Systematic review of dermoscopy and digital dermoscopy/ artificial intelligence for the diagnosis of melanoma

Guidelines of care for the management of primary cutaneous melanoma

The incidence of primary cutaneous melanoma continues to increase each year. Melanoma accounts for the majority of skin cancer-related deaths, but treatment is usually curative following early detection of disease. In this American Academy of Dermatology clinical practice guideline, updated treatment recommendations are provided for patients with primary cutaneous melanoma (American Joint Committee on Cancer stages 0-IIC and pathologic stage III by virtue of a positive sentinel lymph node biopsy). Biopsy techniques for a lesion that is clinically suggestive of melanoma are reviewed, as are recommendations for the histopathologic interpretation of cutaneous melanoma. The use of laboratory, molecular, and imaging tests is examined in the initial work-up of patients with newly diagnosed melanoma and for follow-up of asymptomatic patients. With regard to treatment of primary cutaneous melanoma, recommendations for surgical margins and the concepts of staged excision (including Mohs micrographic surgery) and nonsurgical treatments for melanoma in situ, lentigo maligna type (including topical imiquimod and radiation therapy), are updated. The role of sentinel lymph node biopsy as a staging technique for cutaneous melanoma is described, with recommendations for its use in clinical practice. Finally, current data regarding pregnancy and melanoma, genetic testing for familial melanoma, and management of dermatologic toxicities related to novel targeted agents and immunotherapies for patients with advanced disease are summarized.

Dermatoscopy of Neoplastic Skin Lesions: Recent Advances, Updates, and Revisions

OPINION STATEMENT

Dermatoscopy (dermoscopy) improves the diagnosis of benign and malignant cutaneous neoplasms in comparison with examination with the unaided eye and should be used routinely for all pigmented and non-pigmented cutaneous neoplasms. It is especially useful for the early stage of melanoma when melanoma-specific criteria are invisible to the unaided eye. Preselection by the unaided eye is therefore not recommended. The increased availability of polarized dermatoscopes, and the extended use of dermatoscopy in non-pigmented lesions led to the discovery of new criteria, and we recommend that lesions should be examined with polarized and non-polarized dermatoscopy. The "chaos and clues algorithm" is a good starting point for beginners because it is easy to use, accurate, and it works for all types of pigmented lesions not only for those melanocytic. Physicians, who use dermatoscopy routinely, should be aware of new clues for acral melanomas, nail matrix melanomas, melanoma in situ, and nodular melanoma. Dermatoscopy should also be used to distinguish between different subtypes of basal cell carcinoma and to discriminate highly from poorly differentiated squamous cell carcinomas to optimize therapy and management of non-melanoma skin cancer. One of the most exciting areas of research is the use of dermatoscopic images for machine learning and automated diagnosis. Convolutional neural networks trained with dermatoscopic images are able to diagnose pigmented lesions with the same accuracy as human experts. We humans should not be afraid of this new and exciting development because it will most likely lead to a peaceful and fruitful coexistence of human experts and decision support systems.

Automated decision support in melanocytic lesion management

An automated melanocytic lesion image-analysis algorithm is described that aims to reproduce the decision-making of a dermatologist. The utility of the algorithm lies in its ability to identify lesions requiring excision from lesions not requiring excision. Using only wavelet coefficients as features, and testing three different machine learning algorithms, a cohort of 250 images of pigmented lesions is classified based on expert dermatologists’ recommendations of either excision (165 images) or no excision (85 images). It is shown that the best algorithm utilises the Shannon4 wavelet coupled to the support vector machine, where the latter is used as the classifier. In this case the algorithm, utilising only 22 othogonal features, achieves a 10-fold cross validation sensitivity and specificity of 0.96 and 0.87, resulting in a diagnostic-odds ratio of 261. The advantages of this method over diagnostic algorithms–which make a melanoma/no melanoma decision–are twofold: first, by reproducing the decision-making of a dermatologist, the average number of lesions excised per melanoma among practioners in general can be reduced without compromising the detection of melanoma; and second, the intractable problem of clinically differentiating between many atypical dysplastic naevi and melanoma is avoided. Since many atypical naevi that require excision on clinical grounds will not be melanoma, the algorithm–in contrast to diagnostic algorithms–can aim for perfect specificities without clinical concerns, thus lowering the excision rate of non-melanoma. Finally, the algorithm has been implemented as a smart phone application to investigate its utility in clinical practice and to streamline the assimilation of hitherto unseen tested images into the training set.

