Towards a semantic PACS: Using Semantic Web technology to represent imaging data

Johan Van Soest; Tim Lustberg; Detlef Grittner; M Scott Marshall; Lucas Persoon; Bas Nijsten; Peter Feltens; Andre Dekker

doi:10.3233/978-1-61499-432-9-166

Towards a semantic PACS: Using Semantic Web technology to represent imaging data

Johan Van Soest^*, Tim Lustberg, Detlef Grittner, M Scott Marshall, Lucas Persoon, Bas Nijsten, Peter Feltens, Andre Dekker

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

The DICOM standard is ubiquitous within medicine. However, improved DICOM semantics would significantly enhance search operations. Furthermore, databases of current PACS systems are not flexible enough for the demands within image analysis research. In this paper, we investigated if we can use Semantic Web technology, to store and represent metadata of DICOM image files, as well as linking additional computational results to image metadata. Therefore, we developed a proof of concept containing two applications: one to store commonly used DICOM metadata in an RDF repository, and one to calculate imaging biomarkers based on DICOM images, and store the biomarker values in an RDF repository. This enabled us to search for all patients with a gross tumor volume calculated to be larger than 50 cc. We have shown that we can successfully store the DICOM metadata in an RDF repository and are refining our proof of concept with regards to volume naming, value representation, and the applications themselves.

Original language	English
Pages (from-to)	166-70
Number of pages	5
Journal	Studies in Health Technology and Informatics
Volume	205
DOIs	https://doi.org/10.3233/978-1-61499-432-9-166
Publication status	Published - 2014

Keywords

Humans
Image Interpretation, Computer-Assisted
Information Storage and Retrieval
Internet
Natural Language Processing
Neoplasms
Practice Guidelines as Topic
Radiology Information Systems
Semantics
Terminology as Topic
Tumor Burden

Access to Document

10.3233/978-1-61499-432-9-166Licence: CC BY-NC

Cite this

@article{227a2aae4a1b4ca2946240a7b85516be,

title = "Towards a semantic PACS: Using Semantic Web technology to represent imaging data",

abstract = "The DICOM standard is ubiquitous within medicine. However, improved DICOM semantics would significantly enhance search operations. Furthermore, databases of current PACS systems are not flexible enough for the demands within image analysis research. In this paper, we investigated if we can use Semantic Web technology, to store and represent metadata of DICOM image files, as well as linking additional computational results to image metadata. Therefore, we developed a proof of concept containing two applications: one to store commonly used DICOM metadata in an RDF repository, and one to calculate imaging biomarkers based on DICOM images, and store the biomarker values in an RDF repository. This enabled us to search for all patients with a gross tumor volume calculated to be larger than 50 cc. We have shown that we can successfully store the DICOM metadata in an RDF repository and are refining our proof of concept with regards to volume naming, value representation, and the applications themselves.",

keywords = "Humans, Image Interpretation, Computer-Assisted, Information Storage and Retrieval, Internet, Natural Language Processing, Neoplasms, Practice Guidelines as Topic, Radiology Information Systems, Semantics, Terminology as Topic, Tumor Burden",

author = "{Van Soest}, Johan and Tim Lustberg and Detlef Grittner and Marshall, {M Scott} and Lucas Persoon and Bas Nijsten and Peter Feltens and Andre Dekker",

year = "2014",

doi = "10.3233/978-1-61499-432-9-166",

language = "English",

volume = "205",

pages = "166--70",

journal = "Studies in Health Technology and Informatics",

issn = "0926-9630",

publisher = "IOS Press",

}

TY - JOUR

T1 - Towards a semantic PACS

T2 - Using Semantic Web technology to represent imaging data

AU - Van Soest, Johan

AU - Lustberg, Tim

AU - Grittner, Detlef

AU - Marshall, M Scott

AU - Persoon, Lucas

AU - Nijsten, Bas

AU - Feltens, Peter

AU - Dekker, Andre

PY - 2014

Y1 - 2014

N2 - The DICOM standard is ubiquitous within medicine. However, improved DICOM semantics would significantly enhance search operations. Furthermore, databases of current PACS systems are not flexible enough for the demands within image analysis research. In this paper, we investigated if we can use Semantic Web technology, to store and represent metadata of DICOM image files, as well as linking additional computational results to image metadata. Therefore, we developed a proof of concept containing two applications: one to store commonly used DICOM metadata in an RDF repository, and one to calculate imaging biomarkers based on DICOM images, and store the biomarker values in an RDF repository. This enabled us to search for all patients with a gross tumor volume calculated to be larger than 50 cc. We have shown that we can successfully store the DICOM metadata in an RDF repository and are refining our proof of concept with regards to volume naming, value representation, and the applications themselves.

AB - The DICOM standard is ubiquitous within medicine. However, improved DICOM semantics would significantly enhance search operations. Furthermore, databases of current PACS systems are not flexible enough for the demands within image analysis research. In this paper, we investigated if we can use Semantic Web technology, to store and represent metadata of DICOM image files, as well as linking additional computational results to image metadata. Therefore, we developed a proof of concept containing two applications: one to store commonly used DICOM metadata in an RDF repository, and one to calculate imaging biomarkers based on DICOM images, and store the biomarker values in an RDF repository. This enabled us to search for all patients with a gross tumor volume calculated to be larger than 50 cc. We have shown that we can successfully store the DICOM metadata in an RDF repository and are refining our proof of concept with regards to volume naming, value representation, and the applications themselves.

KW - Humans

KW - Image Interpretation, Computer-Assisted

KW - Information Storage and Retrieval

KW - Internet

KW - Natural Language Processing

KW - Neoplasms

KW - Practice Guidelines as Topic

KW - Radiology Information Systems

KW - Semantics

KW - Terminology as Topic

KW - Tumor Burden

U2 - 10.3233/978-1-61499-432-9-166

DO - 10.3233/978-1-61499-432-9-166

M3 - Article

C2 - 25160167

SN - 0926-9630

VL - 205

SP - 166

EP - 170

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

ER -