Asymmetry in dermoscopic melanocytic lesion images: a computer description based on colour distribution

Digital dermoscopy improves the accuracy of melanoma diagnosis. The aim of this study was to develop and validate software for assessment of asymmetry in melanocytic lesion images, based on evaluation of colour symmetry, and to compare it with assessment by human observers. An image analysis program enabling numerical assessment of asymmetry in melanocytic lesions, based on the evaluation and comparison of CIE L*a*b* colour components (CIE L*a*b* is the name of a colour space defined by the Commission Internationale de l'Eclairage) inside image colour blocks, was employed on the recorded lesion images. Clinical evaluation of asymmetry in dermoscopic images was performed on the same image set employing a 0-1 scoring system. Asymmetry judgement was expressed by the clinicians for 12.8% of benign naevi, 44.7% of atypical naevi and 64.2% of malignant melanomas, whereas the computer identified as asymmetric 6.3%, 33.3% and 82.2%, respectively. Numerical parameters referring to malignant melanomas were significantly higher, both with respect to benign naevi and atypical naevi. The numerical parameters produced could be effectively employed for computer-aided melanoma diagnosis.     

Morphometric diagnosis of melanocytic skin tumors

Checking consecutively sampled routine sections of 206 melanocytic lesions with a maximum vertical diameter of at least 1 mm (133 benign dermal nevi, 20 Spitz's nevi, 53 primary malignant melanomas), we measured the morphometric features of at least 60 nuclei each from the superficial and the deep dermal tumor portion using a computer-assisted interactive image analysis system. Furthermore we calculated the so-called maturation parameter (MP) in each case as the ratio of the mean nuclear area in the deep portion and the superficial portion. When we compared the results with those obtained in a training set, we found that the lowest evidence for the discrimination of benign and malignant melanocytic lesions resulted from the application of the mean values of the nuclear area in the superficial layer (efficiency = 62.1%). The efficiency was higher when we used the mean values of the nuclear area in the deep layer (96.1%) and the maturation parameter (85.4%). By applying the mean nuclear area in the deep portion and the maturation parameter simultaneously, we gained the highest efficiency, specificity, and sensitivity for the distinction between benign dermal nevi and malignant melanomas (0.968, 0.955, 1) as well as for the distinction between Spitz's nevi and malignant melanomas (0.986, 0.950, 1). Our study shows that morphometry provides reliable diagnostic results in routinely sampled melanocytic skin tumors.     

Automatic differentiation of melanoma from melanocytic nevi with multispectral digital dermoscopy: a feasibility study

BACKGROUND: Differentiation of melanoma from melanocytic nevi is difficult even for skin cancer specialists. This motivates interest in computer-assisted analysis of lesion images. OBJECTIVE: Our purpose was to offer fully automatic differentiation of melanoma from dysplastic and other melanocytic nevi through multispectral digital dermoscopy. METHOD: At 4 clinical centers, images were taken of pigmented lesions suspected of being melanoma before biopsy. Ten gray-level (MelaFind) images of each lesion were acquired, each in a different portion of the visible and near-infrared spectrum. The images of 63 melanomas (33 invasive, 30 in situ) and 183 melanocytic nevi (of which 111 were dysplastic) were processed automatically through a computer expert system to separate melanomas from nevi. The expert system used either a linear or a nonlinear classifier. The "gold standard" for training and testing these classifiers was concordant diagnosis by two dermatopathologists. RESULTS: On resubstitution, 100% sensitivity was achieved at 85% specificity with a 13-parameter linear classifier and 100%/73% with a 12-parameter nonlinear classifier. Under leave-one-out cross-validation, the linear classifier gave 100%/84% (sensitivity/specificity), whereas the nonlinear classifier gave 95%/68%. Infrared image features were significant, as were features based on wavelet analysis. CONCLUSION: Automatic differentiation of invasive and in situ melanomas from melanocytic nevi is feasible, through multispectral digital dermoscopy.     

