Using relevant regions in image search and query refinement for medical CBIR

Edward Kim, Sameer Antani, Sharon Xiaolei Huang, L. Rodney Long, Dina Demner-Fushman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In clinical decision processes, relevant scientific publications and their associated medical images can provide valuable and insightful information. However, effectively searching through both text and image data is a difficult and arduous task. More specifically in the area of image search, finding similar images (or regions within images) poses another significant hurdle for effective knowledge dissemination. Thus, we propose a method using local regions within images to perform and refine medical image retrieval. In our first example, we define and extract large, characteristic regions within an image, and then show how to use these regions to match a query image to similar content. In our second example, we enable the formulation of a mixed query based upon text, image, and region information, to better represent the end user's search intentions. Given our new framework for region-based queries, we present an improved set of similar search results.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2011
Subtitle of host publicationAdvanced PACS-Based Imaging Informatics and Therapeutic Applications
DOIs
StatePublished - Jun 8 2011
EventMedical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications - Lake Buena Vista, FL, United States
Duration: Feb 16 2011Feb 17 2011

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7967
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications
CountryUnited States
CityLake Buena Vista, FL
Period2/16/112/17/11

Fingerprint

Image retrieval
Publications
retrieval
formulations

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

Kim, E., Antani, S., Huang, S. X., Long, L. R., & Demner-Fushman, D. (2011). Using relevant regions in image search and query refinement for medical CBIR. In Medical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications [796707] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7967). https://doi.org/10.1117/12.878192
Kim, Edward ; Antani, Sameer ; Huang, Sharon Xiaolei ; Long, L. Rodney ; Demner-Fushman, Dina. / Using relevant regions in image search and query refinement for medical CBIR. Medical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications. 2011. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{07655e1ac01549a6a36f9b0cf2b8d700,
title = "Using relevant regions in image search and query refinement for medical CBIR",
abstract = "In clinical decision processes, relevant scientific publications and their associated medical images can provide valuable and insightful information. However, effectively searching through both text and image data is a difficult and arduous task. More specifically in the area of image search, finding similar images (or regions within images) poses another significant hurdle for effective knowledge dissemination. Thus, we propose a method using local regions within images to perform and refine medical image retrieval. In our first example, we define and extract large, characteristic regions within an image, and then show how to use these regions to match a query image to similar content. In our second example, we enable the formulation of a mixed query based upon text, image, and region information, to better represent the end user's search intentions. Given our new framework for region-based queries, we present an improved set of similar search results.",
author = "Edward Kim and Sameer Antani and Huang, {Sharon Xiaolei} and Long, {L. Rodney} and Dina Demner-Fushman",
year = "2011",
month = "6",
day = "8",
doi = "10.1117/12.878192",
language = "English (US)",
isbn = "9780819485090",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
booktitle = "Medical Imaging 2011",

}

Kim, E, Antani, S, Huang, SX, Long, LR & Demner-Fushman, D 2011, Using relevant regions in image search and query refinement for medical CBIR. in Medical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications., 796707, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 7967, Medical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications, Lake Buena Vista, FL, United States, 2/16/11. https://doi.org/10.1117/12.878192

Using relevant regions in image search and query refinement for medical CBIR. / Kim, Edward; Antani, Sameer; Huang, Sharon Xiaolei; Long, L. Rodney; Demner-Fushman, Dina.

Medical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications. 2011. 796707 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7967).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Using relevant regions in image search and query refinement for medical CBIR

AU - Kim, Edward

AU - Antani, Sameer

AU - Huang, Sharon Xiaolei

AU - Long, L. Rodney

AU - Demner-Fushman, Dina

PY - 2011/6/8

Y1 - 2011/6/8

N2 - In clinical decision processes, relevant scientific publications and their associated medical images can provide valuable and insightful information. However, effectively searching through both text and image data is a difficult and arduous task. More specifically in the area of image search, finding similar images (or regions within images) poses another significant hurdle for effective knowledge dissemination. Thus, we propose a method using local regions within images to perform and refine medical image retrieval. In our first example, we define and extract large, characteristic regions within an image, and then show how to use these regions to match a query image to similar content. In our second example, we enable the formulation of a mixed query based upon text, image, and region information, to better represent the end user's search intentions. Given our new framework for region-based queries, we present an improved set of similar search results.

AB - In clinical decision processes, relevant scientific publications and their associated medical images can provide valuable and insightful information. However, effectively searching through both text and image data is a difficult and arduous task. More specifically in the area of image search, finding similar images (or regions within images) poses another significant hurdle for effective knowledge dissemination. Thus, we propose a method using local regions within images to perform and refine medical image retrieval. In our first example, we define and extract large, characteristic regions within an image, and then show how to use these regions to match a query image to similar content. In our second example, we enable the formulation of a mixed query based upon text, image, and region information, to better represent the end user's search intentions. Given our new framework for region-based queries, we present an improved set of similar search results.

UR - http://www.scopus.com/inward/record.url?scp=79957953024&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957953024&partnerID=8YFLogxK

U2 - 10.1117/12.878192

DO - 10.1117/12.878192

M3 - Conference contribution

AN - SCOPUS:79957953024

SN - 9780819485090

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2011

ER -

Kim E, Antani S, Huang SX, Long LR, Demner-Fushman D. Using relevant regions in image search and query refinement for medical CBIR. In Medical Imaging 2011: Advanced PACS-Based Imaging Informatics and Therapeutic Applications. 2011. 796707. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.878192