A relative color approach to color discrimination for malignant melanoma detection in dermoscopy images

BACKGROUND: Skin lesion color is an important feature for diagnosing malignant melanoma. In previous research, skin lesion color was investigated for discriminating malignant melanoma lesions from benign lesions in clinical images. Colors characteristics of melanoma were determined using color histogram analysis over a training set of images. Percent melanoma color and color clustering ratio features were used to quantify the presence of melanoma-colored pixels within skin lesions for skin lesion discrimination. METHODS: In this research, the relative color histogram analysis technique is used to evaluate skin lesion discrimination based on color feature calculations in different regions of the skin lesion in dermoscopy images. The histogram analysis technique is examined for varying training set sizes from the set of 113 malignant melanomas and 113 benign dysplastic nevi images. RESULTS: Experimental results show improved discrimination capability for feature calculations focused in the interior lesion region. Recognition rates for malignant melanoma and dysplastic nevi as high as 87.7% and 74.9%, respectively, are observed for the color clustering ratio computed using the outer 75% uniformly distributed area with a 10% offset within the boundary. CONCLUSIONS: Experimental results appear to indicate that the melanoma color feature information is located in the interior of the lesion, excluding the 10% central-most region. The techniques presented here including the use of relative color and the determination of benign and malignant regions of the relative color histogram may be applicable to any set of images of benign and malignant lesions.     

A basis function feature‐based approach for skin lesion discrimination in dermatology dermoscopy images

Background: Skin lesion color is an important feature for diagnosing malignant melanoma. New basis function correlation features are proposed for discriminating malignant melanoma lesions from benign lesions in dermoscopy images. The proposed features are computed based on correlating the luminance histogram of melanoma or benign labeled relative colors from a specified portion of the skin lesion with a set of basis functions. These features extend previously developed statistical and fuzzy logic‐based relative color histogram analysis techniques for automated mapping of colors representative of melanoma and benign skin lesions from a training set of lesion images. Methods: Using the statistical and fuzzy logic‐based approaches for relative color mapping, melanoma and benign color features are computed over skin lesion region of interest, respectively. Luminance histograms are obtained from the melanoma and benign mapped colors within the lesion region of interest and are correlated with a set of basis functions to quantify the distribution of colors. The histogram analysis techniques and feature calculations are evaluated using a data set of 279 malignant melanomas and 442 benign dysplastic nevi images. Results: Experimental test results showed that combining existing melanoma and benign color features with the proposed basis function features found from the melanoma mapped colors yielded average correct melanoma and benign lesion discrimination rates as high as 86.45% and 83.35%, respectively. Conclusions: The basis function features provide an alternative approach to melanoma discrimination that quantifies the variation and distribution of colors characteristic of melanoma and benign skin lesions.     

Lesion border detection in dermoscopy images using dynamic programming

Background/purpose: Automated border detection is an important and challenging task in the computerized analysis of dermoscopy images. However, dermoscopic images often contain artifacts such as illumination, dermoscopic gel, and outline (hair, skin lines, ruler markings, and blood vessels). As a result, there is a need for robust methods to remove artifacts and detect lesion borders in dermoscopy images. Methods: This automated method consists of three main steps: (1) preprocessing, (2) edge candidate point detection, and (3) tumor outline delineation. First, algorithms to reduce artifacts were used. Second, a least‐squares method (LSM) was performed to acquire edge points. Third, dynamic programming (DP) technique was used to find the optimal boundary of the lesion. Statistical measures based on dermatologist‐drawn borders were utilized as ground‐truth to evaluate the performance of the proposed method. Results: The method is tested on a total of 240 dermoscopic images: 30 benign melanocytic, 50 malignant melanomas, 50 basal cell carcinomas, 20 Merkel cell carcinomas, 60 seborrheic keratosis, and 30 atypical naevi. We obtained mean border detection error of 8.6%, 5.04%, 9.0%, 7.02%, 2.01%, and 3.24%, respectively. Conclusions: The results demonstrate that border detection combined with artifact removal increases sensitivity and specificity for segmentation of lesions in dermoscopy images.     