Weight of decision-making impairs clinical assessment of melanocytic lesions

BACKGROUND AND OBJECTIVE: We studied the weight of decision-making on clinical assessment of melanocytic lesions judging benign, atypical, and malignant lesions; common mistakes; and total removal rates, comparing dermatologists with nondermatologists. METHODS: Of 11,246 histopathology specimens, 3,768 had a clinical assessment of melanocytic lesions. Histopathologic diagnosis served as the gold standard. RESULTS: Benign nevi were assessed most accurately (77%). Dermatologists assessed benign nevi better (p < .0001). The accuracy of clinical assessment in atypical nevi and melanoma was lower (23% and 42%, respectively). Seborrheic keratosis was the most common mistaken diagnosis. Complete removal of clinically benign nevi, atypical nevi, and melanoma was 84%, 90%, and 89%. Decision-making impaired clinical assessement of melanocytic lesions by 5% for dermatologists and 9% for nondermatologists. CONCLUSION: The accuracy of clinical assessment of melanocytic lesions is high for benign nevi, with dermatologists outperforming nondermatologists. Clinicians overestimated malignant potential. Complete removal was more frequent in suspicious lesions. Clinical decision-making impaired assessment by 5 to 9%.     

The dermoscopic classification of atypical melanocytic naevi (Clark naevi) is useful to discriminate benign from malignant melanocytic lesions

BACKGROUND: The dermoscopic classification is a useful tool for handling patients with atypical naevi (Clark naevi). OBJECTIVES: To investigate if the dermoscopic classification of atypical naevi is of any value to discriminate benign from malignant melanocytic lesions. METHODS: Consecutive patients (n = 205) were included with 254 suspicious melanocytic lesions, confirmed by histopathology at the Pigmented Lesions Clinic of the Department of Dermatology, University Medical Center, University of Tuebingen, Germany. In this retrospective study, dermoscopic images of benign and malignant melanocytic lesions were classified according to the dermoscopic classification of atypical naevi (reticular, globular, homogeneous or combinations of two of these) and pigmentation (uniform, central hyper- or hypopigmentation, eccentric peripheral hyper- or hypopigmentation, or multifocal hyper- or hypopigmentation). The three-structure type (reticular, globular and homogeneous) was additionally defined. RESULTS: Reticular, homogeneous and reticular-homogeneous types were significantly more frequent in naevi than in melanomas, whereas the three-structure type was significantly more frequent in melanomas (P < 0.001). A sensitivity of 86.7%, specificity of 87.7% and diagnostic accuracy of 87.4% was obtained. Uniformly pigmented and centrally hyperpigmented types were significantly more frequent in naevi than in melanomas, whereas eccentric peripheral hyperpigmented and multifocal hyper- or hypopigmented types were significantly more frequent in melanomas (P < 0.001). CONCLUSIONS: The dermoscopic classification of atypical naevi (Clark naevi) is useful to discriminate benign from malignant melanocytic lesions. The three-structure type and eccentric peripheral hyperpigmentation were significantly more frequently found in malignant than in benign melanocytic lesions. The knowledge of these two dermoscopic types should be helpful for the management of patients presenting with multiple melanocytic lesions.     

Phosphoinositide 3-kinase is not overexpressed in melanocytic lesions

BACKGROUND: Although various studies have stressed the role of phosphatase and tensin homologue deleted on chromosome 10 (PTEN)-PI3K-AKT pathway in the progression of melanocytic lesions, little is known about the expression pattern of PI3K in these lesions. OBJECTIVE: To investigate the expression pattern of PI3K in benign and dysplastic nevi, primary melanomas, and metastatic melanomas and the role of PTEN and PI3K in melanocytic tumor progression. METHODS: Tissue microarrays were constructed using formalin-fixed, paraffin-embedded archival tissue blocks from 89 melanocytic lesions: 17 benign nevi, 18 dysplastic nevi, 23 primary melanomas, and 31 metastatic melanomas. Expression of PTEN and PI3K (p85 and p110 subunits) was evaluated immunohistochemically, and the number of cells and labeling intensity were assessed semiquantitatively. RESULTS: Both benign and dysplastic nevi showed strong cytoplasmic staining with PTEN, which was subsequently less in melanomas and completely lost in the metastatic lesions. Eleven of 17 (64%) benign nevi, seven of 10 (70%) dysplastic nevi, four of 23 (17%) primaries, and one of 31 (3%) visceral or lymph node metastasis showed strong positivity. Loss of PTEN expression from benign and dysplastic nevi to melanoma was statistically significant (p=0.001). Although few cells showed reactivity for phosphoinositide 3-kinase (PI3 kinase)-p85 subunit, strong positivity was not detected in the cytoplasm of benign, malignant, or metastatic lesions, except for a single visceral metastasis. Three of 13 (23%) nevi showed positivity for the p110 subunit. No positivity was observed in the dysplastic nevi. Two of 22 (9%) melanomas, one of 14 (7%) visceral metastasis, and three of 12 (25%) lymph node metastasis showed strong positivity. There was no statistical difference in PI3 kinase expression in benign and malignant melanocytic lesions (p=0.2). CONCLUSION: PI3K is not overexpressed in melanocytic lesions.     

