RESUMEN

There has been growing scientific interest in the research field of deep learning techniques applied to skin cancer diagnosis in the last decade. Though encouraging data have been globally reported, several discrepancies have been observed in terms of study methodology, result presentations and validation in clinical settings. The present review aimed to screen the scientific literature on the application of DL techniques to dermoscopic melanoma/nevi differential diagnosis and extrapolate those original studies adequately by reporting on a DL model, comparing them among clinicians and/or another DL architecture. The second aim was to examine those studies together according to a standard set of statistical measures, and the third was to provide dermatologists with a comprehensive explanation and definition of the most used artificial intelligence (AI) terms to better/further understand the scientific literature on this topic and, in parallel, to be updated on the newest applications in the medical dermatologic field, along with a historical perspective. After screening nearly 2000 records, a subset of 54 was selected. Comparing the 20 studies reporting on convolutional neural network (CNN)/deep convolutional neural network (DCNN) models, we have a scenario of highly performant DL algorithms, especially in terms of low false positive results, with average values of accuracy (83.99%), sensitivity (77.74%), and specificity (80.61%). Looking at the comparison with diagnoses by clinicians (13 studies), the main difference relies on the specificity values, with a +15.63% increase for the CNN/DCNN models (average specificity of 84.87%) compared to humans (average specificity of 64.24%) with a 14,85% gap in average accuracy; the sensitivity values were comparable (79.77% for DL and 79.78% for humans). To obtain higher diagnostic accuracy and feasibility in clinical practice, rather than in experimental retrospective settings, future DL models should be based on a large dataset integrating dermoscopic images with relevant clinical and anamnestic data that is prospectively tested and adequately compared with physicians.

RESUMEN

BACKGROUND: Phacomatosis pigmentokeratotica (PPK) is a distinct and rare type of epidermal nevus syndrome characterized by coexisting nonepidermolytic organoid sebaceous nevus (SN) with one or more speckled lentiginous nevi (SLN). Atypical nevi including compound Spitz and compound dysplastic may manifest within regions of SLN. Patients with PPK, or similar atypical nevus syndromes, may be subject to a significant lifetime number of biopsies, leading to pain, scarring, anxiety, financial burden, and decreased quality of life. The current literature includes case reports, genetics, and associated extracutaneous symptoms of PPK, but use of noninvasive imaging techniques have not been explored. We aim to investigate the value of high-frequency ultrasound (HFUS) and optical coherence tomography (OCT) in discriminating morphological features of pigmented lesions and nevus sebaceous within one patient with PPK. MATERIALS AND METHODS: Two modalities, (1) HFUS imaging, based on acoustic properties and (2) OCT imaging, based on optical properties, were used to image a patient with PPK. Benign pigmented lesions, which may raise clinical suspicion for significant atypia, and nevus sebaceous, were selected on different areas of the body to be studied. RESULTS: Five pigmented lesions and one area of nevus sebaceous were imaged and analyzed for noninvasive features. Distinct patterns of hypoechoic features were seen on HFUS and OCT. CONCLUSION: HFUS provides a deep view of the tissue, with ability to differentiate gross structures beneath the skin. OCT provides a smaller penetration depth and a higher resolution. We have described noninvasive features of atypical nevi and nevus sebaceous on HFUS and OCT, which indicate benign etiology.

Asunto(s)

RESUMEN

Since the late 1970s, the diagnosis and management of dysplastic nevi have been areas fraught with controversy in the fields of dermatology and dermatopathology. Diagnostic uncertainty and lack of standardized nomenclature continue to propagate confusion among clinicians, dermatopathologists, and patients. In part I of this CME review article, we summarize the historical context that gave rise to the debate surrounding dysplastic nevi and review key features for diagnosis, classification, and management, as well as epidemiology. We discuss essentials of clinical criteria, dermoscopic features, histopathologic features, and the diagnostic utility of total body photography and reflectance confocal microscopy in evaluating dysplastic nevi, with emphasis on information available since the last comprehensive review a decade ago.

