A possible melanoma discrimination index based on hyperspectral data: A pilot study

Takashi Nagaoka, Atsushi Nakamura, Haruka Okutani, Yoshio Kiyohara, Takayuki Sota

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Background: Early detection and proper excision of the primary lesions of malignant melanoma (MM) are crucial for reducing melanoma-related deaths. To support the early detection of melanoma, automated melanoma screening systems have been extensively studied and developed. In this article, we present a hyperspectral melanoma screening system and propose a possible melanoma discrimination index derived from the characteristics of the pigment molecules in the skin, both of which have been derived from hyperspectral data (HSD). Methods: The index expresses the disordered nature of each lesion including variegation in color based on variation in spectral information obtained from each lesion. Performance of the index in discriminating melanomas from other pigmented skin lesions has been studied in five cases of melanoma (41 HSD sets), one case of Spitz nevus (13 HSD sets), 10 cases of seborrheic keratosis (78 HSD sets), three cases of basal cell carcinoma (16 HSD sets), and nine cases of melanocytic nevus (21 HSD sets), obtained from patients and volunteers, all of whom were Japanese. Results: Performance of the index, which reflects the disordered nature of a lesion, discriminates melanomas with a sensitivity of 90%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.93, on resubstitution. Conclusion: An objective melanoma discrimination index at a molecular pigmentary level, derived from HSD, has been proposed, and its performance evaluated. This index was highly successful in discriminating MM from non-melanoma, although the statistical population was small.

Original languageEnglish
Pages (from-to)301-310
Number of pages10
JournalSkin Research and Technology
Volume18
Issue number3
DOIs
Publication statusPublished - 2012 Aug

Fingerprint

Melanoma
Epithelioid and Spindle Cell Nevus
Seborrheic Keratosis
Pigmented Nevus
Skin
Basal Cell Carcinoma
ROC Curve
Volunteers
Color
Datasets

Keywords

  • Computer-assisted diagnosis
  • Diagnostic imaging
  • Early detection of cancer
  • Melanoma
  • Spectrum analysis

ASJC Scopus subject areas

  • Dermatology

Cite this

A possible melanoma discrimination index based on hyperspectral data : A pilot study. / Nagaoka, Takashi; Nakamura, Atsushi; Okutani, Haruka; Kiyohara, Yoshio; Sota, Takayuki.

In: Skin Research and Technology, Vol. 18, No. 3, 08.2012, p. 301-310.

Research output: Contribution to journalArticle

Nagaoka, Takashi ; Nakamura, Atsushi ; Okutani, Haruka ; Kiyohara, Yoshio ; Sota, Takayuki. / A possible melanoma discrimination index based on hyperspectral data : A pilot study. In: Skin Research and Technology. 2012 ; Vol. 18, No. 3. pp. 301-310.
@article{db747324efcd4bc1b7058d8dfaea5023,
title = "A possible melanoma discrimination index based on hyperspectral data: A pilot study",
abstract = "Background: Early detection and proper excision of the primary lesions of malignant melanoma (MM) are crucial for reducing melanoma-related deaths. To support the early detection of melanoma, automated melanoma screening systems have been extensively studied and developed. In this article, we present a hyperspectral melanoma screening system and propose a possible melanoma discrimination index derived from the characteristics of the pigment molecules in the skin, both of which have been derived from hyperspectral data (HSD). Methods: The index expresses the disordered nature of each lesion including variegation in color based on variation in spectral information obtained from each lesion. Performance of the index in discriminating melanomas from other pigmented skin lesions has been studied in five cases of melanoma (41 HSD sets), one case of Spitz nevus (13 HSD sets), 10 cases of seborrheic keratosis (78 HSD sets), three cases of basal cell carcinoma (16 HSD sets), and nine cases of melanocytic nevus (21 HSD sets), obtained from patients and volunteers, all of whom were Japanese. Results: Performance of the index, which reflects the disordered nature of a lesion, discriminates melanomas with a sensitivity of 90{\%}, a specificity of 84{\%}, and an area under the receiver operating characteristic curve of 0.93, on resubstitution. Conclusion: An objective melanoma discrimination index at a molecular pigmentary level, derived from HSD, has been proposed, and its performance evaluated. This index was highly successful in discriminating MM from non-melanoma, although the statistical population was small.",
keywords = "Computer-assisted diagnosis, Diagnostic imaging, Early detection of cancer, Melanoma, Spectrum analysis",
author = "Takashi Nagaoka and Atsushi Nakamura and Haruka Okutani and Yoshio Kiyohara and Takayuki Sota",
year = "2012",
month = "8",
doi = "10.1111/j.1600-0846.2011.00571.x",
language = "English",
volume = "18",
pages = "301--310",
journal = "Skin Research and Technology",
issn = "0909-752X",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - A possible melanoma discrimination index based on hyperspectral data