The fluorescence of melanocytic lesions

The fluorescence of routine formalin-fixed sections of a variety of melanocytic lesions has been studied. The technique has value in distinguishing benign and atypical nevi from malignant melanomas. Forty-one of 48 melanomas exhibited positive fluorescence, whereas 15 of 86 of a variety of benign nevi were positive. The majority of the negative melanomas were Hutchinson's melanotic freckles, and the majority of the positive nevi were Spitz's nevi. Positive focal junctional fluorescence was a feature in up to half of the cases from established dysplastic nevus syndrome, but was noted only occasionally in sporadic dysplastic nevi. This distinguishes the dysplastic group from banal nevi and may be a marker of malignant potential. It is proposed that positive fluorescence is a marker of a melanocyte with an immature metabolic pathway.     

Objective follow-up of atypical melanocytic skin lesions: a retrospective study

Various authors have suggested that information from longitudinal observation (follow-up) of dynamic changes in atypical melanocytic pigmented skin lesions (MPSL) could enable identification of early malignant melanoma escaping initial observation due to an absence of specific clinical and dermoscopic features. The aim of our retrospective study was to determine the existence of numerical variables regarding changes in MPSL that could be useful to differentiate early melanomas and atypical nevi. The study was carried out in two Italian dermatology Centres. Digital dermoscopy analyzers (DB-Mips System) were used to evaluate dermoscopic images of 94 equivocal pigmented skin lesions under observation for 6–12 months and then excised because of changes across time (29 melanomas and 65 nevi). The analyzer evaluates 49 parameters grouped into four categories: geometries, colours, textures and islands of colour. The ROC curve designed on the 49 digital dermoscopy analysis parameters showed good accuracy. At sensitivity (SE) = specificity (SP), it correctly classified 89.3% of cases. When objective pigmented skin lesion parameters were considered together with their objective changes over 6–12 months, a decisive increase in discrimination capacity was obtained. At SE = SP accuracy was 96.3%. Analysis of the parameters of our model and statistical analysis enabled us to interpret/identify the most significant factors of modification and differentiation of lesions, providing quantitative insights into the diagnosis of equivocal MPSL and demonstrating the utility of objective/numerical follow-up.     

Automated epiluminescence microscopy—tissue counter analysis using CART and 1-NN in the diagnosis of Melanoma

Background/purpose: In tissue counter analysis, digital images are overlayed with regularly distributed measuring masks (elements) of equal size and shape, and the digital contents (grey level, colour and texture parameters) of each element are used for statistical analysis. In this study we assessed the applicability of tissue counter analysis and machine learning algorithms on tumour segmentation and diagnostic discrimination of benign and malignant melanocytic skin lesions.
Methods: A total of 369 standardised dermatoscopic images (93 melanomas, 276 benign nevi) were evaluated. The Classification and Regression Tree (CART) analysis was performed in order to differentiate between melanocytic skin lesions and surrounding skin. Instance-based learning (1-NN) was tested for differentiating between benign and malignant tumour elements. For diagnostic assessment, only the percentage of elements suggestive for malignancy in each lesion was used.
Results: Evaluation of a total of 369 melanocytic skin lesions showed a suitable segmentation of the tumour portion in 97.6%. When instance-based learning was applied to an independent test set, a threshold value of 27.4% of elements suggestive for malignancy recognised 35 out of 35 melanomas and 100 out of 101 nevi (sensitivity 100%, specificity 99%, positive predictive value 97.2%, negative predictive value 100%).
Conclusion: Tissue counter analysis combined with machine learning algorithms turned out to be a useful method for diagnostic purposes in epiluminescence microscopy.     

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.     

