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

Background Dermoscopy improves diagnostic accuracy of the unaided eye for melanoma, and digital dermoscopy with artificial intelligence or computer diagnosis has also been shown useful for the diagnosis of melanoma. At present there is no clear evidence regarding the diagnostic accuracy of dermoscopy compared with artificial intelligence. Objectives To evaluate the diagnostic accuracy of dermoscopy and digital dermoscopy/artificial intelligence for melanoma diagnosis and to compare the diagnostic accuracy of the different dermoscopic algorithms with each other and with digital dermoscopy/artificial intelligence for the detection of melanoma. Methods A literature search on dermoscopy and digital dermoscopy/artificial intelligence for melanoma diagnosis was performed using several databases. Titles and abstracts of the retrieved articles were screened using a literature evaluation form. A quality assessment form was developed to assess the quality of the included studies. Heterogeneity among the studies was assessed. Pooled data were analysed using meta‐analytical methods and comparisons between different algorithms were performed. Results Of 765 articles retrieved, 30 studies were eligible for meta‐analysis. Pooled sensitivity for artificial intelligence was slightly higher than for dermoscopy (91% vs. 88%; P = 0·076). Pooled specificity for dermoscopy was significantly better than artificial intelligence (86% vs. 79%; P < 0·001). Pooled diagnostic odds ratio was 51·5 for dermoscopy and 57·8 for artificial intelligence, which were not significantly different (P = 0·783). There were no significance differences in diagnostic odds ratio among the different dermoscopic diagnostic algorithms. Conclusions Dermoscopy and artificial intelligence performed equally well for diagnosis of melanocytic skin lesions. There was no significant difference in the diagnostic performance of various dermoscopy algorithms. The three‐point checklist, the seven‐point checklist and Menzies score had better diagnostic odds ratios than the others; however, these results need to be confirmed by a large‐scale high‐quality population‐based study.     

Pre-operative diagnosis of pigmented skin lesions: in vivo dermoscopy performs better than dermoscopy on photographic images

BACKGROUND: Epiluminescence microscopy (ELM) (dermoscopy, dermatoscopy) is a technique for non-invasive diagnosis of pigmented skin lesions that improves the diagnostic performance of dermatologists. Little is known about the possible influence of associated clinical features on the reliability of dermoscopic diagnosis during in vivo examination. OBJECTIVE: To compare diagnostic performance of in vivo dermoscopy (combined clinical and dermoscopic examination) with that of dermoscopy performed on photographic slides (pure dermoscopy). DESIGN: This case series comprised 256 pigmented skin lesions consecutively identified as suspicious or equivocal during examination in a general dermatological clinic. Clinical examination and in vivo dermoscopy were performed before excision by two trained dermatologists. The same observers carried out dermoscopy on photographic slides at a later time, and these three diagnostic classifications were reviewed together with the histological findings for the individual lesions. This was carried out in a university hospital. RESULTS: In vivo dermoscopy performed better than dermoscopy on photographic slides for classification of pigmented skin lesions compared with histological diagnosis, and both performed better than general clinical diagnosis. In vivo dermoscopic diagnosis of melanoma showed 98.1% sensitivity, 95.5% specificity and 96.1% diagnostic accuracy while dermoscopic diagnosis of melanoma on photographic slides was less reliable with 81.5% sensitivity, 86.7% specificity and 85.2% diagnostic accuracy. In particular, diagnosis of melanoma based on photographic slides led to nine false negative cases (three in situ, six invasive; thickness ranges 0.2-1.5 mm). CONCLUSIONS: In vivo dermoscopy, i.e. combined clinical and dermoscopic examination, is more reliable than dermoscopy on photographic slides. In clinical practice, therefore, in vivo dermoscopy cannot be considered independent from associated clinical characteristics of the lesions, which help the trained observer to reach a more precise classification. This may have implications on the reliability of ELM diagnosis made by an observer not fully trained in the clinical diagnosis of pigmented skin lesions or by a remote observer during digital ELM teleconsultation.     

Surveillance of patients at high risk for cutaneous malignant melanoma using digital dermoscopy

