Delineation of malignant skin tumors by hyperspectral imaging using diffusion maps dimensionality reduction

V. Zheludev, I. Pölönen (Corresponding Author), N. Neittaanmäki-Perttu, A. Averbuch, P. Neittaanmäki, M. Grönroos, Heikki Saari

Research output: Contribution to journalArticleScientificpeer-review

12 Citations (Scopus)

Abstract

A new non-invasive method for delineation of lentigo maligna and lentigo maligna melanoma is demonstrated. The method is based on the analysis of the hyperspectral images taken in vivo before surgical excision of the lesions. For this, the characteristic features of the spectral signatures of diseased pixels and healthy pixels are extracted, which combine the intensities in a few selected wavebands with the coefficients of the wavelet frame transforms of the spectral curves. To reduce dimensionality and to reveal the internal structure of the datasets, the diffusion maps technique is applied. The averaged Nearest Neighbor and the Classification and Regression Tree (CART) classifiers are utilized as the decision units. To reduce false alarms by the CART classifier, the Aisles procedure is used.
Original languageEnglish
Pages (from-to)48 - 60
JournalBiomedical Signal Processing and Control
Volume16
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Hutchinson's Melanotic Freckle
Tumors
Skin
Classifiers
Pixels
Wavelet Analysis
Neoplasms
Melanoma
Hyperspectral imaging

Keywords

  • hyperspectral imaging
  • framelet
  • delineation
  • malignant
  • tumor

Cite this

Zheludev, V. ; Pölönen, I. ; Neittaanmäki-Perttu, N. ; Averbuch, A. ; Neittaanmäki, P. ; Grönroos, M. ; Saari, Heikki. / Delineation of malignant skin tumors by hyperspectral imaging using diffusion maps dimensionality reduction. In: Biomedical Signal Processing and Control. 2015 ; Vol. 16. pp. 48 - 60.
@article{476dff4cb35f49f0baddf65d1b706c37,
title = "Delineation of malignant skin tumors by hyperspectral imaging using diffusion maps dimensionality reduction",
abstract = "A new non-invasive method for delineation of lentigo maligna and lentigo maligna melanoma is demonstrated. The method is based on the analysis of the hyperspectral images taken in vivo before surgical excision of the lesions. For this, the characteristic features of the spectral signatures of diseased pixels and healthy pixels are extracted, which combine the intensities in a few selected wavebands with the coefficients of the wavelet frame transforms of the spectral curves. To reduce dimensionality and to reveal the internal structure of the datasets, the diffusion maps technique is applied. The averaged Nearest Neighbor and the Classification and Regression Tree (CART) classifiers are utilized as the decision units. To reduce false alarms by the CART classifier, the Aisles procedure is used.",
keywords = "hyperspectral imaging, framelet, delineation, malignant, tumor",
author = "V. Zheludev and I. P{\"o}l{\"o}nen and N. Neittaanm{\"a}ki-Perttu and A. Averbuch and P. Neittaanm{\"a}ki and M. Gr{\"o}nroos and Heikki Saari",
year = "2015",
doi = "10.1016/j.bspc.2014.10.010",
language = "English",
volume = "16",
pages = "48 -- 60",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",
publisher = "Elsevier",

}

Delineation of malignant skin tumors by hyperspectral imaging using diffusion maps dimensionality reduction. / Zheludev, V.; Pölönen, I. (Corresponding Author); Neittaanmäki-Perttu, N.; Averbuch, A.; Neittaanmäki, P.; Grönroos, M.; Saari, Heikki.

In: Biomedical Signal Processing and Control, Vol. 16, 2015, p. 48 - 60.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Delineation of malignant skin tumors by hyperspectral imaging using diffusion maps dimensionality reduction

AU - Zheludev, V.

AU - Pölönen, I.

AU - Neittaanmäki-Perttu, N.

AU - Averbuch, A.

AU - Neittaanmäki, P.

AU - Grönroos, M.

AU - Saari, Heikki

PY - 2015

Y1 - 2015

N2 - A new non-invasive method for delineation of lentigo maligna and lentigo maligna melanoma is demonstrated. The method is based on the analysis of the hyperspectral images taken in vivo before surgical excision of the lesions. For this, the characteristic features of the spectral signatures of diseased pixels and healthy pixels are extracted, which combine the intensities in a few selected wavebands with the coefficients of the wavelet frame transforms of the spectral curves. To reduce dimensionality and to reveal the internal structure of the datasets, the diffusion maps technique is applied. The averaged Nearest Neighbor and the Classification and Regression Tree (CART) classifiers are utilized as the decision units. To reduce false alarms by the CART classifier, the Aisles procedure is used.

AB - A new non-invasive method for delineation of lentigo maligna and lentigo maligna melanoma is demonstrated. The method is based on the analysis of the hyperspectral images taken in vivo before surgical excision of the lesions. For this, the characteristic features of the spectral signatures of diseased pixels and healthy pixels are extracted, which combine the intensities in a few selected wavebands with the coefficients of the wavelet frame transforms of the spectral curves. To reduce dimensionality and to reveal the internal structure of the datasets, the diffusion maps technique is applied. The averaged Nearest Neighbor and the Classification and Regression Tree (CART) classifiers are utilized as the decision units. To reduce false alarms by the CART classifier, the Aisles procedure is used.

KW - hyperspectral imaging

KW - framelet

KW - delineation

KW - malignant

KW - tumor

U2 - 10.1016/j.bspc.2014.10.010

DO - 10.1016/j.bspc.2014.10.010

M3 - Article

VL - 16

SP - 48

EP - 60

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

ER -