Asunto(s)

RESUMEN

Introduction: It is well known that multiple patient-related risk factors contribute to the development of cutaneous melanoma, including demographic, phenotypic and anamnestic factors. Objectives: We aimed to investigate which MM risk factors were relevant to be incorporated in a risk scoring-classifier based clinico-dermoscopic algorithm. Methods: This retrospective study was performed on a monocentric dataset of 374 atypical melanocytic skin lesions sharing equivocal dermoscopic features, excised in the suspicion of malignancy. Dermoscopic standardized images of 258 atypical nevi (aN) and 116 early melanomas (eMM) were collected along with objective lesional data (i.e., maximum diameter, specific body site and body area) and 7 dermoscopic data. All cases were combined with a series of 10 MM risk factors, including demographic (2), phenotypic (5) and anamnestic (3) ones. Results: The proposed iDScore 2021 algorithm is composed by 9 variables (age, skin phototype I/II, personal/familiar history of MM, maximum diameter, location on the lower extremities (thighs/legs/ankles/back of the feet) and 4 dermoscopic features (irregular dots and globules, irregular streaks, blue gray peppering, blue white veil). The algorithm assigned to each lesion a score from 0 to 18, reached an area under the ROC curve of 92% and, with a score threshold ≥ 6, a sensitivity (SE) of 98.2% and a specificity (SP) of 50.4%, surpassing the experts in SE (+13%) and SP (+9%). Conclusions: An integrated checklist combining multiple anamnestic data with selected relevant dermoscopic features can be useful in the differential diagnosis and management of eMM and aN exhibiting with equivocal features.

RESUMEN

Atypical (Clark) nevi are benign tumors that may be considered precursors of melanoma. Many studies acknowledge a linear progression from typical to atypical nevi that eventually transform into melanoma. It is often challenging to differentiate a Clark nevus from melanoma, especially in its early stages, due to their clinical, dermoscopic, and histological resemblance. Dermoscopy is a powerful tool in early melanoma diagnosis, but it is a subjective method of examination. Therefore, the use of dermoscopic algorithms and checklists can overcome this issue. In the case of a difficult diagnosis, since both dermoscopy and histopathological exam are subjective methods of examination, modern molecular biology techniques can be used to distinguish between benign and malignant tumors. This study aimed to test the accuracy of specific clinical and dermoscopic criteria in order to distinguish between benign and malignant tumors, with a secondary objective to provide an overview of the clinical and dermoscopic features of atypical nevi and melanoma. In the present study, dermoscopic algorithms did not necessarily help distinguish benign and malignant tumors but demonstrated that nevi and melanoma have similar characteristics.

RESUMEN

Background: The use of mobile electronic devices as support to medical activity was largely implemented in the past decade. Introduction: Our first aim was to evaluate the frequency of use of different electronic devices, that is, personal computer (PC), notebook, tablet, smartphone, in a pool of dermatologists recruited to perform multiple online testing session on difficult melanocytic skin lesions (MSLs) cases. The second aim was to evaluate the feasibility of each device in terms of teledermatologic diagnostic performance; the use of four different diagnostic methods, that is, intuitive diagnosis and three dermoscopic algorithms, was also investigated. Materials and Methods: A total of 111 dermatologists with 4 different levels of experience in dermoscopy, performed 4 tests (intuitive diagnosis and iDScore, ABCD rule, 7-point-checklist-based diagnosis) on 979 MSLs blinded cases. Each testing session was performed with a preferred device. Results: The overall highest areas under the receiver operating characteristic (AUROC) (82%) was obtained by young generation dermoscopists 1-4 years experience) when using an integrated clinical dermoscopic algorithm (iDScore) on a notebook. The average dermatologist using the iDScore obtained AUROC 77.40% with large screen devices (PC and notebook) 77.6% with small screen (tablet, smartphone) and 78.2% by combining the two. Discussion: Young generation of dermoscopists alternately use different devices, whereas elderly generation still prefer to use the PC. The diagnostic performances obtained with small/large screen were not statistically different from those obtained with fixed/mobile devices. Conclusions: Mobile devices were feasible tools to achieve adequate diagnostic accuracy in difficult MSLs, on a teledermatology setting, independently from participant skill level/age.