Performance of a computer-aided digital dermoscopic image analyzer for melanoma detection in 1,076 pigmented skin lesion biopsies

BACKGROUND

Digital dermoscopic image analysis of pigmented skin lesions (PSLs) has become increasingly popular, despite its unclear clinical utility. Unbiased, high-powered studies investigating the efficacy of commercially available systems are limited.

OBJECTIVE

To investigate the diagnostic performance of the FotoFinder Mole-Analyzer in assessing PSLs for cutaneous melanoma.

METHODS

In this 15-year retrospective study, the histopathologies of 1076 biopsied PSLs among a total of 2500 imaged PSLs were collected. The biopsied PSLs were categorized as benign or malignant (cutaneous melanoma) based on histopathology. Analyzer scores (0-1.00) for these PSLs were obtained and grouped according to histopathology.

RESULTS

At an optimized cutoff score of 0.50, a sensitivity of 56% and a specificity of 74% were achieved. The area under the receiver operating characteristics curve was 0.698, indicating poor accuracy as a diagnostic tool.

LIMITATIONS

This study had a retrospective design and involved only a single institution.

CONCLUSION

Our study reveals a low sensitivity of the scoring function of this digital dermoscopic image analyzer for detecting cutaneous melanomas. Physicians must apply keen clinical judgment when using such devices in the screening of suspicious PSLs.

Acral melanoma detection using a convolutional neural network for dermoscopy images

Background/Purpose

Acral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions.

Methods

A total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist’s and non-expert’s evaluation.

Results

The accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert’s evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden’s index like 0.6795, 0.6073, which were similar score with the expert.

Conclusion

Although further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.

Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images

BACKGROUND

Computer vision may aid in melanoma detection.

OBJECTIVE

We sought to compare melanoma diagnostic accuracy of computer algorithms to dermatologists using dermoscopic images.

METHODS

We conducted a cross-sectional study using 100 randomly selected dermoscopic images (50 melanomas, 44 nevi, and 6 lentigines) from an international computer vision melanoma challenge dataset (n = 379), along with individual algorithm results from 25 teams. We used 5 methods (nonlearned and machine learning) to combine individual automated predictions into "fusion" algorithms. In a companion study, 8 dermatologists classified the lesions in the 100 images as either benign or malignant.

RESULTS

The average sensitivity and specificity of dermatologists in classification was 82% and 59%. At 82% sensitivity, dermatologist specificity was similar to the top challenge algorithm (59% vs. 62%, P = .68) but lower than the best-performing fusion algorithm (59% vs. 76%, P = .02). Receiver operating characteristic area of the top fusion algorithm was greater than the mean receiver operating characteristic area of dermatologists (0.86 vs. 0.71, P = .001).

LIMITATIONS

The dataset lacked the full spectrum of skin lesions encountered in clinical practice, particularly banal lesions. Readers and algorithms were not provided clinical data (eg, age or lesion history/symptoms). Results obtained using our study design cannot be extrapolated to clinical practice.

CONCLUSION

Deep learning computer vision systems classified melanoma dermoscopy images with accuracy that exceeded some but not all dermatologists.

Diagnosing malignant melanoma in ambulatory care: a systematic review of clinical prediction rules

OBJECTIVES

Malignant melanoma has high morbidity and mortality rates. Early diagnosis improves prognosis. Clinical prediction rules (CPRs) can be used to stratify patients with symptoms of suspected malignant melanoma to improve early diagnosis. We conducted a systematic review of CPRs for melanoma diagnosis in ambulatory care.

DESIGN

Systematic review.

DATA SOURCES

A comprehensive search of PubMed, EMBASE, PROSPERO, CINAHL, the Cochrane Library and SCOPUS was conducted in May 2015, using combinations of keywords and medical subject headings (MeSH) terms.