BACKGROUND: Dermoscopy has improved the sensitivity and specificity of clinical diagnosis of melanoma from 60% to over 90%. However, in order not to miss melanoma a certain percentage of suspicious but benign lesions has to be excised. OBJECTIVES: To evaluate the dermoscopic changes and the rates of excision in benign melanocytic naevi and cutaneous malignant melanoma in long-term follow-up of high-risk patients using digital dermoscopy. METHODS: Digital dermoscopic images of 2015 atypical melanocytic naevi in 196 high-risk patients were analysed retrospectively. Among others, the following data were collected for each naevus: changes in surface area, overall architecture, dermoscopic patterns and distribution of pigmentation. All tumours suspicious for melanoma or showing asymmetrical changes were excised. RESULTS: During a median follow-up time of 25 months 128 (6.4%) of all naevi showed changes in size or architecture. Eighty-six per cent of all changes in patients who attended more than one visit were observed at the first follow-up visit. Thirty-three lesions showing changes were excised and two melanomas in situ and 31 melanocytic naevi were diagnosed. CONCLUSIONS: Follow-up examinations using digital dermoscopy revealed unchanged morphology in the large majority of melanocytic naevi. Excisions were only performed in cases of asymmetrical growth, asymmetrical changes of pigmentation, or development of dermoscopic features indicative of melanoma. The ratio of 33 lesions excised in order to identify two melanomas in situ seems reasonable and may be further reduced in future.     

Practical color calibration for dermoscopy, applied to a digital epiluminescence microscope

BACKGROUND/PURPOSE: The assessment of colors is essential for melanoma (MM) diagnosis, both for pattern analysis on dermoscopic images, and when using semiquantitative methods. Our aim was to provide a simple, precise characterization and reproducible calibration of the color response for dermoscopic instruments. METHODS: Three processes were used to correct the non-uniform illumination pattern of the instrument, to easily estimate the camera gamma settings and to describe the color space conversion matrices required to produce standard images, in any color space. A specific color space was also developed to optimize the representation of dermatoscopic colors. The calibration technique was tested both on synthetic reference surfaces and on real images by comparing the difference between the images colors obtained with two different equipments. RESULTS: The differences between the images acquired by means of the two instruments, calculated on the reference patterns after calibration, were up to 10 times lower then before, while comparison of histograms referring to real images provided an improvement of about seven times on average. CONCLUSIONS: A complete workflow for dermatologic image calibration, which allows the user to continue using his own software and algorithms, but with a much higher informative content, is presented. The technique is simple and may improve cooperation between different research centers, in teleconsulting contexts or for result comparisons.     

Dysplastic naevus vs. in situ melanoma: digital dermoscopy analysis

BACKGROUND: To date, much confusion exists about the biological significance of dysplastic naevi and about the relationship between melanocytic dysplasia and clinical atypia. OBJECTIVES: To use a digital dermoscopy analyser with a series of 'borderline' pigmented skin lesions (i.e. dysplastic naevi and in situ melanomas) to find correlation between the studied variables and to determine their discriminating power with respect to histological diagnosis. METHODS: The pigmented skin lesions (n = 174) were histologically examined by three experienced dermatopathologists and identified as in situ melanomas (n = 38) and dysplastic naevi (n = 136). The system evaluated 48 parameters as possible discriminant variables, grouped into four categories: geometry, colours, textures and islands of colour. Once the lesions were analysed (stepwise discriminant analysis), sensitivity, specificity and accuracy were calculated. RESULTS: At the end of the stepwise procedure the percentage of cases classified correctly was 71.8%. Of 136 dysplastic naevi only 98 were classified correctly, while 27 of 38 in situ melanomas were recognized correctly. CONCLUSIONS: We conclude that there are so far no digital dermoscopic criteria that can clearly distinguish dysplastic naevi from in situ melanomas.     

Dermatoscopy in the diagnosis of pigmented skin lesions: a new semiology for the dermatologist.

Dermatoscopy or epiluminescence microscopy (ELM), is a noninvasive method that enables clinicians to evaluate fully--by means of a magnified oil immersion diascopy--numerous morphological features, not visible with the naked eye, which enhance the diagnosis of nearly all pigmented skin lesions. In recent years, a burst of research activity in this topic has been carried out, dealing with different aspects, and new frontiers, of this technique. First, a continuous refinement of dermatoscopic terminology is undertaken, paying particular attention to the diagnostic performance of dermatoscopy at peculiar anatomical sites and to the building of different dermatoscopic algorithms aimed at a simplified diagnosis of melanoma, even for less experienced observers. Another point of interest concerns the possible role of dermatoscopy in the pre-operative assessment of melanoma thickness. Finally, promising data about the role of digital equipment in the follow up of melanocytic skin lesions as well as in the automated diagnosis of pigmented skin lesions have been recently reported. This paper should enable readers to become familiar with the procedure and terminology of ELM in the diagnosis of pigmented skin lesions encouraging a greater understanding of different methods (pattern analysis, algorithms) in the diagnosis of melanoma using ELM.     

Influence of variability in assessment of Breslow thickness,mitotic rate and ulceration among US pathologists interpreting invasive melanoma,for the purpose of AJCC staging

Background

Melanoma staging has depended on depth of invasion (Breslow thickness, BT), mitotic rate (MR) and ulceration. In anticipation of the AJCC's eighth edition, variability in pathologists' assessment of these factors and consequently in tumor staging was assessed.