IMP‐3 expression in melanocytic lesions

Background: Insulin‐like growth factor‐II mRNA‐binding protein 3 (IMP‐3 ), a member of the insulin‐like growth factor mRNA‐binding protein family, is expressed in several human malignancies, including melanomas. However, the expression of IMP‐3 has not been explored in melanoma in situ, various histologic subtypes of invasive melanomas and atypical Spitz tumors. Methods: IMP‐3 immunostain was performed in 157 melanocytic lesions. Results: Nearly all benign (8/8), dysplastic (8/8) and Spitz nevi (8/9) were negative for IMP‐3. Focal IMP‐3 positivity was observed in 5/12 melanoma in situ and 4/15 superficial melanomas (Breslow depth ≤1 mm). Half (10/20) of deep melanomas (Breslow depth >1 mm) and 25/52 metastatic melanomas demonstrated strong IMP‐3 staining. IMP‐3 expression differs significantly between non‐desmoplastic melanomas (superficial and deep) and benign or dysplastic or Spitz nevi (p = 0.0427, respectively). Four of 23 desmoplastic melanomas expressed IMP‐3 , which was significantly different from deep melanomas (p = 0.0109). IMP‐3 stained 7 of 10 atypical Spitz tumors. The difference between atypical Spitz tumors and Spitz nevi was statistically significant (p = 0.0256). Conclusion: A malignant circumstance, such as non‐desmoplastic melanoma or atypical Spitz tumor, can be inferred when IMP‐3 is expressed, suggesting potential diagnostic value of IMP‐3 in melanocytic lesions. Yu L, Xu H, Wasco MJ, Bourne PA, Ma L. IMP‐3 expression in melanocytic lesions.     

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.     

A zonal comparison of MIB1-Ki67 immunoreactivity in benign and malignant melanocytic lesions

Differentiation between malignant melanomas and benign nevi can sometimes be difficult by conventional histopathology, and additional diagnostic markers may be helpful. This study investigated the immunoreactivity of the cell proliferation marker MIB1-Ki67 in 23 compound nevi, 17 dysplastic nevi, 8 Spitz nevi (SN), and 24 malignant melanomas (MMs) and evaluated its ability in separating benign nevi from MMs. In each lesion, the average number (percentage) of MIB1-positive nuclei (%MIB1-Mean) and the maximal number (percentage) of MIB1-positive nuclei (%MIB1-Max) were determined from each of the superficial, middle, and deep dermal zones of the lesion as well as from the entire lesion. The %MIB1-Max was determined from subjectively selected area(s) of high count. Malignant melanomas had a significantly greater %MIB1-Mean and %MIB1-Max than all benign nevi in all individual zones and in the entire lesion (p < 0.05). Discriminant analysis showed that the %MIB1-Mean and %MIB1-Max counted from the whole lesions had better discriminating abilities than from the individual zones. By using the %MIB1-Mean from all zones, all lesions except 1 SN and 3 MMs could be correctly classified as benign or malignant. When using the %MIB1-Max from all zones, all but 2 SN could be correctly separated as benign or malignant. Thus, MIB1-Ki67 immunoreactivity closely correlates with the benignancy or malignancy of melanocytic lesions and may assist in the differentiation of benign nevi from MMs.     

Dermoscopic patterns of acral melanocytic nevi and melanomas in a white population in central Italy

OBJECTIVE: To investigate the dermoscopic features of acral melanocytic lesions in a white population in central Italy. DESIGN: Retrospective review. SETTING: University dermatology department. PATIENTS: Six hundred fifty-one Italian subjects, ranging in age from 6 months to 78 years. MAIN OUTCOME MEASURES: We retrospectively investigated all digital dermoscopic images of acral melanocytic lesions included in our database from January 1996 to May 2005. RESULTS: We retrieved digital images of 723 benign acral melanocytic lesions in 641 patients (235 males and 406 females; mean age, 26.5 years) and of 10 acral melanomas in 10 patients (7 males and 3 females; mean age, 65 years). Individual lesions were located on the soles (n=520), fingers (n=146), and palms (n=67). Among acral nevi, the parallel furrow (42.1%) was the most common pattern, followed by the latticelike (14.9%), nontypical (13.7%), fibrillar (10.8%), homogeneous (9.3%), globular (5.4%), and reticular (2.1%) patterns. The frequency of distribution of the latticelike, nontypical, fibrillar, and homogeneous patterns significantly differed (P<.001, P=.03, P<.001, and P=.03, respectively) between anatomical sites. Also, 13 acral nevi (1.8%), mainly located on the fingers, showed a new combined pattern (transition pattern) consisting of a brownish black network associated with a parallel furrow or latticelike pattern. All 10 acral melanomas showed a multicomponent dermoscopic pattern. CONCLUSIONS: In our series of acral nevi, we observed 8 dermoscopic patterns, with varying distribution by anatomical site. Identification of a specific pattern is highly suggestive of the benign or the malignant nature of any given acral melanocytic lesion.     