STUDY SELECTION AND DATA EXTRACTION

Studies deriving and validating, validating or assessing the impact of a CPR for predicting melanoma diagnosis in ambulatory care were included. Data extraction and methodological quality assessment were guided by the CHARMS checklist.

RESULTS

From 16 334 studies reviewed, 51 were included, validating the performance of 24 unique CPRs. Three impact analysis studies were identified. Five studies were set in primary care. The most commonly evaluated CPRs were the ABCD, more than one or uneven distribution of Colour, or a large (greater than 6 mm) Diameter (ABCD) dermoscopy rule (at a cut-point of >4.75; 8 studies; pooled sensitivity 0.85, 95% CI 0.73 to 0.93, specificity 0.72, 95% CI 0.65 to 0.78) and the 7-point dermoscopy checklist (at a cut-point of ≥1 recommending ruling in melanoma; 11 studies; pooled sensitivity 0.77, 95% CI 0.61 to 0.88, specificity 0.80, 95% CI 0.59 to 0.92). The methodological quality of studies varied.

CONCLUSIONS

At their recommended cut-points, the ABCD dermoscopy rule is more useful for ruling out melanoma than the 7-point dermoscopy checklist. A focus on impact analysis will help translate melanoma risk prediction rules into useful tools for clinical practice.

Dermoscopic features of livedoid vasculopathy

Livedoid vasculopathy (atrophie blanche) is a form of thrombotic vasculopathy. It is characterized by small ulcers that become crusted, and heal after several months to produce white atrophic scars. The most commonly affected sites are the lower legs, in particular the dorsum of the feet and ankles. To date, the dermoscopic features of livedoid vasculopathy have not been clearly described in the literature. In this observational study, we sought to evaluate the dermoscopic patterns of livedoid vasculopathy and determine whether the dermoscopic features are associated with certain histopathological characteristics. We evaluated 9 patients with livedoid vasculopathy by dermoscopy. Skin biopsy specimens were stained with hematoxylin and eosin for histopathologic examination, and dermoscopic features were correlated with histopathological characteristics. In the majority of patients with livedoid vasculopathy, examination with dermoscopy revealed central crusted ulcers or ivory white areas associated with peripheral pigmentation in a reticular pattern. In addition, increased vascular structures including linear and glomerular vessels were found. On histopathological examination, the central ivory white areas correlated with dermal fibrosis, the reticular pigmentation corresponded to epidermal basal layer hyperpigmentation or melanin within melanophages in the dermal papillae, and the vascular structures correlated with dilatation and proliferation of capillaries in the upper dermis. In summary, the most common dermoscopic features of livedoid vasculopathy identified in this study were central crusted ulcers or ivory white scar-like areas associated with peripheral reticular pigmentation and increased vascular structures. The characterization of dermoscopic criteria for livedoid vasculopathy may improve the accuracy in the clinical diagnosis and follow-up of this disease.

Computer-Aided Decision Support for Melanoma Detection Applied on Melanocytic and Nonmelanocytic Skin Lesions: A Comparison of Two Systems Based on Automatic Analysis of Dermoscopic Images

Commercially available clinical decision support systems (CDSSs) for skin cancer have been designed for the detection of melanoma only. Correct use of the systems requires expert knowledge, hampering their utility for nonexperts. Furthermore, there are no systems to detect other common skin cancer types, that is, nonmelanoma skin cancer (NMSC). As early diagnosis of skin cancer is essential, there is a need for a CDSS that is applicable to all types of skin lesions and is suitable for nonexperts. Nevus Doctor (ND) is a CDSS being developed by the authors. We here investigate ND's ability to detect both melanoma and NMSC and the opportunities for improvement. An independent test set of dermoscopic images of 870 skin lesions, including 44 melanomas and 101 NMSCs, were analysed by ND. Its sensitivity to melanoma and NMSC was compared to that of Mole Expert (ME), a commercially available CDSS, using the same set of lesions. ND and ME had similar sensitivity to melanoma. For ND at 95% melanoma sensitivity, the NMSC sensitivity was 100%, and the specificity was 12%. The melanomas misclassified by ND at 95% sensitivity were correctly classified by ME, and vice versa. ND is able to detect NMSC without sacrificing melanoma sensitivity.

