Localization of lesions in dermoscopy images using ensembles of thresholding methods

M. Emre Celebi, Hitoshi Iyatomi, Gerald Schaefer, William V. Stoecker

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

Abstract

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Experiments on a large set of images demonstrate that the presented method achieves both fast and accurate localization of lesions in dermoscopy images.

Original languageEnglish
Title of host publicationAdvances in image and video technology
Subtitle of host publicationthird Pacific Rim Symposium, PSIVT 2009, Tokyo, Japan, January 13-16, 2009. Proceedings
EditorsToshikazu Wada, Fay Huang, Stephen Lin
Place of PublicationBerlin (DE)
PublisherSpringer
Pages1094-1103
Number of pages10
ISBN (Electronic)978-3-540-92957-4
ISBN (Print)978-3-540-92956-7
DOIs
Publication statusPublished - 2009
Event3rd Pacific Rim Symposium - Tokyo, Japan
Duration: 13 Jan 200916 Jan 2009

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume5414
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Symposium

Symposium3rd Pacific Rim Symposium
Abbreviated titlePSIVT 2009
CountryJapan
CityTokyo
Period13/01/0916/01/09

Fingerprint

Thresholding
Ensemble
Skin
Imaging techniques
Melanoma
Large Set
Experiments
Modality
Iterative Algorithm
Preprocessing
Imaging
Demonstrate
Experiment

Cite this

Celebi, M. E., Iyatomi, H., Schaefer, G., & Stoecker, W. V. (2009). Localization of lesions in dermoscopy images using ensembles of thresholding methods. In T. Wada, F. Huang, & S. Lin (Eds.), Advances in image and video technology: third Pacific Rim Symposium, PSIVT 2009, Tokyo, Japan, January 13-16, 2009. Proceedings (pp. 1094-1103). (Lecture Notes in Computer Science; Vol. 5414). Berlin (DE): Springer. https://doi.org/10.1007/978-3-540-92957-4_95
Celebi, M. Emre ; Iyatomi, Hitoshi ; Schaefer, Gerald ; Stoecker, William V. / Localization of lesions in dermoscopy images using ensembles of thresholding methods. Advances in image and video technology: third Pacific Rim Symposium, PSIVT 2009, Tokyo, Japan, January 13-16, 2009. Proceedings. editor / Toshikazu Wada ; Fay Huang ; Stephen Lin. Berlin (DE) : Springer, 2009. pp. 1094-1103 (Lecture Notes in Computer Science).
@inproceedings{86c6fb489f174ec6908f5a73fd3eab3c,
title = "Localization of lesions in dermoscopy images using ensembles of thresholding methods",
abstract = "Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Experiments on a large set of images demonstrate that the presented method achieves both fast and accurate localization of lesions in dermoscopy images.",
author = "Celebi, {M. Emre} and Hitoshi Iyatomi and Gerald Schaefer and Stoecker, {William V.}",
year = "2009",
doi = "10.1007/978-3-540-92957-4_95",
language = "English",
isbn = "978-3-540-92956-7",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "1094--1103",
editor = "Toshikazu Wada and Fay Huang and Stephen Lin",
booktitle = "Advances in image and video technology",
address = "Germany",

}

Celebi, ME, Iyatomi, H, Schaefer, G & Stoecker, WV 2009, Localization of lesions in dermoscopy images using ensembles of thresholding methods. in T Wada, F Huang & S Lin (eds), Advances in image and video technology: third Pacific Rim Symposium, PSIVT 2009, Tokyo, Japan, January 13-16, 2009. Proceedings. Lecture Notes in Computer Science, vol. 5414, Springer, Berlin (DE), pp. 1094-1103, 3rd Pacific Rim Symposium, Tokyo, Japan, 13/01/09. https://doi.org/10.1007/978-3-540-92957-4_95

Localization of lesions in dermoscopy images using ensembles of thresholding methods. / Celebi, M. Emre; Iyatomi, Hitoshi; Schaefer, Gerald; Stoecker, William V.

Advances in image and video technology: third Pacific Rim Symposium, PSIVT 2009, Tokyo, Japan, January 13-16, 2009. Proceedings. ed. / Toshikazu Wada; Fay Huang; Stephen Lin. Berlin (DE) : Springer, 2009. p. 1094-1103 (Lecture Notes in Computer Science; Vol. 5414).

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

TY - GEN

T1 - Localization of lesions in dermoscopy images using ensembles of thresholding methods

AU - Celebi, M. Emre

AU - Iyatomi, Hitoshi

AU - Schaefer, Gerald

AU - Stoecker, William V.

PY - 2009

Y1 - 2009

N2 - Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Experiments on a large set of images demonstrate that the presented method achieves both fast and accurate localization of lesions in dermoscopy images.

AB - Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Experiments on a large set of images demonstrate that the presented method achieves both fast and accurate localization of lesions in dermoscopy images.

UR - http://link.springer.com/chapter/10.1007%2F978-3-540-92957-4_95

UR - http://www.scopus.com/inward/record.url?scp=60149103804&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-92957-4_95

DO - 10.1007/978-3-540-92957-4_95

M3 - Conference contribution

AN - SCOPUS:60149103804

SN - 978-3-540-92956-7

T3 - Lecture Notes in Computer Science

SP - 1094

EP - 1103

BT - Advances in image and video technology

A2 - Wada, Toshikazu

A2 - Huang, Fay

A2 - Lin, Stephen

PB - Springer

CY - Berlin (DE)

ER -

Celebi ME, Iyatomi H, Schaefer G, Stoecker WV. Localization of lesions in dermoscopy images using ensembles of thresholding methods. In Wada T, Huang F, Lin S, editors, Advances in image and video technology: third Pacific Rim Symposium, PSIVT 2009, Tokyo, Japan, January 13-16, 2009. Proceedings. Berlin (DE): Springer. 2009. p. 1094-1103. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-540-92957-4_95