Digital dermatoscopic follow‐up of 1027 melanocytic lesions in 121 patients at risk of malignant melanoma

Objective  The aim of the presented prospective study was to use a digital dermatoscopic system to follow‐up patients with multiple melanocytic naevi, and to evaluate the frequency and character of dermatoscopic changes. Methods  We monitored selected melanocytic lesions with the use of a 6‐month follow‐up interval between check‐ups. We searched for changes in size, shape, symmetry, structure and colour. We defined the criteria for surgical excision and histopathological examination of changing lesions. We created a small group of excised unchanged atypical melanocytic naevi. Results  We completed dermatoscopic monitoring of 1027 melanocytic lesions in 121 patients at risk of developing malignant melanoma. The average total follow‐up interval was 21.0 months. We noticed a substantial enlargement of monitored lesions in 4.5% of cases, and there was a change of shape in 1.3% and change of asymmetry in 2.0%. The appearance of new structures, frequently being associated with malignant melanoma, was observed in 10 lesions, and it was predictive for the histopathological confirmation of this diagnosis in all cases. About 80% of monitored lesions remained unchanged. We excised 38 monitored lesions (seven melanomas in situ, four thin invasive melanomas and 27 melanocytic naevi). There was no melanoma excised in the group of unchanged atypical melanocytic lesions. Conclusion  Digital dermatoscopic follow‐up facilitates the recognition of thin malignant melanomas and helps to reduce the number of unnecessary excisions.     

Follow-up of melanocytic skin lesions with digital epiluminescence microscopy: patterns of modifications observed in early melanoma, atypical nevi, and common nevi

BACKGROUND: Digital epiluminescence microscopy (DELM) has been reported to be a useful technique for the follow-up of melanocytic nevi. One of the promises of this technique is to identify modifications over time that indicate impending or incipient malignancy and to facilitate surveillance of melanocytic skin lesions, particularly in patients with multiple clinically atypical nevi. OBJECTIVE: Our purpose was to report on patterns of modifications over time observed in benign melanocytic skin lesions and melanoma. METHODS: A total of 1862 sequentially recorded DELM images of melanocytic lesions from 202 patients (mean age, 36.1 years; 54.0% female patients) with multiple clinically atypical nevi were included in the analysis. The median follow-up interval was 12. 6 months. Melanocytic lesions with substantial modifications over time (enlargement, changes in shape, regression, color changes or appearance of ELM structures known to be associated with melanoma) were excised and referred to histopathologic examination. RESULTS: A total of 75 melanocytic skin lesions (4.0%) from 52 patients (mean age, 33.3 years; 63.5% female patients) showed substantial modifications over time and were excised and referred to histopathologic examination. Eight changing lesions were histologically diagnosed as early melanomas. These lesions frequently showed focal enlargement associated with a change in shape as well as appearance of ELM structures that are known to be associated with melanoma. In contrast, the majority of benign changing lesions (common and atypical nevi) showed symmetric enlargement without substantial structural ELM changes. Six of the 8 patients in whom melanoma developed were unaware of the fact that the lesion had changed over time. CONCLUSION: We demonstrate that follow-up of melanocytic lesions with DELM helps to identify patterns of morphologic modifications typical for early melanoma. DELM may therefore serve as a useful tool to improve the surveillance of patients with multiple atypical nevi.     

