Title :
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
fDate :
3/1/2001 12:00:00 AM
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;
Journal_Title :
Medical Imaging, IEEE Transactions on
