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.     

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.     

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.     

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.     

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.     

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%.     

Intraepidermal distribution patterns of melanocytes in the melanocytic lesions on the sole: proposed criteria for histopathologic diagnosis of plantar malignant melanoma in situ

Eighty-eight melanocytic lesions on the soles of Japanese were histologically investigated. Increased numbers of solitary melanocytes above the basal layer of the epidermis were often found in the benign melanocytic nevi on the sole: in 5 lesions of 9 congenital melanocytic nevi, 22 of 65 acquired melanocytic nevi, and 1 of 5 dysplastic nevi. In addition, a moderate degree of nuclear atypia of proliferating melanocytes was frequently observed in the benign melanocytic nevi on the sole: in 3 lesions of 9 congenital melanocytic nevi, 17 of 65 acquired melanocytic nevi, and 2 of 5 dysplastic nevi. Therefore it cannot be said that increased numbers of solitary atypical melanocytes above the basal layer is a characteristic histologic feature of early malignant melanoma in situ. Combining the intraepidermal distribution patterns of melanocytes and maximum diameter of the lesion, we propose criteria for histopathologic diagnosis of plantar malignant melanoma in situ.     

Quantitative discrimination of pigmented lesions using three-dimensional high-resolution ultrasound reflex transmission imaging

High-resolution ultrasound-reflex transmission imaging is a non-invasive method that can be performed in vivo. We have adapted and refined this technique for skin imaging. Scans can be analyzed to produce objective parameters. Previous work has highlighted sonographic differences between benign and malignant lesions. The aim of this study was to produce and test numerical parameters from ultrasound skin images that would quantify the acoustic differences between common pigmented lesions, which may aid their discrimination from melanoma. We report our findings for randomly selected patients referred from primary care with suspected melanoma. Those subsequently classified as malignant melanoma (MM), seborrheic keratosis (SK), and benign nevi by a consultant dermatologist (n=87) were imaged by high-resolution ultrasound-reflex transmission imaging. Using surrounding normal skin as a control, numerical sonographic parameters were derived for each lesion giving a relative measure of surface sound reflectance, intra-lesional sound reflection, total sound attenuation, and the relative uniformity of each parameter across the tumor. Significant quantitative differences existed between benign and malignant pigmented lesions studied. Sufficient discrimination was produced between MM (n=25), SKs (n=24) and other benign-pigmented lesions (n=38) to potentially reduce the referral of benign tumors by 65% without missing melanoma.     

Automatic lesion boundary detection in dermoscopy images using gradient vector flow snakes

BACKGROUND: Malignant melanoma has a good prognosis if treated early. Dermoscopy images of pigmented lesions are most commonly taken at x 10 magnification under lighting at a low angle of incidence while the skin is immersed in oil under a glass plate. Accurate skin lesion segmentation from the background skin is important because some of the features anticipated to be used for diagnosis deal with shape of the lesion and others deal with the color of the lesion compared with the color of the surrounding skin. METHODS: In this research, gradient vector flow (GVF) snakes are investigated to find the border of skin lesions in dermoscopy images. An automatic initialization method is introduced to make the skin lesion border determination process fully automated. RESULTS: Skin lesion segmentation results are presented for 70 benign and 30 melanoma skin lesion images for the GVF-based method and a color histogram analysis technique. The average errors obtained by the GVF-based method are lower for both the benign and melanoma image sets than for the color histogram analysis technique based on comparison with manually segmented lesions determined by a dermatologist. CONCLUSIONS: The experimental results for the GVF-based method demonstrate promise as an automated technique for skin lesion segmentation in dermoscopy images.     

How well do physicians recognize melanoma and other problem lesions?

The alarming increase in the incidence of cutaneous malignant melanoma in the United States emphasizes the importance of its early detection and treatment. Early detection requires accurate clinical recognition of both malignant and precancerous skin lesions (dysplastic nevi). This study presents data on dermatologists' and nondermatologists' ability to diagnose skin lesions. A total of 105 nondermatologist physicians, from first-year residents to practicing physicians, and forty-eight dermatologists were asked to identify color slides or photographs of eleven cutaneous lesions, including malignant melanomas, dysplastic nevi, and innocuous lesions such as seborrheic keratoses and common moles. Diagnosis of cutaneous lesions was generally inaccurate among nondermatologists. Only 38% correctly identified four or more of the six melanomas as melanoma of any type, and 58% were unable to diagnose dysplastic nevi. Only 17% categorized their relevant training as excellent or good. Improved training in the diagnosis of skin lesions for practicing physicians and house staff is required if mortality from malignant melanoma is to be decreased in the United States.     