Methods

One‐hundred and fifteen cases of invasive melanoma, established by a consensus panel, were assessed by 187 pathologists. Variation was studied in BT, the detection of mitotic figures, and ulceration. The sources of this variation and its effect on tumor staging are considered.

Results

On average, participant assessments closely approached consensus BT. Greater variation was identified in the classification of mitogenicity, which (like ulceration) upstages a T1 melanoma from T1a to T1b in the seventh but not eighth edition. In cases with a T1a diagnosis by the consensus panel, 15.6% of participants identified one or more mitotic figures (indicative of a false positive); and in cases diagnosed asT1b by the consensus panel, 32.0% of participants failed to find mitotic figures (false negative).

Conclusion

Variability in the staging of T1 melanoma among pathologists when using the AJCC seventh edition criteria is closely related to the detection of mitotic figures, with BT playing a less prominent role. Decreased variability is expected after implementation of the eighth edition.     

The role of pattern analysis and the ABCD rule of dermoscopy in the detection of histological atypia in melanocytic naevi

BACKGROUND: Clinical features of melanocytic naevi correlate poorly with the presence, histopathologically, of architectural disorder and cytological atypia, making the detection of histological atypia by means of macroscopic appearance unreliable. OBJECTIVES: The aim of this study was to investigate the diagnostic effectiveness of dermoscopy in the non-invasive detection of histological atypia in naevi. METHODS: Observers blinded for histological diagnosis classified a series of 168 melanocytic naevi as common or atypical on the basis of their clinical features and on their dermoscopic profile. The diagnostic performance of both methods compared with the true (histopathological) diagnosis was assessed. RESULTS: Dermoscopy using pattern analysis showed better results than clinical examination in the non-invasive detection of naevi with architectural disorder with or without cytological atypia (diagnostic accuracy 45% vs. 28%). A statistically significant difference in the frequency of dermoscopic parameters between atypical and common naevi was found for atypical pigment network (39% vs. 17%, P = 0.001) and dermoscopic regression structures (13% vs. 2%, P = 0.008). Dermoscopic features, which best predicted histological atypia in naevi, were regression structures (white scar-like areas or peppering), irregular vascular pattern and grey-blue areas (positive predictive values 83%, 83% and 73%, respectively). In contrast, no statistically significant difference in the mean values of the ABCD score between common and atypical naevi was found. The best diagnostic performance of dermoscopy by means of the ABCD rule (cut-off point of 4.0 of total dermoscopy score) was not dissimilar to that of clinical diagnosis (diagnostic accuracy 30%). CONCLUSIONS: Dermoscopy by means of pattern analysis enhances the diagnostic accuracy of dermatologists in the prediction of histological atypia in melanocytic naevi as compared with clinical examination alone.     

A practical review of dermoscopy for pediatric dermatology part I: Melanocytic growths

The value of dermoscopy in the detection of skin cancer is well established. Less is published on the utility of dermoscopy in the evaluation of pediatric skin disease. Our review (in two parts) aims to serve as an update on pediatric dermoscopy and to provide readers with a practical application for the use of dermoscopy in pediatric dermatology clinics. In part I, we propose a dermoscopy algorithm for pediatric skin disease and melanocytic growths, and in part II, we address vascular growths, common skin infections, and inflammatory conditions for which dermoscopy is valuable.     

Possible role of dermoscopy in the detection of a primary cutaneous melanoma of unknown origin

For 2-8% of patients with metastatic melanoma, cutaneous and mucosal clinical examination does not lead to diagnosis of the primary tumour, which remains unknown. We report the case of a 41-year-old male patient who had received a diagnosis of metastatic melanoma after histological examination of an enlarged axillary lymph node, without previous detection of the primary lesion at his first dermatological examination. No pigmented skin lesions located in the anatomical area potentially drained by the affected axillary basin showed clinical features suggestive of a melanoma. Neither did the so-called 'ugly duckling' sign help us to identify the melanoma, because of the presence of a large number of clinically similar, common or slightly atypical melanocytic lesions located in that area. After dermoscopic examination we were able to narrow the field of possible candidates for excision to four lesions, selected on the basis of their dermoscopic features. Histological examination revealed the primary melanoma (superficial spreading melanoma (SSM), level III, thickness 0.5 mm)--located on the back--and three naevi with atypia. Preoperative distinction of the melanoma from the other three lesions was not possible because of the lack of well-established features of malignancy, even at dermoscopic analysis ('featureless' melanoma). Dermoscopy may thus play a role in the detection of a clinically unknown primary melanoma by narrowing the field of lesions to be removed for histological examination, saving many unnecessary excisions that would otherwise be inevitable.     