DERMA: a melanoma diagnosis platform based on collaborative multilabel analog reasoning

The number of melanoma cancer-related death has increased over the last few years due to the new solar habits. Early diagnosis has become the best prevention method. This work presents a melanoma diagnosis architecture based on the collaboration of several multilabel case-based reasoning subsystems called DERMA. The system has to face up several challenges that include data characterization, pattern matching, reliable diagnosis, and self-explanation capabilities. Experiments using subsystems specialized in confocal and dermoscopy images have provided promising results for helping experts to assess melanoma diagnosis.

Computer aided diagnostic support system for skin cancer: a review of techniques and algorithms

Image-based computer aided diagnosis systems have significant potential for screening and early detection of malignant melanoma. We review the state of the art in these systems and examine current practices, problems, and prospects of image acquisition, pre-processing, segmentation, feature extraction and selection, and classification of dermoscopic images. This paper reports statistics and results from the most important implementations reported to date. We compared the performance of several classifiers specifically developed for skin lesion diagnosis and discussed the corresponding findings. Whenever available, indication of various conditions that affect the technique's performance is reported. We suggest a framework for comparative assessment of skin cancer diagnostic models and review the results based on these models. The deficiencies in some of the existing studies are highlighted and suggestions for future research are provided.

Systematic review of diagnostic accuracy of reflectance confocal microscopy for melanoma diagnosis in patients with clinically equivocal skin lesions

BACKGROUND

Melanoma is a cancer of the skin and is increasing in incidence in the UK and Europe. Melanoma is a condition that is often curable if detected at an early stage, which makes accurate diagnosis vital. Reflectance confocal microscopy (RCM) is a tool used to image the skin. It gives high magnification images of the skin, which may provide more accurate diagnosis of lesions that are equivocal on clinical examination and dermoscopy.

OBJECTIVE

To determine the diagnostic accuracy of reflectance confocal microscopy (RCM), for melanoma diagnosis, as an add-on test to clinical examination and dermoscopy in the diagnosis of equivocal pigmented skin lesions using histopathology as the reference standard.

METHODS

A search was conducted of MEDLINE, EMBASE and six other electronic databases from inception to present. Forward citation searching and hand searching of reference lists were also conducted. Diagnostic accuracy studies that assess RCM in the diagnosis of melanoma were included in the review. Two contributors conducted the search, data extraction and assessment of methodological quality using QUADAS-2. Statistical analysis was performed using hierarchical bivariate random effects meta-analysis.

RESULTS

951 titles and abstracts were screened. Five studies comprising 909 lesions were eligible for meta-analysis. Meta-analysis returned a per lesion sensitivity of 93% [95% CI 89-96] and a specificity of 76% [95% CI 68-83].

CONCLUSIONS

The utility of reflectance confocal microscopy (RCM) as an add-on test for the diagnosis of melanoma depends on the trade off between over-excising benign lesions and misdiagnosing melanoma as benign. This becomes important when considering lesions on surgically difficult or cosmetically important areas of the body.

Decision support in dermatology and medicine: history and recent developments

This article is focused on diagnostic decision support tools and will provide a brief history of clinical decision support (CDS), examine the components of CDS and its associated terminology, and discuss recent developments in the use and application of CDS systems, particularly in the field of dermatology. For this article, we use CDS to mean an interactive system allowing input of patient-specific information and providing customized medical knowledge-based results via automated reasoning, for example, a set of rules and/or an underlying logic, and associations.

New diagnostics for melanoma detection: from artificial intelligence to RNA microarrays

Early detection of melanoma remains crucial to ensuring a favorable prognosis. Dermoscopy and total body photography are well-established noninvasive aids that increase the diagnostic accuracy of dermatologists in their daily routine, beyond that of a naked-eye examination. New noninvasive diagnostic techniques, such as reflectance confocal microscopy, multispectral digital imaging and RNA microarrays, are currently being investigated to determine their utility for melanoma detection. This review presents emerging technologies for noninvasive melanoma diagnosis, and discusses their advantages and limitations.

