Automated melanoma recognition

Author

Ganster, Harald ; Pinz, Axel ; Röhrer, Reinhard ; Wildling, Ernst ; Binder, Michael ; Kittler, Harald

Author_Institution

Inst. for Comput. Graphics & Vision, Tech. Univ. Graz, Austria

Volume

20

Issue

3

fYear

2001

fDate

3/1/2001 12:00:00 AM

Firstpage

233

Lastpage

239

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%.

Keywords

bioluminescence; biomedical imaging; cancer; feature extraction; image classification; image recognition; image segmentation; medical image processing; optical microscopy; skin; ELM; automated melanoma recognition; basic segmentation algorithms; binary mask; computerized analysis; early recognition; epiluminescence microscopy; final kNN classification; fusion strategy; global parameters; local parameters; malignancy; malignant melanoma; radiometric features; sensitivity; shape features; skin lesion; specificity; statistical feature subset selection methods; Cancer; Image analysis; Image recognition; Image segmentation; Lesions; Malignant tumors; Microscopy; Radiometry; Shape; Skin; Algorithms; Humans; Image Processing, Computer-Assisted; Melanoma; Microscopy; Sensitivity and Specificity; Skin Neoplasms;

fLanguage

English

Journal_Title

Medical Imaging, IEEE Transactions on

Publisher

ieee

ISSN

0278-0062

Type

jour

DOI

10.1109/42.918473

Filename

918473