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.     

Laypersons' perceptual discrimination of pigmented skin lesions

BACKGROUND: Most cutaneous malignant melanomas of the skin are visible and should, at least in theory, be possible to detect with the naked eye. OBJECTIVE: This study was conducted to learn more about laypersons' ability to discriminate between benign pigmented lesions and malignant ones. METHODS: Four groups of laypersons (n = 120) were asked to evaluate pictures of different types of pigmented skin lesions, before and after they received information about the ABCD (asymmetry, border irregularity, color variegation, and diameter greater than 6 mm) criteria, with respect to the necessity of action. RESULTS: The respondents made adequate assessments of melanomas but overestimated the danger of benign pigmented skin lesions. Information about the ABCD criteria enhanced their ability to make adequate assessments. CONCLUSION: People seem to make adequate decisions concerning how to act if they have a melanoma. On the other hand, common moles and dysplastic nevi were harder to discriminate. Providing information to the public about the features of melanomas, in accordance with the ABCD criteria, might help laypersons in their perceptual discrimination of skin lesions.     

Digital computer analysis of dermatoscopical images of 260 melanocytic skin lesions; perimeter/area ratio for the differentiation between malignant melanomas and melanocytic nevi

BACKGROUND: Digital computer analysis of dermatoscopical images has been reported to facilitate the differential diagnosis of pigmented skin lesions in recent years. OBJECTIVE: The aim of our study was to perform digital computer analysis of a set of different melanocytic lesions and compare the objective results. METHODS: The set of 260 melanocytic lesions (150 excised difficult cases (46 melanomas, 47 atypical nevi, 57 common nevi and 110 unexcised common nevi) was automatically analysed by the digital dermatoscopical system microDERM. We searched for differences in asymmetry, size, compactness and colour distribution. Perimeter/area ratio was calculated. RESULTS: The perimeter/area ratio was detected as the most important criterion for differentiation between malignant and benign melanocytic lesions (sensitivity 91.3% and specificity 90.7% for malignant melanomas vs. all benign nevi; sensitivity 91.3% and specificity 80.8% for melanomas vs. clinically atypical nevi). Differences in size of the lesion, shape and asymmetry of colour were found and statistically verified. Using step-wise logistic regression the formula for calculation of probability of malignant nature of every analysed lesion was constructed. CONCLUSION: The perimeter/area ratio is a simple parameter for the differential diagnosis of melanocytic skin lesions.     

Diagnostic tissue elements in melanocytic skin tumors in automated image analysis

In tissue counter analysis, digital images are divided into subregions (elements), and the digital information in each element is used for statistical analysis. In this study, we assessed the morphologic details of tissue elements that have turned out to be of diagnostic significance in the discrimination of benign common nevi and malignant melanoma. After creation of a data set based on a total of 12,000 cellular elements obtained from 100 benign common nevi and 100 malignant melanomas, classification and regression tree (CART) analysis was performed to differentiate between cellular elements of nevi and melanoma. In a second step, the slides were re-evaluated by the decision tree; cellular elements suggestive either for benign common nevi or for malignant melanoma were highlighted on zoomed images of the whole sections, and the individual elements were displayed in galleries. Eight groups of elements (so-called terminal nodes) seemed to indicate benign common nevi, whereas seven terminal nodes were suggestive for malignant melanoma. The elements of nodes suggestive for benign nevi largely contained nevus cells with amphiphilic cytoplasm intermingled with fibrillary material, whereas the elements of the nodes suggestive for malignant lesions often showed hyperchromatism, perinuclear halos, heavy pigmentation, or a lymphohistiocytic infiltrate. Tissue counter analysis automatically detects tissue elements that are in accordance with morphologic criteria used in conventional histopathology for diagnostic discrimination.     