Dermoscopy is a suitable method for the observation of the pregnancy-related changes in melanocytic nevi

BACKGROUND: It is a common opinion that expansion and darkening in melanocytic nevi may occur during pregnancy. The main problem is that whether it is a usual finding, or it is a condition that requires suspicion about melanoma. OBJECTIVES: It was aimed to find the changes that might occur in the sizes and structures of melanocytic nevi during pregnancy. METHODS: Ninety-seven nevi of the 56 pregnant women in the first trimester were evaluated in the study. The localization and size of the nevi were recorded on a standard body diagram. After clinical examination, dermoscopic analyses were applied. Pattern analyses were done, and total dermoscopy scores (TDS) were calculated by applying ABCD scoring system. All subjects were seen again during the third trimester. RESULTS: There was a statistically significant difference between the mean diameters of nevi in the first and third trimester (P = 0.001). Of nevi whose diameters increased, 10 (50.00%) were localized on the front of body, 6 (30.00%) on the face and neck, 3 (15.00%) on the legs, and 1 (5.00%) on the back. The enlargement in diameters was more significant on the front of the body, but there was no statistically significant difference. Compared according to the pattern analysis, new dot formation was observed only on the structure of six nevi during the last trimester. Four of them were localized on the front of the body. There was statistically significant increase in mean TDS in comparison between the first and third trimesters (P = 0008). CONCLUSIONS: During the pregnancy, widening in diameters and structure changes of nevi may be seen especially on the front of the body. We also think that these findings might be connected with expansion of the skin during pregnancy. Dermoscopic controls are the first choice of method to analyse the nevi since the patient may not recognize these changes.     

Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting

Background  Dermoscopy is a noninvasive technique that enables the clinician to perform direct microscopic examination of diagnostic features, not seen by the naked eye, in pigmented skin lesions. Diagnostic accuracy of dermoscopy has previously been assessed in meta-analyses including studies performed in experimental and clinical settings.
Objectives  To assess the diagnostic accuracy of dermoscopy for the diagnosis of melanoma compared with naked eye examination by performing a meta-analysis exclusively on studies performed in a clinical setting.
Methods  We searched for publications from 1987 to January 2008 and found nine eligible studies. The selected studies compare diagnostic accuracy of dermoscopy with naked eye examination using a valid reference test on consecutive patients with a defined clinical presentation, performed in a clinical setting. Hierarchical summary receiver operator curve analysis was used to estimate the relative diagnostic accuracy for clinical examination with, and without, the use of dermoscopy.
Results  We found the relative diagnostic odds ratio for melanoma, for dermoscopy compared with naked eye examination, to be 15·6 [95% confidence interval (CI) 2·9–83·7, P  = 0·016]; removal of two outlier studies changed this to 9·0 (95% CI 1·5–54·6, P  = 0·03).
Conclusions  Dermoscopy is more accurate than naked eye examination for the diagnosis of cutaneous melanoma in suspicious skin lesions when performed in the clinical setting.     

Clinical usefulness of dermoscopy in the management of lentigo maligna melanoma treated with topical imiquimod: A case report

The importance of dermoscopy for diagnosing lentigo maligna melanoma (LMM) is well known. More recently, dermoscopy has been proposed as a useful tool also for the treatment choice and monitoring. Herein, we present an 87‐year‐old woman, who was successfully treated with imiquimod 5% cream after surgical persistence of residual LMM and for whom dermoscopy was helpful to assist diagnosis and assess tumor persistence after surgery and its response to topical treatment with imiquimod.     

Impact of digital dermoscopy analysis on the decision to follow up or to excise a pigmented skin lesion: a multicentre study

Background: The quality of early malignant melanoma (MM) diagnosis is dependent on the experience of dermatologists, tools like dermoscopy and histopathology, and awareness and education of the studied population. Does a higher rate of excision of pigmented skin lesions (PSL) increase the rate of detected melanomas? Material and Methods: The DB‐MIPS objective tool, able to evaluate mathematical defined variables, has been used to verify the variability of measurements among PSL stored by five different centres located in Italy, Switzerland, and Germany. Results: The objective analysis showed low differences in terms of moles' features among the different groups, arguing for robustness of the dermatological patient's PSL inspection. Differences in terms of false positives and predictive positive values have been detected. The tendency to follow up a lesion was proportional to the percentage of thin MM (<0.75 mm tumour thickness), while the interventism was proportional to the percentage of dysplastic moles. Similar percentage of thin melanoma has been observed in all the centres, indicating a standardization in early diagnosing among experienced dermatologists. The main difference among the centres was their mode of action, i.e. to follow up or remove suspicious PSL. Conclusion: Interventism depends neither on the geographic site nor on the features of the observed moles. Higher removal rates do not correspond to higher MM detections: this means that an in‐depth knowledge of melanoma patterns is required and follow‐up of suspicious moles is highly suggested.