Colour analysis of skin lesion regions for melanoma discrimination in clinical images

Background: Skin lesion colour is an important feature for diagnosing malignant melanoma. Colour histogram analysis over a training set of images has been used to identify colours characteristic of melanoma, i.e., melanoma colours. A percent melanoma colour feature defined as the percentage of the lesion pixels that are melanoma colours has been used as a feature to discriminate melanomas from benign lesions.
Methods: In this research, the colour histogram analysis technique is extended to evaluate skin lesion discrimination based on colour feature calculations in different regions of the skin lesion. The colour features examined include percent melanoma colour and a novel colour clustering ratio. Experiments are performed using clinical images of 129 malignant melanomas and 129 benign lesions consisting of 40 seborrheic keratoses and 89 nevocellular nevi.
Results: Experimental results show improved discrimination capability for feature calculations focused in the lesion boundary region. Specifically, correct melanoma and benign recognition rates are observed as high as 89 and 83%, respectively, for the percent melanoma colour feature computed using only the outermost, uniformly distributed 10% of the lesion's area.
Conclusions: The experimental results show for the features investigated that the region closest to the skin lesion boundary contains the greatest colour discrimination information for lesion screening. Furthermore, the percent melanoma colour feature consistently outperformed the colour clustering ratio for the different skin lesion regions examined. The clinical application of this result is that clustered colours appear to be no more significant than colours of arbitrary distribution within a lesion.     

Watershed segmentation of dermoscopy images using a watershed technique

Background/purpose: Automatic lesion segmentation is an important part of computer‐based image analysis of pigmented skin lesions. In this research, a watershed algorithm is developed and investigated for adequacy of skin lesion segmentation in dermoscopy images. Methods: Hair, black border and vignette removal methods are introduced as preprocessing steps. The flooding variant of the watershed segmentation algorithm was implemented with novel features adapted to this domain. An outer bounding box, determined by a difference function derived from horizontal and vertical projection functions, is added to estimate the lesion area, and the lesion area error is reduced by a linear estimation function. As a post‐processing step, a second‐order B‐Spline smoothing method is introduced to smooth the watershed border. Results: Using the average of three sets of dermatologist‐drawn borders as the ground truth, an overall error of 15.98% was obtained using the watershed technique. Conclusion: The implementation of the flooding variant of the watershed algorithm presented here allows satisfactory automatic segmentation of pigmented skin lesions.     

An improved objective evaluation measure for border detection in dermoscopy images

Background: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Owing to the difficulty and subjectivity of human interpretation, dermoscopy image analysis has become an important research area. One of the most important steps in dermoscopy image analysis is the automated detection of lesion borders. Although numerous methods have been developed for the detection of lesion borders, very few studies were comprehensive in the evaluation of their results.
Methods: In this paper, we evaluate five recent border detection methods on a set of 90 dermoscopy images using three sets of dermatologist-drawn borders as the ground truth. In contrast to previous work, we utilize an objective measure, the normalized probabilistic rand index, which takes into account the variations in the ground-truth images.
Conclusion: The results demonstrate that the differences between four of the evaluated border detection methods are in fact smaller than those predicted by the commonly used exclusive-OR measure.     

Border detection in dermoscopy images using statistical region merging

Background: As a result of advances in skin imaging technology and the development of suitable image processing techniques, during the last decade, there has been a significant increase of interest in the computer-aided diagnosis of melanoma. Automated border detection is one of the most important steps in this procedure, because the accuracy of the subsequent steps crucially depends on it.
Methods: In this article, we present a fast and unsupervised approach to border detection in dermoscopy images of pigmented skin lesions based on the statistical region merging algorithm.
Results: The method is tested on a set of 90 dermoscopy images. The border detection error is quantified by a metric in which three sets of dermatologist-determined borders are used as the ground-truth. The proposed method is compared with four state-of-the-art automated methods (orientation-sensitive fuzzy c-means, dermatologist-like tumor extraction algorithm, meanshift clustering, and the modified JSEG method).
Conclusion: The results demonstrate that the method presented here achieves both fast and accurate border detection in dermoscopy images.     

