C.D. is a Research Associate and R.K. is a Senior Research Associate with the Fonds National de la Recherche Scientifique (FNRS), Belgium.
Computer-assisted analysis of epiluminescence microscopy images of pigmented skin lesions†
Version of Record online: 2 NOV 1999
Copyright © 1999 Wiley-Liss, Inc.
Volume 37, Issue 4, pages 255–266, 1 December 1999
How to Cite
Debeir, O., Decaestecker, C., Pasteels, J.-L., Salmon, I., Kiss, R. and Van Ham, P. (1999), Computer-assisted analysis of epiluminescence microscopy images of pigmented skin lesions. Cytometry, 37: 255–266. doi: 10.1002/(SICI)1097-0320(19991201)37:4<255::AID-CYTO2>3.0.CO;2-5
- Issue online: 2 NOV 1999
- Version of Record online: 2 NOV 1999
- Manuscript Accepted: 14 AUG 1999
- Manuscript Revised: 15 JUN 1999
- Manuscript Received: 9 FEB 1999
- epiluminescence microscopy;
- pigmented skin lesion;
- computer-assisted image analysis;
- pixel classification;
- image segmentation
Epiluminescence microscopy (ELM) is a noninvasive clinical tool recently developed for the diagnosis of pigmented skin lesions (PSLs), with the aim of improving melanoma screening strategies. However, the complexity of the ELM grading protocol means that considerable expertise is required for differential diagnosis. In this paper we propose a computer-based tool able to screen ELM images of PSLs in order to aid clinicians in the detection of lesion patterns useful for differential diagnosis.
The method proposed is based on the supervised classification of pixels of digitized ELM images, and leads to the construction of classes of pixels used for image segmentation. This process has two major phases, i.e., a learning phase, where several hundred pixels are used in order to train and validate a classification model, and an application step, which consists of a massive classification of billions of pixels (i.e., the full image) by means of the rules obtained in the first phase.
Our results show that the proposed method is suitable for lesion-from-background extraction, for complete image segmentation into several typical diagnostic patterns, and for artifact rejection. Hence, our prototype has the potential to assist in distinguishing lesion patterns which are associated with diagnostic information such as diffuse pigmentation, dark globules (black dots and brown globules), and the gray-blue veil.
The system proposed in this paper can be considered as a tool to assist in PSL diagnosis. Cytometry 37:255–266, 1999. © 1999 Wiley-Liss, Inc.