Cyclin D1 and D3 expression in melanocytic skin lesions

Cyclins, cyclin-dependent kinases, as well as proteins cooperating with them are responsible for cell cycle regulation which is crucial for normal development, injury repair, and tumorigenesis. D-type cyclins regulate G1 cell cycle progression by enhancing the activities of cyclin-dependent kinases, and their expression is frequently altered in tumors. Disturbances in cyclin expression were also reported in melanocytic skin lesions. The objective of the study was to evaluate the expression of cyclins D1 and D3 in common, dysplastic, and malignant melanocytic skin lesions. Forty-eight melanocytic skin lesions including common nevi (10), dysplastic nevi (24), and melanomas (14) were diagnosed by dermoscopy and excised. Expression of cyclin D1 and D3 was detected by immunohistochemistry and quantified as percentage of immunostained cell nuclei in each sample. In normal skin, expression of cyclins D1 and D3 was not detected. The mean percentage of cyclin D1-positive nuclei was 7.75% for melanoma samples, 5% for dysplastic nevi samples, and 0.34% for common nevi samples. For cyclin D3, the respective values were 17.8, 6.4, and 1.8%. Statistically significant differences in cyclin D1 expression were observed between melanomas and common nevi as well as between dysplastic and common nevi (p = 0.0001), but not between melanomas and dysplastic nevi. Cyclin D3 expression revealed significant differences between all investigated lesion types (p = 0.0000). The mean cyclin D1 and D3 scores of melanomas with Breslow thickness <1 mm and >1 mm were not significantly different. G1/S abnormalities are crucial for the progression of malignant melanoma, and enhanced cyclin D1 and D3 expression leading to increased melanocyte proliferation is observed in both melanoma and dysplastic nevi. In histopathologically ambiguous cases, lower cyclin D3 expression in dysplastic nevi can be a diagnostic marker for that lesion type.     

Significant melanocytic lesions in infancy, childhood, and adolescence

Malignant melanoma is diagnosed yearly in approximately 300 persons under age 20 in the United States. Relatively recent advances in dermatology include the recognition of lesions felt to be potential precursors of malignant melanoma. Small congenital melanocytic nevi, present in 1 per cent of all newborn infants, may have a small but definite potential for developing malignant melanoma. Furthermore, despite inconclusive data, many leading dermatologists now advocate removal of these small congenital lesions. Giant congenital melanocytic nevi, with their strong predilection for undergoing malignant change, are removed surgically at an early age, often in multistaged procedures. Dermabrasion, once felt to have a role in the treatment of giant congenital nevi, does not remove the malignant potential of these lesions. The dysplastic nevus syndrome, recognized in 1976, identifies individuals at increased risk for developing melanoma. Adolescents who have the dysplastic nevus syndrome or who are members of families with the syndrome require close medical supervision and patient education. The benign Spitz nevus, with its histologic similarity to malignant melanoma, continues to challenge the dermatopathologist and clinician. These lesions--the Spitz nevus, dysplastic nevus, congenital melanocytic nevus, and malignant melanoma--must all be actively considered when regarding the many other benign melanocytic lesions found in infancy, childhood, and adolescence.     

Comparison of pHH3, Ki-67, and survivin immunoreactivity in benign and malignant melanocytic lesions

Differentiating malignant melanoma from benign melanocytic lesions can be challenging. We undertook this study to evaluate the use of the immunohistochemical mitosis marker phospho-Histone H3 (pHH3) and the proliferation markers Ki-67 and survivin in separating malignant melanoma from benign nevi. Sixty-six melanocytic lesions (18 malignant melanomas, 8 Spitz nevi, 20 dysplastic nevi, and 20 compound nevi) were stained with antibodies to pHH3, Ki-67, and survivin. No pHH3 expression was detected in the dermis of compound and dysplastic nevi. Rare mitoses were observed in the superficial dermis in 3 of 8 Spitz nevi (37%). Staining for pHH3 was higher in malignant melanomas [average 25 per 10 high-power field (HPF), range 2-75 per 10 HPF] than in Spitz nevi (average 0.5 per 10 HPF, range 0-2 per 10 HPF) and was heterogeneously distributed in the malignant melanomas compared with a superficial dermal location in Spitz nevi. There was no cytoplasmic staining for survivin in any of the 66 melanocytic lesions and no nuclear staining in any of the benign ones. Survivin nuclear staining was present in 12 of 18 cases of malignant melanoma (67%) with an average index of 7% (range 0%-15%). In benign melanocytic lesions, the Ki-67 index was less than 5% (range 0%-4%) and staining was present close to the dermo-epidermal junction compared with an average index of 27% in melanomas (range 5%-50%) and a generally heterogeneous pattern of staining throughout the dermis. pHH3 and Ki-67 can be useful adjuncts to histopathology to separate malignant melanoma from benign nevi. pHH3 is especially useful to highlight mitoses and to rapidly assess the mitotic activity in melanocytic lesions.     

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.