Colour histogram analysis for melanoma discrimination in clinical images

Background: Malignant melanoma, the most deadly form of skin cancer, has a good prognosis if treated in the curable early stages. Colour provides critical discriminating information for the diagnosis of malignant melanoma.
Methods: This research introduces a three-dimensional relative colour histogram analysis technique to identify colours characteristic of melanomas and then applies these 'melanoma colours' to differentiate benign skin lesions from melanomas. The relative colour of a skin lesion is determined based on subtracting a representative colour of the surrounding skin from each lesion pixel. A colour mapping for 'melanoma colours' is determined using a training set of images. A percent melanoma colour feature, defined as the percentage of the lesion pixels that are melanoma colours, is used for discriminating melanomas from benign lesions. The technique is evaluated using a clinical image data set of 129 malignant melanomas and 129 benign lesions consisting of 40 seborrheic keratoses and 89 nevocellular nevi.
Results: Using the percent melanoma colour feature for discrimination, experimental results yield correct melanoma and benign lesion discrimination rates of 84.3 and 83.0%, respectively.
Conclusions: The results presented in this work suggest that lesion colour in clinical images is strongly related to the presence of melanoma in that lesion. However, colour information should be combined with other information in order to further reduce the false negative and false positive rates.     

Detection of asymmetric blotches (asymmetric structureless areas) in dermoscopy images of malignant melanoma using relative color

BACKGROUND: Dermoscopy, also known as dermatoscopy or epiluminescence microscopy (ELM), is a non-invasive, in vivo technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One prominent feature useful for melanoma detection in dermoscopy images is the asymmetric blotch (asymmetric structureless area). METHOD: Using both relative and absolute colors, blotches are detected in this research automatically by using thresholds in the red and green color planes. Several blotch indices are computed, including the scaled distance between the largest blotch centroid and the lesion centroid, ratio of total blotch areas to lesion area, ratio of largest blotch area to lesion area, total number of blotches, size of largest blotch, and irregularity of largest blotch. RESULTS: The effectiveness of the absolute and relative color blotch features was examined for melanoma/benign lesion discrimination over a dermoscopy image set containing 165 melanomas (151 invasive melanomas and 14 melanomas in situ) and 347 benign lesions (124 nevocellular nevi without dysplasia and 223 dysplastic nevi) using a leave-one-out neural network approach. Receiver operating characteristic curve results are shown, highlighting the sensitivity and specificity of melanoma detection. Statistical analysis of the blotch features are also presented. CONCLUSION: Neural network and statistical analysis showed that the blotch detection method was somewhat more effective using relative color than using absolute color. The relative-color blotch detection method gave a diagnostic accuracy of about 77%.     

Approximate lesion localization in dermoscopy images

Background: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Because of the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis.
Methods: In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms.
Results: The method is tested on a set of 428 dermoscopy images. The localization error is quantified by a metric that uses dermatologist-determined borders as the ground truth.
Conclusion: The results demonstrate that the method presented here achieves both fast and accurate localization of lesions in dermoscopy images.     

The use of digital dermoscopy for the follow-up of congenital nevi: a pilot study

One of the main problems in the management of congenital nevi is the potential risk for malignant transformation and the resulting need for follow-up examination. Dermoscopy is a noninvasive technique that has been shown to be useful for the follow-up of benign melanocytic skin lesions as well as the early diagnosis of malignant melanoma. Therefore we thought to use the digital dermoscopy (DD) technique for the follow-up of congenital nevi. For documentation purposes we registered an overview, and the following standardized dermoscopic images of every lesion: representative architectural pattern, border of the lesion, and regions of "special interest." In all instances the examination with digital dermoscopy was well tolerated by the patients and the integration of the parents to the "live" examination on the computer screen was appreciated. The follow-up was easy to perform with these standardized documents. We showed the feasibility of follow-up of congenital nevi using digital dermoscopy. Furthermore, we identified three different patterns as well as some typical structures seen in congenital nevi by DD.     