High-definition optical coherence tomography enables visualization of individual cells in healthy skin: comparison to reflectance confocal microscopy

High-definition OCT (HD-OCT) is an innovative technique based on the principle of conventional OCT. Our objective was to test the resolution and image quality of HD-OCT in comparison with reflectance confocal microscopy (RCM) of healthy skin. Firstly, images have been made of a ultra-high-resolution line-pair phantome with both systems. Secondly, we investigated 21 healthy volunteers of different phototypes with HD-OCT and RCM on volar forearm and compared the generated images. HD-OCT displays also differences depending on the skin phototype and anatomical site. The 3-μm lateral resolution of the HD-OCT could be confirmed by the phantom analysis. The identification of cells in the epidermis can be made by both techniques. RCM offers the best lateral resolution, and HD-OCT has the best penetration depth, providing images of individual cells deeper within the dermis. Eccrine ducts and hair shafts with pilosebaceous units can be observed depending on skin site. HD-OCT provides morphological imaging with sufficient resolution and penetration depth to permit visualization of individual cells at up to 570 μm in depth offering the possibility of additional structural information complementary to that of RCM. HD-OCT further has the possibility for rapid three-dimensional imaging.

The etiology and molecular genetics of human pigmentation disorders

Pigmentation, defined as the placement of pigment in skin, hair, and eyes for coloration, is distinctive because the location, amount, and type of pigmentation provides a visual manifestation of genetic heterogeneity in pathways regulating the pigment-producing cells, melanocytes. The scope of this genetic heterogeneity in humans ranges from normal to pathological pigmentation phenotypes. Clinically, normal human pigmentation encompasses a variety of skin and hair color as well as punctate pigmentation such as melanocytic nevi (moles) or ephelides (freckles), while abnormal human pigmentation exhibits markedly reduced or increased pigment levels, known as hypopigmentation and hyperpigmentation, respectively. Elucidation of the molecular genetics underlying pigmentation has revealed genes important for melanocyte development and function. Furthermore, many pigmentation disorders show additional defects in cells other than melanocytes, and identification of the genetic insults in these disorders has revealed pleiotropic genes, where a single gene is required for various functions in different cell types. Thus, unravelling the genetics of easily visualized pigmentation disorders has identified molecular similarities between melanocytes and less visible cell types/tissues, arising from a common developmental origin and/or shared genetic regulatory pathways. Herein we discuss notable human pigmentation disorders and their associated genetic alterations, focusing on the fact that the developmental genetics of pigmentation abnormalities are instructive for understanding normal pathways governing development and function of melanocytes.

Validation Study of Automated Dermal/Epidermal Junction Localization Algorithm in Reflectance Confocal Microscopy Images of Skin

Reflectance confocal microscopy (RCM) has seen increasing clinical application for noninvasive diagnosis of skin cancer. Identifying the location of the dermal-epidermal junction (DEJ) in the image stacks is key for effective clinical imaging. For example, one clinical imaging procedure acquires a dense stack of 0.5×0.5mm FOV images and then, after manual determination of DEJ depth, collects a 5×5mm mosaic at that depth for diagnosis. However, especially in lightly pigmented skin, RCM images have low contrast at the DEJ which makes repeatable, objective visual identification challenging. We have previously published proof of concept for an automated algorithm for DEJ detection in both highly- and lightly-pigmented skin types based on sequential feature segmentation and classification. In lightly-pigmented skin the change of skin texture with depth was detected by the algorithm and used to locate the DEJ. Here we report on further validation of our algorithm on a more extensive collection of 24 image stacks (15 fair skin, 9 dark skin). We compare algorithm performance against classification by three clinical experts. We also evaluate inter-expert consistency among the experts. The average correlation across experts was 0.81 for lightly pigmented skin, indicating the difficulty of the problem. The algorithm achieved epidermis/dermis misclassification rates smaller than 10% (based on 25×25 mm tiles) and average distance from the expert labeled boundaries of ~6.4 μm for fair skin and ~5.3 μm for dark skin, well within average cell size and less than 2x the instrument resolution in the optical axis.

