Automated melanoma recognition

Harald Ganster; Ernst Wildling; Michael Binder; Harald Kittler; Axel Pinz; R. Röhrer

doi:10.1109/42.918473

Automated melanoma recognition

Harald Ganster, Ernst Wildling, Michael Binder, Harald Kittler, Axel Pinz, R. Röhrer

Research output: Contribution to journal › Article › peer-review

Abstract

A system for the computerized analysis of images obtained from epiluminescence microscopy (ELM) has been developed to enhance the early recognition of malignant melanoma. As an initial step, the binary mask of the skin lesion is determined by several basic segmentation algorithms together with a fusion strategy. A set of features containing shape and radiometric features as well as local and global parameters is calculated to describe the malignancy of a lesion. Significant features are then selected from this set by application of statistical feature subset selection methods. The final kNN classification delivers a sensitivity of 87% with a specificity of 92%

Original language	English
Pages (from-to)	233-239
Journal	IEEE Transactions on Medical Imaging
Volume	20
Issue number	3
DOIs	https://doi.org/10.1109/42.918473
Publication status	Published - 2001

Access to Document

10.1109/42.918473

Cite this

@article{987dd4d1cf1b4ad890a24ffac4388140,

title = "Automated melanoma recognition",

abstract = "A system for the computerized analysis of images obtained from epiluminescence microscopy (ELM) has been developed to enhance the early recognition of malignant melanoma. As an initial step, the binary mask of the skin lesion is determined by several basic segmentation algorithms together with a fusion strategy. A set of features containing shape and radiometric features as well as local and global parameters is calculated to describe the malignancy of a lesion. Significant features are then selected from this set by application of statistical feature subset selection methods. The final kNN classification delivers a sensitivity of 87% with a specificity of 92%",

author = "Harald Ganster and Ernst Wildling and Michael Binder and Harald Kittler and Axel Pinz and R. R{\"o}hrer",

year = "2001",

doi = "10.1109/42.918473",

language = "English",

volume = "20",

pages = "233--239",

journal = "IEEE Transactions on Medical Imaging",

issn = "1558-254X",

publisher = "Institute of Electrical and Electronics Engineers",

number = "3",

}

TY - JOUR

T1 - Automated melanoma recognition

AU - Ganster, Harald

AU - Wildling, Ernst

AU - Binder, Michael

AU - Kittler, Harald

AU - Pinz, Axel

AU - Röhrer, R.

PY - 2001

Y1 - 2001

N2 - A system for the computerized analysis of images obtained from epiluminescence microscopy (ELM) has been developed to enhance the early recognition of malignant melanoma. As an initial step, the binary mask of the skin lesion is determined by several basic segmentation algorithms together with a fusion strategy. A set of features containing shape and radiometric features as well as local and global parameters is calculated to describe the malignancy of a lesion. Significant features are then selected from this set by application of statistical feature subset selection methods. The final kNN classification delivers a sensitivity of 87% with a specificity of 92%

AB - A system for the computerized analysis of images obtained from epiluminescence microscopy (ELM) has been developed to enhance the early recognition of malignant melanoma. As an initial step, the binary mask of the skin lesion is determined by several basic segmentation algorithms together with a fusion strategy. A set of features containing shape and radiometric features as well as local and global parameters is calculated to describe the malignancy of a lesion. Significant features are then selected from this set by application of statistical feature subset selection methods. The final kNN classification delivers a sensitivity of 87% with a specificity of 92%

U2 - 10.1109/42.918473

DO - 10.1109/42.918473

M3 - Article

SN - 1558-254X

VL - 20

SP - 233

EP - 239

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 3

ER -

Automated melanoma recognition

Abstract

Access to Document

Fingerprint

Cite this