Differentiation of melanoma from benign mimics using the relative‐color method

Background: Previous studies have successfully classified 86% of malignant melanomas using a relative‐color segmentation method, by feature extraction from photographic images in the automatic identification of skin tumors. These studies were extended by applying the relative‐color method to dermoscopic images of melanoma grouped with melanoma in situ and clark nevus lesions in dermoscopic images allow more control over lighting variations, which contribute to lesion misclassification. Dermoscopic images then enable a more detailed examination of the structure of skin lesions, provide much more structural detail within lesions, and contain visual information that cannot be seen in photographic images. This present work extends the previous studies by applying relative‐color feature extraction to dermoscopic images to differentiate among melanoma, seborrheic keratoses and Reed/Spitz nevi. Objective: To develop a method for automatically differentiating among malignant melanoma, seborrheic keratoses and Reed/Spitz nevi, using digitized, color, dermoscopic images. Methods: Images underwent preprocessing, tumor segmentation, feature extraction and tumor classification. The relative‐color method was used in the segmentation stage. Classification was accomplished by taking the inner products of model tumor feature vectors with test‐image tumor vectors followed by the nearest‐neighbor classification method. Results: The classification rates of melanoma, seborrheic keratoses and Reed/Spitz nevi images mixed together, were 60%, 58.3% and 80%, respectively. Classification of melanoma and Reed/Spitz nevi mixed, were 70% and 90%, respectively. Classification rates were the best when melanoma was being differentiated from seborrheic keratoses. These rates were 100% and 88.9%, respectively. Conclusion: Dermoscopic rather than photographic images were preprocessed, using a hair‐removal technique. They were then converted to relative‐color images, which were segmented using the principal components transform and median split, followed by morphological filtering. After processing, the multi‐dimensional tumor feature space described herein was used to differentiate the tumors. The high success rates for differentiating seborrheic keratoses from melanoma show that the use of dermoscopic images has a strong promise in enabling prescreening, as well as automated assistance and significant improvement in tumor diagnosis in clinics.     

A systematic heuristic approach for feature selection for melanoma discrimination using clinical images

BACKGROUND: Numerous features are derived from the asymmetry, border irregularity, color variegation, and diameter of the skin lesion in dermatology for diagnosing malignant melanoma. Feature selection for the development of automated skin lesion discrimination systems is an important consideration. METHODS: In this research, a systematic heuristic approach is investigated for feature selection and lesion classification. The approach integrates statistical-, correlation-, histogram-, and expert system-based components. Using statistical and correlation measures, interrelationships among features are determined. Expert system analysis is performed to identify redundant features. The feature selection process is applied to 19 shape and color features for a clinical image data set containing 355 malignant melanomas, 125 basal cell carcinomas, 177 dysplastic nevi, 199 nevocellular nevi, 139 seborrheic keratoses, and 45 vascular lesions. RESULTS: Experimental results show reduced lesion classification error rates based on condensing the shape and color feature set from 19 features to 13 features using the feature selection process. Specifically, average test lesion classification error rates for discriminating malignant melanoma from non-melanoma lesions were reduced from 26.6% for 19 features to 23.2% for 13 features over five randomly generated training and test sets. CONCLUSIONS: The experimental results show that the systematic heuristic approach for feature reduction can be successfully applied to achieve improved lesion discrimination. The feature reduction technique facilitates the elimination of redundant information that may inhibit lesion classification performance. The clinical application of this result is that automated skin lesion classification algorithm development can be fostered with systematic feature selection techniques.     

Predictive power of irregular border shapes for malignant melanomas

BACKGROUND/PURPOSE: The Irregularity Index is a measure of border irregularity from pigmented skin lesion images. The measure attempts to quantify the degree of irregularity of the structural indentations and protrusions along a lesion border. A carefully designed study has shown that the parameters derived from the Irregularity Index were highly correlated with expert dermatologists' notion of border shape. This paper investigates the predictive power of these parameters on a set of data with known histological diagnosis. METHODS: A set of 188 pigmented skin lesions (30 malignant melanomas and 158 benign lesions) was selected for the study. Their images were segmented and their border shapes were analysed by the Irregularity Index, producing four border irregularity parameters. The predictive power of these four parameters was estimated by a series of statistical tests. RESULTS: The mean values of the four border irregularity parameters were significantly different between the melanoma group and the benign lesion group. When using the four parameters to predict its disease status, the leave-one-out classification rate was 82.4%, and the area under the receiver operating characteristic curve was 0.77. A malignant melanoma was 8.9 times more likely to have an irregular border than a benign lesion. CONCLUSION: This study confirmed that border irregularity is an important clinical feature for the diagnosis of malignant melanoma. It also indicates that the computer-derived measures based on the Irregularity Index capture to certain extent the kind of irregularity which is exhibited by melanomas.     