Clinical and dermoscopic features of 88 scalp naevi in 39 children

BACKGROUND

Paediatric scalp naevi may represent a source of anxiety for practitioners and parents, as the clinical and dermoscopic features of typical naevi have yet to be defined. Prompted by concern about the large size, irregular borders and colour variation of scalp naevi, clinicians and parents may request unnecessary excision of these naevi.

OBJECTIVES

To establish the typical clinical and dermoscopic patterns of scalp naevi in children younger than 18 years old to help optimize clinical care and management.

METHODS

Scalp naevi were imaged with a camera (Canon Rebel, XSi; Canon, Tokyo, Japan) and dermoscopic attachment (Dermlite Foto, 30 mm lens; 3Gen, San Juan Capistrano, CA, U.S.A.) to the camera. The clinical and dermoscopic images were reviewed and analysed. Both acquired and congenital scalp naevi were included but were not further differentiated from each other.

RESULTS

We obtained clinical and dermoscopic images of 88 scalp naevi in 39 white children. Two subjects had received chronic immunosuppressive medication. Nineteen children had a family history of melanoma. Boys (18/39 subjects, 46%) possessed 68% (60 naevi) of scalp naevi imaged. Younger (< 10 years old) subjects (24/39 subjects, 62%) possessed 42% (37 naevi) of scalp naevi. The main clinical patterns included eclipse (n=18), cockade (n = 3), solid brown (n=42) and solid pink (n=25) naevi. Solid-coloured naevi showed the following dermoscopic patterns: globular (57%), complex (reticular-globular) (27%), reticular (9%), homogeneous (6%) and fibrillar (1%). The majority of naevi had a unifying feature - perifollicular hypopigmentation, which caused the appearance of scalloped, irregular borders if occurring on the periphery, or variegation in pigmentation, if occurring within the naevi.

CONCLUSIONS

Older subjects and boys tend to harbour a larger proportion of scalp naevi. The main clinical patterns include solid-coloured and eclipse naevi. The most common dermoscopic pattern of scalp naevi is the globular pattern. Perifollicular hypopigmentation is a hallmark feature of signature scalp naevi. Dermoscopy is a noninvasive tool in the evaluation of cutaneous melanocytic lesions in children and may decrease the number of unnecessary excisions.

Semi-automated Algorithm for Localization of Dermal/ Epidermal Junction in Reflectance Confocal Microscopy Images of Human Skin

The examination of the dermis/epidermis junction (DEJ) is clinically important for skin cancer diagnosis. Reflectance confocal microscopy (RCM) is an emerging tool for detection of skin cancers in vivo. However, visual localization of the DEJ in RCM images, with high accuracy and repeatability, is challenging, especially in fair skin, due to low contrast, heterogeneous structure and high inter- and intra-subject variability. We recently proposed a semi-automated algorithm to localize the DEJ in z-stacks of RCM images of fair skin, based on feature segmentation and classification. Here we extend the algorithm to dark skin. The extended algorithm first decides the skin type and then applies the appropriate DEJ localization method. In dark skin, strong backscatter from the pigment melanin causes the basal cells above the DEJ to appear with high contrast. To locate those high contrast regions, the algorithm operates on small tiles (regions) and finds the peaks of the smoothed average intensity depth profile of each tile. However, for some tiles, due to heterogeneity, multiple peaks in the depth profile exist and the strongest peak might not be the basal layer peak. To select the correct peak, basal cells are represented with a vector of texture features. The peak with most similar features to this feature vector is selected. The results show that the algorithm detected the skin types correctly for all 17 stacks tested (8 fair, 9 dark). The DEJ detection algorithm achieved an average distance from the ground truth DEJ surface of around 4.7μm for dark skin and around 7-14μm for fair skin.

