Unsupervised sub-segmentation for pigmented skin lesions
ABSTRACT Early identification of malignant melanoma with the surgical removal of thin lesions is the most effective treatment for skin cancers. A computer-aided diagnostic system assists to improve the diagnostic accuracy, where segmenting lesion from normal skin is usually considered as the first step. One of the challenges in the automated segmentation of skin lesions arises from the fact that darker areas within the lesion should be considered separate from the more general suspicious lesion as a whole, because these pigmented areas can provide significant additional diagnostic information.
This paper presents, for the first time, an unsupervised segmentation scheme to allow the isolation of normal skin, pigmented skin lesions, and interesting darker areas inside the lesion simultaneously. An adaptive mean-shift is first applied with a 5D spatial colour-texture feature space to generate a group of homogenous regions. Then the sub-segmentation maps are calculated by integrating maximal similarity-based region merging and the kernel k-means algorithm, where the number of segments is defined by a cluster validity measurement.
The proposed method has been validated extensively on both normal digital photographs and dermoscopy images, which demonstrates competitive performance in achieving automatic segmentation. The isolated dark areas have proved helpful in the discrimination of malignant melanomas from atypical benign nevi. Compared with the results obtained from the asymmetry measure of the entire lesion, the asymmetry distribution of the isolated dark areas helped increase the accuracy of the identification of malignant melanoma from 65.38% to 73.07%, and this classification accuracy reached 80.77% on integrating both asymmetry descriptors.
The proposed segmentation scheme gives the lesion boundary closed to the manual segmentation obtained by experienced dermatologists. The initial classification results indicate that the study of the distributions of darker areas inside the lesions is very promising in characterizing melanomas.
- SourceAvailable from: Alessia Amelio
Conference Paper: Skin lesion image segmentation using a color genetic algorithm[Show abstract] [Hide abstract]
ABSTRACT: The development of computer-aided diagnosis systems for skin cancer detection has attracted a lot of interest in the research community. In particular, the availability of an accurate automatic segmentation tool for detecting skin lesions from background skin is of primary importance for the overall diagnosis system. In this paper we investigate the capability of a color image segmentation method based on Genetic Algorithms in discriminating skin lesions. Experimental results show that the segmentation approach is able to detect lesion borders quite accurately, thus coupled with a merging technique of the surrounding region could reveal a promising method for isolating skin tumor.Proceedings of the 15th annual conference companion on Genetic and evolutionary computation; 07/2013
- [Show abstract] [Hide abstract]
ABSTRACT: OBJECTIVE: Computerized analysis of pigmented skin lesions (PSLs) is an active area of research that dates back over 25years. One of its main goals is to develop reliable automatic instruments for recognizing skin cancer from images acquired in vivo. This paper presents a review of this research applied to microscopic (dermoscopic) and macroscopic (clinical) images of PSLs. The review aims to: (1) provide an extensive introduction to and clarify ambiguities in the terminology used in the literature and (2) categorize and group together relevant references so as to simplify literature searches on a specific sub-topic. METHODS AND MATERIAL: The existing literature was classified according to the nature of publication (clinical or computer vision articles) and differentiating between individual and multiple PSL image analysis. We also emphasize the importance of the difference in content between dermoscopic and clinical images. RESULTS: Various approaches for implementing PSL computer-aided diagnosis systems and their standard workflow components are reviewed and summary tables provided. An extended categorization of PSL feature descriptors is also proposed, associating them with the specific methods for diagnosing melanoma, separating images of the two modalities and discriminating references according to our classification of the literature. CONCLUSIONS: There is a large discrepancy in the number of articles published on individual and multiple PSL image analysis and a scarcity of reported material on the automation of lesion change detection. At present, computer-aided diagnosis systems based on individual PSL image analysis cannot yet be used to provide the best diagnostic results. Furthermore, the absence of benchmark datasets for standardized algorithm evaluation is a barrier to a more dynamic development of this research area.Artificial intelligence in medicine 10/2012; DOI:10.1016/j.artmed.2012.08.002 · 1.36 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: Computer-assisted diagnosis (CAD) of malignant melanoma (MM) has been advocated to help clinicians in achieving a more objective and reliable assessment. However, conventional CAD systems only examine the features extracted from digital photographs of lesions. Failure to incorporate patient personal information constrains their applicability in clinical settings. To develop a new CAD system to improve the performance of automatic diagnosis of melanoma which, for the first time, incorporates lesion digital features with important patient metadata into learning process. Thirty-two features are extracted from digital photographs to characterise skin lesions. Patient personal information like age, gender, lesion site and their combinations are quantified as metadata. The integration of digital features and metadata is realised through an extended Laplacian Eigenmap, a dimensionality reduction method grouping lesions with similar digital features and metadata into the same classes. The diagnosis is 82.14% sensitivity and 86.07% specificity, when only multidimensional digital features are used; while the results are significantly improved to 95.25% sensitivity and 90.96% specificity respectively, after metadata are incorporated appropriately. The proposed system achieves a level of sensitivity comparable to experienced dermatologists aided by conventional dermoscopes. This demonstrates the potential of our method for assisting clinicians in diagnosing melanoma, and the benefit it could provide to patients and hospitals by greatly reducing unnecessary excision of benign naevi. This paper proposes an enhanced CAD system by incorporating clinical metadata in the learning process for automatic classification of melanoma. Results demonstrate that the additional metadata and the mechanism to incorporate them are useful for improving computer-assisted diagnosis of melanoma. This article is protected by copyright. All rights reserved.British Journal of Dermatology 07/2013; 169(5). DOI:10.1111/bjd.12550 · 4.10 Impact Factor