Cutaneous melanoma: making a clinical diagnosis, present and future

The minimum requirement for the general dermatologist for clinically assessing pigmented skin lesions is dermoscopy. In expert hands, this technique has been shown to improve both the sensitivity and specificity for the diagnosis of melanoma. This is also reflected by lower benign melanoma excision ratios and decreased excision rates. Evidence is mounting for the routine use of total body skin photography for patients with a very high risk of developing cutaneous melanoma. Both long-term (12 months) and short-term (3 months) digital dermoscopy monitoring has been shown to allow the detection of dermoscopically featureless melanoma and is central for the clinical assessment of melanocytic lesions at the Sydney Melanoma Diagnostic Center. The use of automated instruments for the diagnosis of cutaneous melanoma is still in an experimental phase, and its utility is dependent on the evidence that such instruments give a clinically useful expert second opinion. Currently, other noninvasive diagnostic techniques, such as in vivo confocal scanning laser microscopy, are reserved for clinical research settings.     

Digital dermoscopy analysis of atypical pigmented skin lesions: a stepwise logistic discriminant analysis approach

Background: Digital microscopy is a non-invasive diagnostic technique enabling determination of characteristics that cannot be appreciated by direct observation. If correctly applied, this technique can be useful for the diagnosis of pigmented skin lesions.
Purpose: To evaluate the utility of digital microscopy for analysing atypical benign and malignant pigmented skin lesions exploiting digital numerical filtering and automatic measurements.
Methods: Forty-eight parameters were identified as possible discriminating variables, and were grouped in four categories: geometries, colours, textures, and islands of colour. Statistical analysis was used to identify the variables with the highest discriminating power.
Results: The high quality of the digital image made it possible to observe diagnostic signs in pigmented skin lesion images, acquired by the present technique, in great detail. Specially designed filtering enhanced certain diagnostic patterns. Stepwise discriminant analysis selected only 10 variables (the means of these variables were higher in melanomas than in nevi).
Conclusions: The combined use of digital dermoscopy and stepwise logistic discriminant analysis made it possible to single out the best objective variables for distinguishing atypical nevi and early melanoma.     

Skin lesion classification using relative color features

BACKGROUND/PURPOSE: Clinically, it is difficult to differentiate the early stage of malignant melanoma and certain benign skin lesions due to similarity in appearance. Our research uses image analysis of clinical skin images and relative color-based pattern recognition techniques to enhance the images and improve differentiation of these lesions. METHODS: First, the relative color images were created from digitized photographic images. Then, they were segmented into objects and morphologically filtered. Next, the relative color features were extracted from the objects to form two different feature spaces; a lesion feature space and an object feature space. The two feature spaces serve as two data models to be analyzed to determine the best features. Finally, we used a statistical analysis model of relative color features, which better classifies the various types of skin lesions. RESULTS/CONCLUSIONS: The best features found for differentiation of melanoma and benign skin lesions from this study are area, mean in the red and blue bands, standard deviation in the red and green bands, skewness in the green band, and entropy in the red band. With the relative color feature algorithm developed, the best results were obtained with a multi-layer perceptron neural network model. This showed an overall classification success of 79%, with 70% of the benign lesions successfully classified, and 86% of malignant melanoma successfully classified.     

Segmentation of dermatoscopic images by frequency domain filtering and k‐means clustering algorithms

Background/Purpose: Since the introduction of epiluminescence microscopy (ELM), image analysis tools have been extended to the field of dermatology, in an attempt to algorithmically reproduce clinical evaluation. Accurate image segmentation of skin lesions is one of the key steps for useful, early and non‐invasive diagnosis of coetaneous melanomas. Methods: This paper proposes two image segmentation algorithms based on frequency domain processing and k‐means clustering/fuzzy k‐means clustering. The two methods are capable of segmenting and extracting the true border that reveals the global structure irregularity (indentations and protrusions), which may suggest excessive cell growth or regression of a melanoma. As a pre‐processing step, Fourier low‐pass filtering is applied to reduce the surrounding noise in a skin lesion image. Results: A quantitative comparison of the techniques is enabled by the use of synthetic skin lesion images that model lesions covered with hair to which Gaussian noise is added. The proposed techniques are also compared with an established optimal‐based thresholding skin‐segmentation method. It is demonstrated that for lesions with a range of different border irregularity properties, the k‐means clustering and fuzzy k‐means clustering segmentation methods provide the best performance over a range of signal to noise ratios. The proposed segmentation techniques are also demonstrated to have similar performance when tested on real skin lesions representing high‐resolution ELM images. Conclusion: This study suggests that the segmentation results obtained using a combination of low‐pass frequency filtering and k‐means or fuzzy k‐means clustering are superior to the result that would be obtained by using k‐means or fuzzy k‐means clustering segmentation methods alone.