Staining of melanocytic neoplasms by melanoma antigen recognized by T cells

We stained benign melanocytic nevi and malignant melanoma with antibodies to melanoma antigen recognized by T cells (Mart-1) to determine if this was useful in differentiating benign from malignant melanocytic neoplasms. Forty-five primary malignant melanomas and 71 benign melanocytic nevi were stained with antibodies to Mart-1. Two cases of malignant melanoma metastatic to lymph node and three cutaneous metastases of malignant melanoma were also stained. The degree of staining was graded into diffuse positive staining, focal positive staining, and negative staining. Thirty-six of 45 primary malignant melanomas stained diffusely positive with antibodies to Mart-1. This included three of five desmoplastic malignant melanomas that showed positive staining. Four melanomas showed faint or focal positive staining. One of two metastases to lymph node showed strong positive staining and one showed no staining. All three cutaneous metastases showed diffuse positive staining. Sixty-one of 71 melanocytic nevi showed no staining or faint staining with antibodies to Mart-1. Ten of 71 melanocytic nevi showed strong positive staining. The majority of these were congenital nevi. Staining with antibodies to Mart-1 antigen was a useful marker of malignant melanoma. However, staining may also be seen in benign melanocytic neoplasms. The presence or absence of staining for Mart-1 antigen cannot be used to differentiate benign melanocytic nevi from malignant melanocytic tumors.     

Cdc7 expression in melanomas, Spitz tumors and melanocytic nevi

Background:  Cdc7 is a serine-threonine kinase required for initiation of DNA replication that may play a role in the development and progression of melanoma.
Materials and Methods:  Tissue microarrays containing 40 melanomas, 40 Spitz tumors and 30 nevi were constructed. Staining for Cdc7 was scored semiquantitatively according to intensity and extent, and the values were converted into composite scores.
Results:  Nodular melanomas, atypical Spitz tumors and superficial spreading melanomas had the highest scores (nodular melanomas, 3.67; atypical Spitz tumors, 2.78 and superficial spreading melanomas, 2.44). Typical Spitz nevi, dysplastic nevi and ordinary nevi had the lowest scores. Cdc7 expression in melanomas differed significantly from non-Spitz nevi (p < 0.001). The difference was also significant when invasive melanomas were compared with dysplastic nevi (p < 0.005) and when invasive melanomas were compared with non-atypical Spitz nevi (p < 0.001). However, there was no significant difference between invasive melanomas and atypical Spitz tumors (p = 0.69) or between dysplastic nevi and ordinary nevi (p = 0.73).
Conclusion:  Cdc7 expression differs significantly among cutaneous melanocytic neoplasms and can be evaluated by routine immunohistochemical methods. The results suggest that differences in Cdc7 expression may account for some of the differences between malignant melanomas and benign melanocytic nevi.     

Digital image analysis for diagnosis of cutaneous melanoma. Development of a highly effective computer algorithm based on analysis of 837 melanocytic lesions

BACKGROUND: Digital image analysis has been introduced into the diagnosis of skin lesions based on dermoscopic pictures. OBJECTIVES: To develop a computer algorithm for the diagnosis of melanocytic lesions and to compare its diagnostic accuracy with the results of established dermoscopic classification rules. METHODS: In the Department of Dermatology, University of Tuebingen, Germany, 837 melanocytic skin lesions were prospectively imaged by a dermoscopy video system in consecutive patients. Of these lesions, 269 were excised and examined by histopathology: 84 were classified as cutaneous melanomas and 185 as benign melanocytic naevi. The remaining 568 lesions were diagnosed by dermoscopy as benign. Digital image analysis was performed in all 837 benign and malignant melanocytic lesions using 64 different analytical parameters. RESULTS: For lesions imaged completely (diameter < or = 12 mm), three analytical parameters were found to distinguish clearly between benign and malignant lesions, while in incompletely imaged lesions six parameters enabled differentiation. Based on the respective parameters and logistic regression analysis, a diagnostic computer algorithm for melanocytic lesions was developed. Its diagnostic accuracy was 82% for completely imaged and 84% for partially imaged lesions. All 837 melanocytic lesions were classified by established dermoscopic algorithms and the diagnostic accuracy was found to be in the same range (ABCD rule 78%, Menzies' score 83%, seven-point checklist 88%, and seven features for melanoma 81%). CONCLUSIONS: A diagnostic algorithm for digital image analysis of melanocytic lesions can achieve the same range of diagnostic accuracy as the application of dermoscopic classification rules by experts. The present diagnostic algorithm, however, still requires a medical expert who is qualified to recognize cutaneous lesions as being of melanocytic origin.