A new hybrid technique for dermatological image registration

Heng Huang, Paul Bergstresser

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

12 Citations (Scopus)

Abstract

Malignant melanoma is nowadays one of the most malignant tumors among white-skinned populations around the world. The key element in malignant melanoma treatment is the detection of melanomas and their changes at an early stage, before they develop irreversible clinically significant and potentially fatal damage to the patients. Computer automatic diagnosis of skin lesions using early symptoms would be particularly useful as an aid in primary care. During such computer systems, there is a significant clinical demand for accurate dermatological image registration. In this paper, we introduce a new algorithm for the registration of melanomas in successive dermatological image. We reduce the melanoma registration problem to a bipartite graph matching problem. The Voronoi cells are used to measure the similarity between melanomas and build the weighted bipartite graph. A minimum weight maximum cardinality matching is employed to find the global correspondences between dermatological images. Distances order and dynamic programming method are applied into the bipartite graph matching to preserve topology of melanoma distribution. The dermatoscopy images are used to validate the effectiveness of our approach. Since our method is a general registration method for melanomas, it can also be used in other dermatological images.

Original languageEnglish (US)
Title of host publicationProceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE
Pages1163-1167
Number of pages5
DOIs
StatePublished - 2007
Event7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE - Boston, MA, United States
Duration: Jan 14 2007Jan 17 2007

Other

Other7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE
CountryUnited States
CityBoston, MA
Period1/14/071/17/07

Fingerprint

Image registration
Dynamic programming
Tumors
Melanoma
Skin
Computer systems
Topology
Dermoscopy
Computer Systems
Primary Health Care
Weights and Measures
Population

ASJC Scopus subject areas

  • Biotechnology
  • Genetics
  • Bioengineering

Cite this

Huang, H., & Bergstresser, P. (2007). A new hybrid technique for dermatological image registration. In Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE (pp. 1163-1167). [4375708] https://doi.org/10.1109/BIBE.2007.4375708

A new hybrid technique for dermatological image registration. / Huang, Heng; Bergstresser, Paul.

Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE. 2007. p. 1163-1167 4375708.

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

Huang, H & Bergstresser, P 2007, A new hybrid technique for dermatological image registration. in Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE., 4375708, pp. 1163-1167, 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE, Boston, MA, United States, 1/14/07. https://doi.org/10.1109/BIBE.2007.4375708
Huang H, Bergstresser P. A new hybrid technique for dermatological image registration. In Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE. 2007. p. 1163-1167. 4375708 https://doi.org/10.1109/BIBE.2007.4375708
Huang, Heng ; Bergstresser, Paul. / A new hybrid technique for dermatological image registration. Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE. 2007. pp. 1163-1167
@inproceedings{490c2cac484b4e1eb04223d67da35f97,
title = "A new hybrid technique for dermatological image registration",
abstract = "Malignant melanoma is nowadays one of the most malignant tumors among white-skinned populations around the world. The key element in malignant melanoma treatment is the detection of melanomas and their changes at an early stage, before they develop irreversible clinically significant and potentially fatal damage to the patients. Computer automatic diagnosis of skin lesions using early symptoms would be particularly useful as an aid in primary care. During such computer systems, there is a significant clinical demand for accurate dermatological image registration. In this paper, we introduce a new algorithm for the registration of melanomas in successive dermatological image. We reduce the melanoma registration problem to a bipartite graph matching problem. The Voronoi cells are used to measure the similarity between melanomas and build the weighted bipartite graph. A minimum weight maximum cardinality matching is employed to find the global correspondences between dermatological images. Distances order and dynamic programming method are applied into the bipartite graph matching to preserve topology of melanoma distribution. The dermatoscopy images are used to validate the effectiveness of our approach. Since our method is a general registration method for melanomas, it can also be used in other dermatological images.",
author = "Heng Huang and Paul Bergstresser",
year = "2007",
doi = "10.1109/BIBE.2007.4375708",
language = "English (US)",
isbn = "1424415098",
pages = "1163--1167",
booktitle = "Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE",

}

TY - GEN

T1 - A new hybrid technique for dermatological image registration

AU - Huang, Heng

AU - Bergstresser, Paul

PY - 2007

Y1 - 2007

N2 - Malignant melanoma is nowadays one of the most malignant tumors among white-skinned populations around the world. The key element in malignant melanoma treatment is the detection of melanomas and their changes at an early stage, before they develop irreversible clinically significant and potentially fatal damage to the patients. Computer automatic diagnosis of skin lesions using early symptoms would be particularly useful as an aid in primary care. During such computer systems, there is a significant clinical demand for accurate dermatological image registration. In this paper, we introduce a new algorithm for the registration of melanomas in successive dermatological image. We reduce the melanoma registration problem to a bipartite graph matching problem. The Voronoi cells are used to measure the similarity between melanomas and build the weighted bipartite graph. A minimum weight maximum cardinality matching is employed to find the global correspondences between dermatological images. Distances order and dynamic programming method are applied into the bipartite graph matching to preserve topology of melanoma distribution. The dermatoscopy images are used to validate the effectiveness of our approach. Since our method is a general registration method for melanomas, it can also be used in other dermatological images.

AB - Malignant melanoma is nowadays one of the most malignant tumors among white-skinned populations around the world. The key element in malignant melanoma treatment is the detection of melanomas and their changes at an early stage, before they develop irreversible clinically significant and potentially fatal damage to the patients. Computer automatic diagnosis of skin lesions using early symptoms would be particularly useful as an aid in primary care. During such computer systems, there is a significant clinical demand for accurate dermatological image registration. In this paper, we introduce a new algorithm for the registration of melanomas in successive dermatological image. We reduce the melanoma registration problem to a bipartite graph matching problem. The Voronoi cells are used to measure the similarity between melanomas and build the weighted bipartite graph. A minimum weight maximum cardinality matching is employed to find the global correspondences between dermatological images. Distances order and dynamic programming method are applied into the bipartite graph matching to preserve topology of melanoma distribution. The dermatoscopy images are used to validate the effectiveness of our approach. Since our method is a general registration method for melanomas, it can also be used in other dermatological images.

UR - http://www.scopus.com/inward/record.url?scp=47649098045&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47649098045&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2007.4375708

DO - 10.1109/BIBE.2007.4375708

M3 - Conference contribution

AN - SCOPUS:47649098045

SN - 1424415098

SN - 9781424415090

SP - 1163

EP - 1167

BT - Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE

ER -