What's new in skin cancer? An analysis of guidelines and systematic reviews published in 2008-2009

This review summarizes clinically important findings from 17 systematic reviews and 2 guidelines on skin cancer indexed between April 2008 and April 2009. Melanoma primary-prevention measures, such as education, are more likely to be successful in younger children than adolescents, and general population screening for melanoma by whole-body examination is not currently supported by the evidence. A large systematic review of melanoma and pregnancy concluded that pregnancy does not affect prognosis. Two systematic reviews imply that sunburn later in life also increases the risk of melanoma, and that it is just as important as sunburn early in life. Three systematic reviews discussed the role of positron emission tomography and sentinel lymph-node biopsy for melanoma staging, but produced conflicting results. Superior diagnostic accuracy of dermatoscopy over naked-eye examination for melanoma was found in one review, while a second implied nonsignificantly higher sensitivity of computer-based diagnostic methods over dermatoscopy for melanoma but with reduced specificity. There were no identified randomized controlled trials of treatments for unresectable recurrent melanoma, and a review of immunotherapy with vaccines for melanoma failed to prove improved overall and disease-free survival. Guidelines for the management of basal cell carcinoma call for risk stratification, based on numerous factors including tumour size, site and histological subtype. Squamous cell carcinoma of the ear has been shown to spread to regional lymph nodes more commonly than to other sites, and may be predicted by depth of invasion, tumour size, cellular differentiation and completeness of excision.

Pilot study of semiautomated localization of the dermal/epidermal junction in reflectance confocal microscopy images of skin

Reflectance confocal microscopy (RCM) continues to be translated toward the detection of skin cancers in vivo. Automated image analysis may help clinicians and accelerate clinical acceptance of RCM. For screening and diagnosis of cancer, the dermal/epidermal junction (DEJ), at which melanomas and basal cell carcinomas originate, is an important feature in skin. In RCM images, the DEJ is marked by optically subtle changes and features and is difficult to detect purely by visual examination. Challenges for automation of DEJ detection include heterogeneity of skin tissue, high inter-, intra-subject variability, and low optical contrast. To cope with these challenges, we propose a semiautomated hybrid sequence segmentation/classification algorithm that partitions z-stacks of tiles into homogeneous segments by fitting a model of skin layer dynamics and then classifies tile segments as epidermis, dermis, or transitional DEJ region using texture features. We evaluate two different training scenarios: 1. training and testing on portions of the same stack; 2. training on one labeled stack and testing on one from a different subject with similar skin type. Initial results demonstrate the detectability of the DEJ in both scenarios with epidermis/dermis misclassification rates smaller than 10% and average distance from the expert labeled boundaries around 8.5 μm.

Objective melanoma progression

BACKGROUND/PURPOSE

Many aspects of the natural history of malignant melanoma (MM) are still unclear, specifically its appearance at onset and particularly how it changes in time. The purpose of our study was to retrospectively determine objective changes in melanoma over a 3-24-month observation period.

MATERIALS AND METHODS

Our study was carried out in two Italian dermatology centers. Digital dermoscopy analyzers (DB-Mips System) were used to retrospectively evaluate dermoscopic images of 59 MM (with no initial clinical aspects suggesting melanoma) under observation for 3-24 months. The analyzer evaluates 49 parameters grouped into four categories: geometries, colors, textures and islands of color. Multivariate analysis of variance for repeated measures was used to evaluate the statistical significance of the changes in the digital dermoscopy variables of melanomas.

RESULTS

Within-lesion analysis indicated that melanomas increased in dimension (Area, Minimum, and Maximum Diameter), manifested greater disorganization of the internal components (Red, Green and Blue Multicomponent, Contrast, and Entropy) and increased in clusters of milky pink color (Light Red Area).

CONCLUSION

Analysis of the parameters of our model and statistical analysis enabled us to interpret/identify the most significant factors of melanoma modification, providing quantitative insights into the natural history of this cutaneous malignancy.

The role of spectrophotometry in the diagnosis of melanoma

Background

Spectrophotometry (SPT) could represent a promising technique for the diagnosis of cutaneous melanoma (CM) at earlier stages of the disease. Starting from our experience, we further assessed the role of SPT in CM early detection.

Methods

During a health campaign for malignant melanoma at National Cancer Institute of Naples, we identified a subset of 54 lesions to be addressed to surgical excision and histological examination. Before surgery, all patients were investigated by clinical and epiluminescence microscopy (ELM) screenings; selected lesions underwent spectrophotometer analysis. For SPT, we used a video spectrophotometer imaging system (Spectroshade^® MHT S.p.A., Verona, Italy).

