Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering

Srinivasan Rajagopalan, Richard Robb

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

Abstract

The degree of match between the delineation result produced by a segmentation technique and the ground truth can be assessed using robust "presence-absence" resemblance measures. Previously [1], we had investigated and introduced an exhaustive list of similarity indices for assessing multiple segmentation techniques. However, these measures are highly sensitive to even minor boundary perturbations which imminently manifest in the segmentations of random biphasic spaces reminiscent of the stochastic pore-solid distributions in the tissue engineering scaffolds. This paper investigates the ideas adapted from ecology to emphasize global resemblances and ignore minor local dissimilarities. It uses concepts from graph theory to perform controlled local mutations in order to maximize the similarities. The effect of this adjustment is investigated on a comprehensive list (forty nine) of similarity indices sensitive to the over- and underestimation errors associated with image delineation tasks.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6144 II
DOIs
StatePublished - 2006
EventMedical Imaging 2006: Image Processing - San Diego, CA, United States
Duration: Feb 13 2006Feb 16 2006

Other

OtherMedical Imaging 2006: Image Processing
CountryUnited States
CitySan Diego, CA
Period2/13/062/16/06

Fingerprint

Graph theory
Ecology
Scaffolds (biology)
Tissue engineering

Keywords

  • Delineation
  • Porous scaffolds
  • Segmentation
  • Similarity index
  • Tissue engineering

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Rajagopalan, S., & Robb, R. (2006). Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 6144 II). [61444E] https://doi.org/10.1117/12.654000

Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering. / Rajagopalan, Srinivasan; Robb, Richard.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6144 II 2006. 61444E.

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

Rajagopalan, S & Robb, R 2006, Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 6144 II, 61444E, Medical Imaging 2006: Image Processing, San Diego, CA, United States, 2/13/06. https://doi.org/10.1117/12.654000
Rajagopalan S, Robb R. Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6144 II. 2006. 61444E https://doi.org/10.1117/12.654000
Rajagopalan, Srinivasan ; Robb, Richard. / Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6144 II 2006.
@inproceedings{1240662ace844d1b95ca213f9ca2ce95,
title = "Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering",
abstract = "The degree of match between the delineation result produced by a segmentation technique and the ground truth can be assessed using robust {"}presence-absence{"} resemblance measures. Previously [1], we had investigated and introduced an exhaustive list of similarity indices for assessing multiple segmentation techniques. However, these measures are highly sensitive to even minor boundary perturbations which imminently manifest in the segmentations of random biphasic spaces reminiscent of the stochastic pore-solid distributions in the tissue engineering scaffolds. This paper investigates the ideas adapted from ecology to emphasize global resemblances and ignore minor local dissimilarities. It uses concepts from graph theory to perform controlled local mutations in order to maximize the similarities. The effect of this adjustment is investigated on a comprehensive list (forty nine) of similarity indices sensitive to the over- and underestimation errors associated with image delineation tasks.",
keywords = "Delineation, Porous scaffolds, Segmentation, Similarity index, Tissue engineering",
author = "Srinivasan Rajagopalan and Richard Robb",
year = "2006",
doi = "10.1117/12.654000",
language = "English (US)",
isbn = "0819464236",
volume = "6144 II",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Shortest path adjusted similarity metrics for resolving boundary perturbations in scaffold images for tissue engineering

AU - Rajagopalan, Srinivasan

AU - Robb, Richard

PY - 2006

Y1 - 2006

N2 - The degree of match between the delineation result produced by a segmentation technique and the ground truth can be assessed using robust "presence-absence" resemblance measures. Previously [1], we had investigated and introduced an exhaustive list of similarity indices for assessing multiple segmentation techniques. However, these measures are highly sensitive to even minor boundary perturbations which imminently manifest in the segmentations of random biphasic spaces reminiscent of the stochastic pore-solid distributions in the tissue engineering scaffolds. This paper investigates the ideas adapted from ecology to emphasize global resemblances and ignore minor local dissimilarities. It uses concepts from graph theory to perform controlled local mutations in order to maximize the similarities. The effect of this adjustment is investigated on a comprehensive list (forty nine) of similarity indices sensitive to the over- and underestimation errors associated with image delineation tasks.

AB - The degree of match between the delineation result produced by a segmentation technique and the ground truth can be assessed using robust "presence-absence" resemblance measures. Previously [1], we had investigated and introduced an exhaustive list of similarity indices for assessing multiple segmentation techniques. However, these measures are highly sensitive to even minor boundary perturbations which imminently manifest in the segmentations of random biphasic spaces reminiscent of the stochastic pore-solid distributions in the tissue engineering scaffolds. This paper investigates the ideas adapted from ecology to emphasize global resemblances and ignore minor local dissimilarities. It uses concepts from graph theory to perform controlled local mutations in order to maximize the similarities. The effect of this adjustment is investigated on a comprehensive list (forty nine) of similarity indices sensitive to the over- and underestimation errors associated with image delineation tasks.

KW - Delineation

KW - Porous scaffolds

KW - Segmentation

KW - Similarity index

KW - Tissue engineering

UR - http://www.scopus.com/inward/record.url?scp=33745166287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745166287&partnerID=8YFLogxK

U2 - 10.1117/12.654000

DO - 10.1117/12.654000

M3 - Conference contribution

SN - 0819464236

SN - 9780819464231

VL - 6144 II

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

ER -