Tags

Type your tag names separated by a space and hit enter

Intelligent image retrieval based on radiology reports.
Eur Radiol. 2012 Dec; 22(12):2750-8.ER

Abstract

OBJECTIVES

To create an advanced image retrieval and data-mining system based on in-house radiology reports.

METHODS

Radiology reports are semantically analysed using natural language processing (NLP) techniques and stored in a state-of-the-art search engine. Images referenced by sequence and image number in the reports are retrieved from the picture archiving and communication system (PACS) and stored for later viewing. A web-based front end is used as an interface to query for images and show the results with the retrieved images and report text. Using a comprehensive radiological lexicon for the underlying terminology, the search algorithm also finds results for synonyms, abbreviations and related topics.

RESULTS

The test set was 108 manually annotated reports analysed by different system configurations. Best results were achieved using full syntactic and semantic analysis with a precision of 0.929 and recall of 0.952. Operating successfully since October 2010, 258,824 reports have been indexed and a total of 405,146 preview images are stored in the database.

CONCLUSIONS

Data-mining and NLP techniques provide quick access to a vast repository of images and radiology reports with both high precision and recall values. Consequently, the system has become a valuable tool in daily clinical routine, education and research.

KEY POINTS

Radiology reports can now be analysed using sophisticated natural language-processing techniques. Semantic text analysis is backed by terminology of a radiological lexicon. The search engine includes results for synonyms, abbreviations and compositions. Key images are automatically extracted from radiology reports and fetched from PACS. Such systems help to find diagnoses, improve report quality and save time.

Links

Publisher Full Text (DOI)

Authors+Show Affiliations

Gerstmair A
Department of Diagnostic Radiology, University Medical Center Freiburg, Hugstetterstrasse 55, 79106, Freiburg, Germany. axel.gerstmair@uniklinik-freiburg.de
Daumke P
No affiliation info available
Simon K
No affiliation info available
Langer M
No affiliation info available
Kotter E
No affiliation info available

MeSH

AlgorithmsData MiningHumansInformation Storage and RetrievalNatural Language ProcessingRadiology Information SystemsSearch EngineSemanticsSoftwareUser-Computer Interface

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

22865274

Citation

Gerstmair, Axel, et al. "Intelligent Image Retrieval Based On Radiology Reports." European Radiology, vol. 22, no. 12, 2012, pp. 2750-8.
Gerstmair A, Daumke P, Simon K, et al. Intelligent image retrieval based on radiology reports. Eur Radiol. 2012;22(12):2750-8.
Gerstmair, A., Daumke, P., Simon, K., Langer, M., & Kotter, E. (2012). Intelligent image retrieval based on radiology reports. European Radiology, 22(12), 2750-8. https://doi.org/10.1007/s00330-012-2608-x
Gerstmair A, et al. Intelligent Image Retrieval Based On Radiology Reports. Eur Radiol. 2012;22(12):2750-8. PubMed PMID: 22865274.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Intelligent image retrieval based on radiology reports. AU - Gerstmair,Axel, AU - Daumke,Philipp, AU - Simon,Kai, AU - Langer,Mathias, AU - Kotter,Elmar, Y1 - 2012/08/04/ PY - 2012/03/29/received PY - 2012/07/13/accepted PY - 2012/07/02/revised PY - 2012/8/7/entrez PY - 2012/8/7/pubmed PY - 2013/5/28/medline SP - 2750 EP - 8 JF - European radiology JO - Eur Radiol VL - 22 IS - 12 N2 - OBJECTIVES: To create an advanced image retrieval and data-mining system based on in-house radiology reports. METHODS: Radiology reports are semantically analysed using natural language processing (NLP) techniques and stored in a state-of-the-art search engine. Images referenced by sequence and image number in the reports are retrieved from the picture archiving and communication system (PACS) and stored for later viewing. A web-based front end is used as an interface to query for images and show the results with the retrieved images and report text. Using a comprehensive radiological lexicon for the underlying terminology, the search algorithm also finds results for synonyms, abbreviations and related topics. RESULTS: The test set was 108 manually annotated reports analysed by different system configurations. Best results were achieved using full syntactic and semantic analysis with a precision of 0.929 and recall of 0.952. Operating successfully since October 2010, 258,824 reports have been indexed and a total of 405,146 preview images are stored in the database. CONCLUSIONS: Data-mining and NLP techniques provide quick access to a vast repository of images and radiology reports with both high precision and recall values. Consequently, the system has become a valuable tool in daily clinical routine, education and research. KEY POINTS: Radiology reports can now be analysed using sophisticated natural language-processing techniques. Semantic text analysis is backed by terminology of a radiological lexicon. The search engine includes results for synonyms, abbreviations and compositions. Key images are automatically extracted from radiology reports and fetched from PACS. Such systems help to find diagnoses, improve report quality and save time. SN - 1432-1084 UR - https://www.unboundmedicine.com/medline/citation/22865274/Intelligent_image_retrieval_based_on_radiology_reports_ L2 - https://dx.doi.org/10.1007/s00330-012-2608-x DB - PRIME DP - Unbound Medicine ER -