Asunto(s)

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

Early recognition of melanoma in situ (MIS) is an ongoing challenge in dermatology. It rarely arises 'de novo', most frequently resulting due to the transformation of an atypical nevus. The diagnostic criteria for MIS are diverse dermoscopy being the most used and it has a sensitivity of 83% and a specificity of 69% in detecting melanomas. The main objective of our study was to establish the sensitivity and the specificity of each of the 7-point checklist criteria used to differentiate melanocytic nevi from in situ malignant melanoma. The study group included 200 patients, aged over 18 years, with atypical pigmentary nevi after clinical aspects that presented changes in clinical appearance (shape, color, dimensions) during the last 6 months. On each patient we used the 7-point checklist of Argenziano (C1-C7). The study was performed at the Medical Center Dr. Ianosi, in Craiova between January 2016 and September 2018 and it was used Molemax HD computerized dermatoscope. The C1÷C3 criteria are significantly relevant in establishing the diagnosis of MIS in comparison with the diagnosis of nevus, unlike the C4-C7 criterion that is not definitely relevant for confirmation of the MIS diagnosis. There are no enough specific dermoscopic criteria to differentiate MIS from atypical nevus.

RESUMEN

BACKGROUND: Differential diagnosis of clinically atypical nevi (aN) and early melanomas (eMM) still represents a challenge even for experienced dermoscopists, as dermoscopy alone is not sufficient to adequately differentiate these equivocal melanocytic skin lesions (MSLs). OBJECTIVES: The objectives of this study were to investigate what were the most relevant parameters for noninvasive differential diagnosis between eMM and aN among clinical, personal, and dermoscopic data and to evaluate their impact as risk factors for malignancy. METHODS: This was a retrospective study performed on 450 MSLs excised from 2014 to 2016 with a suspicion of malignancy. Dermoscopic standardized images of the 450 MSLs (300 aN and 150 eMM) were collected and evaluated. Patients' personal data (ie, age, gender, body site, maximum diameter) were also recorded. Dermoscopic evaluations were performed by 5 different experts in dermoscopy blinded to histopathological diagnosis. Fleiss' κ was calculated to measure concordance level between experts in the description of dermoscopic parameters for each MSL. The power of the studied variables in discriminating malignant from benign lesions was also investigated through F-statistics. RESULTS: The variables age and maximum diameter supplied the highest discriminant power (F = 253 and 227, respectively). Atypical network, blue white veil and white shiny streaks were the most significant dermoscopic patterns suggestive of malignancy (F = 110, 104 and 99.5, respectively). Shiny white streaks was the only dermoscopic parameter to obtain satisfactory concordance value. Gender was not a discriminant factor. The specific statistical weight of clinical and personal data (ie, "patient's age" and "lesion diameter") surpassed those of atypical dermoscopic features. CONCLUSIONS: The objective clinical and personal data collected here could supply a fundamental contribution in the correct diagnosis of equivocal MSLs and should be included in diagnostic algorithms along with significant dermoscopic features (ie, atypical network, blue-white veil, and shiny white streaks).

RESUMEN

BACKGROUND: Dysplastic nevi (DN) are graded by their degree of atypia into 3 categories of mild, moderate, and severe. In many practices, DN with moderate or severe atypia are generally excised regardless of the status of the shave specimen margins. OBJECTIVE: With a new approach toward the margins on the shave removal specimens (SRS), the goal herein is to assess whether the shave removal procedure can sufficiently remove DN with moderate or severe atypia. METHODS: A total of 426 SRS diagnosed with DN showing moderate or severe atypia between January and December 2015 along with their post-shave excision specimens were reviewed. Based on the author's experience, clear or negative margins on the SRS were defined as neoplastic melanocytes confined within >0.2 mm of the lateral and deep specimen margins. The biopsy specimens were accompanied by Melan-A highlighting the subtle neoplastic cells. RESULTS: With a negative predictive value (NPV) of 98.4% (confidence interval: 97.2% to 100%, P < .001), DN showing moderate or severe atypia with clear margins are most likely removed by the shave procedure. CONCLUSION: Routine excision of DN showing moderate or severe atypia with clear margins on SRS is not necessary. Regular surveillance is sufficient.

