Radiology Report Analysis Using Deep Learning and NLP

• Author(s): Priyadarshini S; Siva Venkatesh M; Ezhil Aadhithyan K; Darsan Karthic P D
• Paper ID: 1714021
• Page: 2364-2369
• Published Date: 09-03-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 8 February-2026

Abstract

Radiology reports contain important diagnostic information but are commonly written in unstructured textual form. This makes automated processing and analysis difficult. This paper presents a framework for Radiology Report Analysis Using Deep Learning and Natural Language Processing (NLP) to extract relevant medical entities and generate concise summaries from radiology reports. The proposed system applies biomedical Named Entity Recognition for identifying anatomical structures and pathological conditions, followed by ontology-based mapping for term standardization. A transformer-based summarization model is used to generate brief clinical summaries. To address privacy concerns, a de-identification module is included to remove sensitive patient information. In addition, a basic consistency check is performed between extracted findings and generated impressions. Experimental observations indicate that the framework can assist in organizing and summarizing radiology report content, supporting clinical review processes.

Keywords

Radiology Reports, Medical NLP, Deep Learning, Clinical Text Analysis.

Citations

IRE Journals:
Priyadarshini S, Siva Venkatesh M, Ezhil Aadhithyan K, Darsan Karthic P D "Radiology Report Analysis Using Deep Learning and NLP" Iconic Research And Engineering Journals Volume 9 Issue 8 2026 Page 2364-2369 https://doi.org/10.64388/IREV9I8-1714021

IEEE:
Priyadarshini S, Siva Venkatesh M, Ezhil Aadhithyan K, Darsan Karthic P D "Radiology Report Analysis Using Deep Learning and NLP" Iconic Research And Engineering Journals, 9(8) https://doi.org/10.64388/IREV9I8-1714021