T2 - A pilot study

AU - Nagaoka, Takashi

AU - Nakamura, Atsushi

AU - Okutani, Haruka

AU - Kiyohara, Yoshio

AU - Sota, Takayuki

PY - 2012/8

Y1 - 2012/8

N2 - Background: Early detection and proper excision of the primary lesions of malignant melanoma (MM) are crucial for reducing melanoma-related deaths. To support the early detection of melanoma, automated melanoma screening systems have been extensively studied and developed. In this article, we present a hyperspectral melanoma screening system and propose a possible melanoma discrimination index derived from the characteristics of the pigment molecules in the skin, both of which have been derived from hyperspectral data (HSD). Methods: The index expresses the disordered nature of each lesion including variegation in color based on variation in spectral information obtained from each lesion. Performance of the index in discriminating melanomas from other pigmented skin lesions has been studied in five cases of melanoma (41 HSD sets), one case of Spitz nevus (13 HSD sets), 10 cases of seborrheic keratosis (78 HSD sets), three cases of basal cell carcinoma (16 HSD sets), and nine cases of melanocytic nevus (21 HSD sets), obtained from patients and volunteers, all of whom were Japanese. Results: Performance of the index, which reflects the disordered nature of a lesion, discriminates melanomas with a sensitivity of 90%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.93, on resubstitution. Conclusion: An objective melanoma discrimination index at a molecular pigmentary level, derived from HSD, has been proposed, and its performance evaluated. This index was highly successful in discriminating MM from non-melanoma, although the statistical population was small.

AB - Background: Early detection and proper excision of the primary lesions of malignant melanoma (MM) are crucial for reducing melanoma-related deaths. To support the early detection of melanoma, automated melanoma screening systems have been extensively studied and developed. In this article, we present a hyperspectral melanoma screening system and propose a possible melanoma discrimination index derived from the characteristics of the pigment molecules in the skin, both of which have been derived from hyperspectral data (HSD). Methods: The index expresses the disordered nature of each lesion including variegation in color based on variation in spectral information obtained from each lesion. Performance of the index in discriminating melanomas from other pigmented skin lesions has been studied in five cases of melanoma (41 HSD sets), one case of Spitz nevus (13 HSD sets), 10 cases of seborrheic keratosis (78 HSD sets), three cases of basal cell carcinoma (16 HSD sets), and nine cases of melanocytic nevus (21 HSD sets), obtained from patients and volunteers, all of whom were Japanese. Results: Performance of the index, which reflects the disordered nature of a lesion, discriminates melanomas with a sensitivity of 90%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.93, on resubstitution. Conclusion: An objective melanoma discrimination index at a molecular pigmentary level, derived from HSD, has been proposed, and its performance evaluated. This index was highly successful in discriminating MM from non-melanoma, although the statistical population was small.

KW - Computer-assisted diagnosis

KW - Diagnostic imaging

KW - Early detection of cancer

KW - Melanoma

KW - Spectrum analysis

UR - http://www.scopus.com/inward/record.url?scp=84862199476&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862199476&partnerID=8YFLogxK

U2 - 10.1111/j.1600-0846.2011.00571.x

DO - 10.1111/j.1600-0846.2011.00571.x

M3 - Article

C2 - 22092570

AN - SCOPUS:84862199476

VL - 18

SP - 301

EP - 310

JO - Skin Research and Technology

JF - Skin Research and Technology

SN - 0909-752X

IS - 3

ER -