Results

Among the 54 patients harbouring cutaneous pigmented lesions, we performed comparison between results from the SPT screening and the histological diagnoses as well as evaluation of both sensitivity and specificity in detecting CM using either SPT or conventional approaches. For all pigmented lesions, agreement between histology and SPT classification was 57.4%. The sensitivity and specificity of SPT in detecting melanoma were 66.6% and 76.2%, respectively.

Conclusions

Although SPT is still considered as a valuable diagnostic tool for CM, its low accuracy, sensitivity, and specificity represent the main hamper for the introduction of such a methodology in clinical practice. Dermoscopy remains the best diagnostic tool for the preoperative diagnosis of pigmented skin lesions.

A support vector machine for decision support in melanoma recognition

The early diagnosis of melanoma is critical to achieving reduced mortality and increased survival. Although clinical examination is currently the method of choice for melanocytic lesion assessment, difficulties may arise in the diagnosis of atypical lesions. From both the naked eye and dermoscopic perspective, dysplastic naevi often exhibit a prominent heterogeneity of structure that renders their clinical distinction from melanoma difficult. To address these problems in diagnosis, there exists a heightened interest among researchers regarding the utility of machine learning techniques in computerised image analysis. Here we report on the utility, for dermatologists, of support vector machine (SVM) technology in melanoma diagnosis, using an archive of 199 digital dermoscopic images of excised atypical melanocytic lesions. Our best validation models achieved an average sensitivity and specificity for melanoma diagnosis of 0.86 and 0.72, respectively. Applying the best model to our test set yielded a sensitivity of 0.89, a diagnostic odds ratio of 14.09 and an area under the receiver operated characteristic curve (AUC) of 0.76. Advantages of the procedure implemented are the simplicity of feature extraction and the computationally cheap and efficient nature of SVMs. The derived model generalises well with outcomes that compare favourably with competing algorithms and expert assessment. In line with the concept of the utility of decision support systems in clinical practice, we propose that to reduce the risk of missed melanomas, both the dermatologists' assessment and the SVM diagnosis be incorporated into the clinical decision-making process.

Recent advances in diagnosing cutaneous melanomas

Early detection of lesions while minimising the unnecessary removal of benign lesions is the clinical aim in melanoma diagnosis. In this context, several non-invasive diagnostic modalities, such as dermoscopy, total body photography, and reflectance confocal microscopy have emerged in recent years aiming at increasing diagnostic accuracy. The main developments in this field are the integration of dermoscopy and digital photography into clinical practice.

Size functions for the morphological analysis of melanocytic lesions

Size Functions and Support Vector Machines are used to implement a new automatic classifier of melanocytic lesions. This is mainly based on a qualitative assessment of asymmetry, performed by halving images by several lines through the center of mass, and comparing the two halves in terms of color, mass distribution, and boundary. The program is used, at clinical level, with two thresholds, so that comparison of the two outputs produces a report of low-middle-high risk. Experimental results on 977 images, with cross-validation, are reported.

Optical coherence tomography for imaging of skin and skin diseases

Optical coherence tomography (OCT) is an emerging imaging technology based on light reflection. It provides real-time images with up to 2-mm penetration into the skin and a resolution of approximately 10 microm. It is routinely used in ophthalmology. The normal skin and its appendages have been studied, as have many diseases. The method can provide accurate measures of epidermal and nail changes in normal tissue. Skin cancer and other tumors, as well as inflammatory diseases, have been studied and good agreement found between OCT images and histopathological architecture. OCT also allows noninvasive monitoring of morphologic changes in skin diseases and may have a particular role in the monitoring of medical treatment of nonmelanoma skin cancer. The technology is however still evolving and continued technological development will necessitate an ongoing evaluation of its diagnostic accuracy. Several technical solutions are being pursued to further improve the quality of the images and the data provided, and OCT is being integrated in multimodal imaging devices that would potentially be able to provide a quantum leap to the imaging of skin in vivo.