Asunto(s)

RESUMEN

BACKGROUND: The extent of variability in treatment suggestions for melanocytic lesions made by pathologists is unknown. OBJECTIVE: We investigated how often pathologists rendered suggestions, reasons for providing suggestions, and concordance with national guidelines. METHODS: We conducted a cross-sectional survey of pathologists. Data included physician characteristics, experience, and treatment recommendation practices. RESULTS: Of 301 pathologists, 207 (69%) from 10 states (California, Connecticut, Hawaii, Iowa, Kentucky, Louisiana, New Jersey, New Mexico, Utah, and Washington) enrolled. In all, 15% and 7% reported never and always including suggestions, respectively. Reasons for offering suggestions included improved care (79%), clarification (68%), and legal liability (39%). Reasons for not offering suggestions included referring physician preference (48%), lack of clinical information (44%), and expertise (29%). Training and caseload were associated with offering suggestions (P < .05). Physician suggestions were most consistent for mild/moderate dysplastic nevi and melanoma. For melanoma in situ, 18 (9%) and 32 (15%) pathologists made suggestions that undertreated or overtreated lesions based on National Comprehensive Cancer Network (NCCN) guidelines, respectively. For invasive melanoma, 14 (7%) pathologists made treatment suggestions that undertreated lesions based on NCCN guidelines. LIMITATIONS: Treatment suggestions were self-reported. CONCLUSIONS: Pathologists made recommendations ranging in consistency. These findings may inform efforts to reduce treatment variability and optimize patterns of care delivery for patients.

Asunto(s)

RESUMEN

Reflectance confocal microscopy (RCM) together with dermoscopy enables improved differentiation of melanomas from most nevi. The resulting high sensitivity for detecting melanoma with RCM is complemented by a concomitant increased specificity, which results in the reduction of unnecessary biopsies of nevi. Although RCM can achieve high diagnostic accuracy for early melanoma detection, false-negative and false-positive cases of melanoma are occasionally encountered. This article reviews the essential clues and pitfalls for the diagnosis of melanoma via RCM and highlights the importance of evaluating RCM findings in light of the clinical scenario and dermoscopic features.

Asunto(s)

RESUMEN

Detection and removal of melanoma, before it has metastasized, dramatically improves prognosis and survival. The purpose of this chapter is to (1) summarize current methods of melanoma detection and (2) review state-of-the-art detection methods and technologies that have the potential to reduce melanoma mortality. Current strategies for the detection of melanoma range from population-based educational campaigns and screening to the use of algorithm-driven imaging technologies and performance of assays that identify markers of transformation. This chapter will begin by describing state-of-the-art methods for educating and increasing awareness of at-risk individuals and for performing comprehensive screening examinations. Standard and advanced photographic methods designed to improve reliability and reproducibility of the clinical examination will also be reviewed. Devices that magnify and/or enhance malignant features of individual melanocytic lesions (and algorithms that are available to interpret the results obtained from these devices) will be compared and contrasted. In vivo confocal microscopy and other cellular-level in vivo technologies will be compared to traditional tissue biopsy, and the role of a noninvasive "optical biopsy" in the clinical setting will be discussed. Finally, cellular and molecular methods that have been applied to the diagnosis of melanoma, such as comparative genomic hybridization (CGH), fluorescent in situ hybridization (FISH), and quantitative reverse transcriptase polymerase chain reaction (qRT-PCR), will be discussed.

Asunto(s)

RESUMEN

Familial atypical multiple mole melanoma syndrome (FAMMMS) is an autosomal dominant genodermatosis characterized by multiple melanocytic nevi, usually more than 50, and a family history of melanoma. It is known to be associated with carcinoma of pancreas and other malignancies involving gastrointestinal tract, breast, lung, larynx, and skin in the kindred. There is no published report of FAMMMS in dark-skinned individuals. We report a case of FAMMMS in a dark-skinned adult Indian male, who had multiple extensive nevi all over the body and oral mucosa; associated with malignant melanoma, squamous cell carcinoma (Marjolin's ulcer), and carcinoma of pancreas. His father had died of carcinoma of lung and his sister had a partial phenotypic expression. The clinical presentation of the case is discussed with review of literature.