Shape-based similarity retrieval of Doppler images for clinical decision support

T. Syeda-Mahmood, Pavan Turaga, D. Beymer, F. Wang, A. Amir, H. Greenspan, K. Pohl

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

10 Citations (Scopus)

Abstract

Flow Doppler imaging has become an integral part of an echocardiographic exam. Automated interpretation of flow doppler imaging has so far been restricted to obtaining hemodynamic information from velocity-time profiles depicted in these images. In this paper we exploit the shape patterns in Doppler images to infer the similarity in valvular disease labels for purposes of automated clinical decision support. Specifically, we model the similarity in appearance of Doppler images from the same disease class as a constrained non-rigid translation transform of the velocity envelopes embedded in these images. The shape similarity between two Doppler images is then judged by recovering the alignment transform using a variant of dynamic shape warping. Results of similarity retrieval of doppler images for cardiac decision support on a large database of images are presented.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages855-862
Number of pages8
DOIs
StatePublished - 2010
Externally publishedYes
Event2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 - San Francisco, CA, United States
Duration: Jun 13 2010Jun 18 2010

Other

Other2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
CountryUnited States
CitySan Francisco, CA
Period6/13/106/18/10

Fingerprint

Imaging techniques
Hemodynamics
Labels

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Syeda-Mahmood, T., Turaga, P., Beymer, D., Wang, F., Amir, A., Greenspan, H., & Pohl, K. (2010). Shape-based similarity retrieval of Doppler images for clinical decision support. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 855-862). [5540126] https://doi.org/10.1109/CVPR.2010.5540126

Shape-based similarity retrieval of Doppler images for clinical decision support. / Syeda-Mahmood, T.; Turaga, Pavan; Beymer, D.; Wang, F.; Amir, A.; Greenspan, H.; Pohl, K.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2010. p. 855-862 5540126.

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

Syeda-Mahmood, T, Turaga, P, Beymer, D, Wang, F, Amir, A, Greenspan, H & Pohl, K 2010, Shape-based similarity retrieval of Doppler images for clinical decision support. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 5540126, pp. 855-862, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, United States, 6/13/10. https://doi.org/10.1109/CVPR.2010.5540126
Syeda-Mahmood T, Turaga P, Beymer D, Wang F, Amir A, Greenspan H et al. Shape-based similarity retrieval of Doppler images for clinical decision support. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2010. p. 855-862. 5540126 https://doi.org/10.1109/CVPR.2010.5540126
Syeda-Mahmood, T. ; Turaga, Pavan ; Beymer, D. ; Wang, F. ; Amir, A. ; Greenspan, H. ; Pohl, K. / Shape-based similarity retrieval of Doppler images for clinical decision support. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2010. pp. 855-862
@inproceedings{f2346d36a13a4576927cdb704bd7debe,
title = "Shape-based similarity retrieval of Doppler images for clinical decision support",
abstract = "Flow Doppler imaging has become an integral part of an echocardiographic exam. Automated interpretation of flow doppler imaging has so far been restricted to obtaining hemodynamic information from velocity-time profiles depicted in these images. In this paper we exploit the shape patterns in Doppler images to infer the similarity in valvular disease labels for purposes of automated clinical decision support. Specifically, we model the similarity in appearance of Doppler images from the same disease class as a constrained non-rigid translation transform of the velocity envelopes embedded in these images. The shape similarity between two Doppler images is then judged by recovering the alignment transform using a variant of dynamic shape warping. Results of similarity retrieval of doppler images for cardiac decision support on a large database of images are presented.",
author = "T. Syeda-Mahmood and Pavan Turaga and D. Beymer and F. Wang and A. Amir and H. Greenspan and K. Pohl",
year = "2010",
doi = "10.1109/CVPR.2010.5540126",
language = "English (US)",
isbn = "9781424469840",
pages = "855--862",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Shape-based similarity retrieval of Doppler images for clinical decision support

AU - Syeda-Mahmood, T.

AU - Turaga, Pavan

AU - Beymer, D.

AU - Wang, F.

AU - Amir, A.

AU - Greenspan, H.

AU - Pohl, K.

PY - 2010

Y1 - 2010

N2 - Flow Doppler imaging has become an integral part of an echocardiographic exam. Automated interpretation of flow doppler imaging has so far been restricted to obtaining hemodynamic information from velocity-time profiles depicted in these images. In this paper we exploit the shape patterns in Doppler images to infer the similarity in valvular disease labels for purposes of automated clinical decision support. Specifically, we model the similarity in appearance of Doppler images from the same disease class as a constrained non-rigid translation transform of the velocity envelopes embedded in these images. The shape similarity between two Doppler images is then judged by recovering the alignment transform using a variant of dynamic shape warping. Results of similarity retrieval of doppler images for cardiac decision support on a large database of images are presented.

AB - Flow Doppler imaging has become an integral part of an echocardiographic exam. Automated interpretation of flow doppler imaging has so far been restricted to obtaining hemodynamic information from velocity-time profiles depicted in these images. In this paper we exploit the shape patterns in Doppler images to infer the similarity in valvular disease labels for purposes of automated clinical decision support. Specifically, we model the similarity in appearance of Doppler images from the same disease class as a constrained non-rigid translation transform of the velocity envelopes embedded in these images. The shape similarity between two Doppler images is then judged by recovering the alignment transform using a variant of dynamic shape warping. Results of similarity retrieval of doppler images for cardiac decision support on a large database of images are presented.

UR - http://www.scopus.com/inward/record.url?scp=77956005446&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956005446&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2010.5540126

DO - 10.1109/CVPR.2010.5540126

M3 - Conference contribution

SN - 9781424469840

SP - 855

EP - 862

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -