Melanoma and seborrheic keratosis differentiation using texture features

Purpose: To explore texture features in two-dimensional images to differentiate seborrheic keratosis from melanoma.
Methods: A systematic approach to consistent classification of skin tumors is described. Texture features, based on the second-order histogram, were used to identify the features or a combination of features that could consistently differentiate a malignant skin tumor (melanoma) from a benign one (seborrheic keratosis). Two hundred and seventy-one skin tumor images were separated into training and test sets for accuracy and consistency. Automatic induction was applied to generate classification rules. Data analysis and modeling tools were used to gain further insight into the feature space.
Result and Conclusions: In all, 85–90% of seborrheic keratosis images were correctly differentiated from the malignant skin tumors. The features correlation_average, correlation_range, texture_energy_average and texture_energy_range were found to be the most important features in differentiating seborrheic keratosis from melanoma. Over-all, the seborrheic keratosis images were better identified by the texture features than the melanoma images.     

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.     

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.     

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.     

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.     

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.     

Using 3D differential forms to characterize a pigmented lesion in vivo

Background/purpose: After the formulation of ABCD rules, many new feature extraction methods are emerging to describe the asymmetry, border irregularity, color variation and diameter of malignant melanoma. In this paper, a new research direction orthogonal to ABCD rules that characterizes 3D local disruption of skin surfaces to realize automatic recognition of melanoma is described.
Methods: This paper examines 3D differential forms of skin surfaces to characterize the local geometrical properties of melanoma. Firstly, 3D data of skin surfaces are obtained using a photometric stereo device. Then differential forms of lesion surfaces are determined to describe the geometrical texture patterns involved. Using only these geometrical features, a simple least-squared error-based linear classifier can be constructed to realize the classification of malignant melanomas and benign lesions.
Results: As with the 3D data of 35 melanoma and 66 benign lesion samples collected from local pigmented lesion clinics, the optimal sensitivity and specificity of the constructed linear classifier are 71.4% and 86.4%, respectively. The total area enclosed by the corresponding receiver operating characteristics curve is 0.823.
Conclusion: This study indicates that differential forms obtained from 3D data are very promising in characterizing melanoma. Combining these features with other skin features such as border irregularity and color variation might further improve the accuracy and reliability of the automatic diagnosis of melanoma.     

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.     

Malignant blue nevus with lymph node metastases

Background:  Malignant blue nevi arise within cellular blue nevi and contain atypical mitoses, necrosis, nuclear pleomorphism and prominent nucleoli. Malignant blue nevus has been described as a distinct identity, a rare form of malignant melanoma, and a misdiagnosed melanoma.
Methods:  We present a patient with metastatic malignant blue nevus and studies on the histopathologic, immunohistochemical, and molecular features of the neoplasm.
Results:  Histology showed a malignant blue nevus arising in a combined intradermal and cellular blue nevus. CD117 (c-kit) staining showed diffuse cytoplasmic expression within the cellular blue nevus, decreased staining in the malignant component, and variable positivity within the lymph node metastases. Molecular loss of heterozygosity analysis showed different allelic patterns at the hOGG-1 locus between the melanoma and control skin specimens with a varying heterozygous allelic pattern in both the benign and malignant blue nevus.
Conclusions:  Our case of malignant blue nevus with lymph node metastasis involved mutation of the hOGG-1 DNA repair gene. CD117 showed decreased staining of the primary malignant blue nevus with marked upregulation in the metastatic lesion, unlike most metastatic melanomas. Further study is needed to determine if hOGG-1 mutation or c-kit upregulation play a role in the pathogenesis of dendritic melanocytic lesions (either benign or malignant).     

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.     

Can early malignant melanoma be differentiated from atypical melanocytic nevus by in vivo techniques?

Background/aims: Differentiation between early (Breslow thickness less than 1 mm) malignant melanoma (MM) and atypical melanocytic nevus (AMN) remains a challenge even to trained clinicians. The purpose of this study is to determine the feasibility of reliable discrimination between early MM and AMN with noninvasive, objective, automatic machine vision techniques.
Methods: A data base of 104 digitized dermoscopic color transparencies of melanocytic lesions was used to develop and test our computer-based algorithms for classification of such lesions as malignant (MM) or benign (AMN). Histopathologic diagnoses (30 MM and 74 AMN) were used as the "gold standard" for training and testing the algorithms.
Results: A fully automatic, objective technique for differentiating between early MM and AMN from their dermoscopic digital images was developed. The multiparameter linear classifier was trained to provide 100% sensitivity for MM. In the blind test, this technique did not miss a single MM and its specificity was comparable to that of skilled dermatologists.
Conclusions: Reliable differentiation between early MM and AMN with high sensitivity is possible using machine vision techniques to analyze digitized dermoscopic lesion images.     

Detection of solid pigment in dermatoscopy images using texture analysis

Background/aims: Epiluminescence microscopy (ELM), also known as dermoscopy or dermatoscopy, is a non‐invasive, in vivo technique, that permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. ELM offers a completely new range of visual features. One such feature is the solid pigment, also called the blotchy pigment or dark structureless area. Our goal was to automatically detect this feature and determine whether its presence is useful in distinguishing benign from malignant pigmented lesions. Methods: Here, a texture‐based algorithm is developed for the detection of solid pigment. The factors d and a used in calculating neighboring gray level dependence matrix (NGLDM) numbers were chosen as optimum by experimentation. The algorithms are tested on a set of 37 images. A new index is presented for separation of benign and malignant lesions, based on the presence of solid pigment in the periphery. Results: The NGLDM large number emphasis N2 was satisfactory for the detection of the solid pigment. Nine lesions had solid pigment detected, and among our 37 lesions, no melanoma lacked solid pigment. The index for separation of benign and malignant lesions was applied to the nine lesions. We were able to separate the benign lesions with solid pigment from the malignant lesions with the exception of only one lesion, a Spitz nevus that mimicked a malignant melanoma. Conclusion: Texture methods may be useful in detecting important dermatoscopy features in digitized images and a new index may be useful in separating benign from malignant lesions. Testing on a larger set of lesions is needed before further conclusions can be made.     

Obtaining malignant melanoma indicators through statistical analysis of 3D skin surface disruptions

Background/purpose: It has been observed that disruptions in skin patterns are larger for malignant melanoma (MM) than benign lesions. In order to extend the classification results achieved for 2D skin patterns, this work intends to investigate the feasibility of lesion classification using 3D skin surface texture, in the form of surface normals acquired from a previously built six-light photometric stereo device.
Material and methods: The proposed approach seeks to separate MM from benign lesions through analysis of the degree of surface disruptions in the tilt and slant direction of surface normals, so called skin tilt pattern and skin slant pattern. A 2D Gaussian function is used to simulate a normal region of skin for comparison with a lesion's observed tilt and slant patterns. The differences associated with the two patterns are estimated as the disruptions in the tilt and slant pattern respectively for lesion classification.
Results: Preliminary studies on 11 MMs and 28 benign lesions have given Receiver operating characteristic areas of 0.73 and 0.85 for tilt and slant pattern, respectively, which are better than 0.65 previously obtained for the skin line direction using the same samples.
Conclusions: This paper has demonstrated an important application of 3D skin texture for computer-assisted diagnosis of MM in vivo . By taking advantage of the extra dimensional information, preliminary studies suggest that some improvements over the existing 2D skin line pattern approach for the differentiation between MM and benign lesions.     

Analysis of skin line pattern for lesion classification

Background/purpose: It has been observed that skin patterning tends to be disrupted by malignant but not by benign skin lesions. This suggests that measurements of skin pattern disruption on simply captured white light optical skin images could be a useful contribution to a diagnostic feature set. Previous work using a measurement of line strength by a consistent high-value profiling technique followed by local variance measurement or a region agglomerative classifier to measure skin line pattern disruption was extremely promising but computationally intensive, suggesting that the idea of measuring skin pattern disruption was useful but a simpler method was required.
Methods: The skin pattern was extracted by high-pass filtration and enhanced by adaptive anisotropic (spatial variant) filtering which smoothes along skin lines but not across them. The skin line main direction and direction variance were estimated using a local image gradient matrix and the difference of these measures across the lesion image boundary was used as a lesion classifier.
Results: A set of images of malignant melanoma and benign naevi were processed as above and the scatter plot of results in a two-dimensional feature (line direction and line variation difference) space showed excellent separation of benign and malignant lesions. An ROC plot enclosed an area of 0.88.
Conclusions: The experimental results showed that the local line direction and the local line variation were promising features for distinguishing malignant melanoma from benign lesion and the methods used were effective and computationally low-cost.     

Combination of features from skin pattern and ABCD analysis for lesion classification

BACKGROUND/PURPOSE: It is known that the standard features for lesion classification are ABCD features, that is, asymmetry, border irregularity, colour variegation and diameter of lesion. However, the observation that skin patterning tends to be disrupted by malignant but not by benign skin lesions suggests that measurements of skin pattern disruption on simply captured white light optical skin images could be a useful contribution to a diagnostic feature set. Previous work using both skin line direction and intensity for lesion classification was encouraging. But these features have not been combined with the ABCD features. This paper explores the possibility of combing features from skin pattern and ABCD analysis to enhance classification performance. METHODS: The skin line direction and intensity were extracted from a local tensor matrix of skin pattern. Meanwhile, ABCD analysis was conducted to generate six features. They were asymmetry, border irregularity, colour (red, green and blue) variegations and diameter of lesion. The eight features of each case were combined using a principal component analysis (PCA) to produce two dominant features for lesion classification. RESULTS: A larger set of images containing malignant melanoma (MM) and benign naevi were processed as above and the scatter plot in a two-dimensional dominant feature space showed excellent separation of benign and malignant lesions. An ROC (receiver operating characteristic) plot enclosed an area of 0.94. CONCLUSIONS: The classification results showed that the individual features have a limited discrimination capability and the combined features were promising to distinguish MM from benign lesion.     

Melanocytic nevi with features of Spitz nevi and Clark's/dysplastic nevi ("Spark's" nevi)

Background: Nevi with cytologic characteristics of Spitz nevus and architectural features of Clark's/dysplastic nevus are not well recognized in the literature.
Methods: Twenty-seven nevi with characteristics of Spitz nevus and Clark's/dysplastic nevus are reviewed.
Results: The patients' mean age was 33 years, and 17/27(63%) patients were female. Lesions were most frequent on the trunk and lower extremities. Histopathologically, these nevi were composed of large, monomorphous spindled and/or epithelioid melanocytes. Spindle cells were often oriented parallel to the epidermis, with fused rete and lamellar fibroplasias. Lateral extension of the junctional component was a feature of compound lesions. An average of 10 years of clinical follow up in 12 patients revealed no recurrence or metastasis.
Conclusions: Recognition of this type of nevus is important to avoid confusion with malignant melanoma.     

Enhancement of lesion classification using divergence, curl and curvature of skin pattern

BACKGROUND/PURPOSE: The observation that skin pattern tends to be disrupted by malignant but not by benign skin lesions suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature set. Previous work which generated a flow field of skin pattern using a measurement of local line direction and variation determined by the minimum eigenvalue and its corresponding eigenvector of the local tensor matrix to measure skin pattern disruption was computationally low cost and encouraging. This paper explores the possibility of extracting new features from the first and second differentiations of this flow field to enhance classification performance. METHODS: The skin pattern was extracted from WLC skin images by high-pass filtering. The skin line direction was estimated using a local image gradient matrix to produce a flow field of skin pattern. Divergence, curl, mean and Gaussian curvatures of this flow field were computed from the first and second differentiations of this flow field. The difference of these measures combined with skin line direction across the lesion image boundary was used as a lesion classifier. RESULTS: A set of images of malignant melanoma and benign naevi were analysed as above and the scatter plot in a two-dimensional dominant feature space using principal component analysis showed excellent separation of benign and malignant lesions. A receiver operating characteristic plot enclosed an area of 0.96. CONCLUSIONS: The experimental results show that the divergence, curl, mean and Gaussian curvatures of the flow field can increase lesion classifier accuracy. Combined with skin line direction they are promising features for distinguishing malignant melanoma from benign lesions and the methods used are computationally efficient which is important if their use is to be considered in clinical practice.     

Correlation of image analysis features and visual morphology in melanocytic skin tumours using in vivo confocal laser scanning microscopy

Background/purpose: In vivo confocal laser scanning microscopy (CLSM) represents a novel imaging tool that allows the non-invasive examination of skin cancer morphology at a quasi histological resolution without biopsy. Previous studies dealt with the search for diagnostic, but subjective visual criteria. In this study we examined the correlation between objectively reproducible image-analysis features und visual morphology in melanocytic skin tumours using CLSM.
Methods: Eight hundred and fifty-seven CLSM tumour images including 408 benign nevi and 449 melanoma images were evaluated. Image analysis was based on features of the wavelet transform and classification tree analysis (CART) was used for classification purposes. In a second step, morphologic details of CLSM images, which have turned out to be of diagnostic significance by the classification algorithm were evaluated.
Results: CART analysis of the whole set of CLSM images correctly classified 97.55% of all melanoma images and 96.32% of all nevi images. Seven classification tree nodes seemed to indicate benign nevi, whereas six nodes were suggestive for melanoma morphology. The visual examination of selected nodes demonstrated that monomorphic melanocytic cells and melanocytic cell nests are characteristic for benign nevi whereas polymorphic melanocytic cells, disarray of melanocytic architecture and poorly defined or absent keratinocyte cell borders are characteristic for melanoma.
Conclusion: Well-known, but subjective CLSM criteria could be objectively reproduced by image analysis features and classification tree analysis. Moreover, features not accessible to the human eye seem to contribute to classification success.     

Dermatoscopy turns histopathologist's attention to the suspicious area in melanocytic lesions

BACKGROUND: Histopathologically, the diagnosis of nevus-associated melanoma or melanoma close to a common nevus can be missed if the specimen is cut in a nonrepresentative area or if the section shows only the associated common nevus. OBJECTIVE: To find out whether dermatoscopy of suspicious areas within a nevus can improve the histological diagnosis of malignant melanocytic lesions of the skin. MATERIALS: The study was based on dermatoscopic images of more than 2000 benign and 115 malignant pigmented lesions and a collection of corresponding histopathologic slides. METHODS: The dermatoscopic images and the corresponding histopathologic diagnoses were compared. In case of differences, the histopathologic findings were reevaluated and compared with the dermatoscopic findings. RESULTS: Three cases were identified in which melanoma could have been histopathologically missed as a result of improper sectioning. After the dermatoscopic findings were evaluated, the specimens were reembedded and further sections were obtained. Finally, nevus-associated melanoma or melanoma close to a common nevus was diagnosed. CONCLUSIONS: Specific dermatoscopic patterns of malignancy can be found in highly suspicious areas, eg, broadened networks, radial streaming, pseudopods, or dots located at the periphery. The dermatoscopic-histopathologic correlation can improve the diagnosis of melanoma. Therefore, the clinician should point to the most suspicious area with a drawing or image, and the suspected diagnosis of melanoma and the history of the lesion should be also mentioned.