approaches and their impact on diagnostic accuracy. We also looked into the availability of publicly accessible datasets that can be used for ML research within the radiology domain. Despite the promising advancements, challenges remain, such as data quality issues, interpretability of models and integrations of these technologies into clinical workflows. This review provides a thorough overview of the current research in this field by analysing existing findings and highlighting areas of improvement. The goal is to provide insights that can inform future studies in report analysis and improve the use of AI techniques in radiology.https://ieeexplore.ieee.org/document/11050386/Artificial intelligencedeep learningmachine learningmultimodalnatural language processingradiology reports
spellingShingle Umay Kulsoom
Frank G. Glavin
Malika Bendechache
Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic Review
IEEE Access
Artificial intelligence
deep learning
machine learning
multimodal
natural language processing
radiology reports
title Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic Review
title_full Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic Review
title_fullStr Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic Review
title_full_unstemmed Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic Review
title_short Natural Language Processing and Machine Learning for Analysis of Radiology Reports: A Systematic Review
title_sort natural language processing and machine learning for analysis of radiology reports a systematic review
topic Artificial intelligence
deep learning
machine learning
multimodal
natural language processing
radiology reports
url https://ieeexplore.ieee.org/document/11050386/
work_keys_str_mv AT umaykulsoom naturallanguageprocessingandmachinelearningforanalysisofradiologyreportsasystematicreview
AT frankgglavin naturallanguageprocessingandmachinelearningforanalysisofradiologyreportsasystematicreview
AT malikabendechache naturallanguageprocessingandmachinelearningforanalysisofradiologyreportsasystematicreview