Expert Agreement on the Presence and Spatial Localization of Melanocytic Features in Dermoscopy.

Dermoscopy aids in melanoma detection; however, agreement on dermoscopic features, including those of high clinical relevance, remains poor. In this study, we attempted to evaluate agreement among experts on exemplar images not only for the presence of melanocytic-specific features but also for spatial localization. This was a cross-sectional, multicenter, observational study. Dermoscopy images exhibiting at least 1 of 31 melanocytic-specific features were submitted by 25 world experts as exemplars. Using a web-based platform that allows for image markup of specific contrast-defined regions (superpixels), 20 expert readers annotated 248 dermoscopic images in collections of 62 images. Each collection was reviewed by five independent readers. A total of 4,507 feature observations were performed. Good-to-excellent agreement was found for 14 of 31 features (45.2%), with eight achieving excellent agreement (Gwet's AC >0.75) and seven of them being melanoma-specific features. These features were peppering/granularity (0.91), shiny white streaks (0.89), typical pigment network (0.83), blotch irregular (0.82), negative network (0.81), irregular globules (0.78), dotted vessels (0.77), and blue-whitish veil (0.76). By utilizing an exemplar dataset, a good-to-excellent agreement was found for 14 features that have previously been shown useful in discriminating nevi from melanoma. All images are public (www.isic-archive.com) and can be used for education, scientific communication, and machine learning experiments.

Perifollicular linear projections: A dermatoscopic criterion for the diagnosis of lentigo maligna on the face.

BACKGROUND: Lentigo maligna (LM) can mimic benign, flat, pigmented lesions and can be challenging to diagnose. OBJECTIVE: To describe a new dermatoscopic feature termed "perifollicular linear projections (PLP)" as a diagnostic criterion for LM on the face. METHODS: Retrospective study on reflectance confocal microscopy and dermatoscopy images of flat facial pigmented lesions originating from 2 databases. PLP were defined as short, linear, pigmented projections emanating from hair follicles. Dermatoscopy readers were blinded to the final histopathologic diagnosis. RESULTS: From 83 consecutive LMs, 21/83 (25.3%) displayed "bulging of hair follicles" on reflectance confocal microscopy and 18 of these 21 (85.7%), displayed PLP on dermatoscopy. From a database of 2873 consecutively imaged and biopsied lesions, 252 flat-pigmented facial lesions were included. PLP was seen in 47/76 melanomas (61.8%), compared with 7/176 lesions (3.9%) with other diagnosis (P < .001). The sensitivity was 61.8% (95% CI, 49.9%-72.7%), specificity 96.0% (95% CI, 92.9%-98.4%). PLP was independently associated with LM diagnosis on multivariate analysis (OR 26.1 [95% CI, 9.6%-71.0]). LIMITATIONS: Retrospective study. CONCLUSION: PLP is a newly described dermatoscopic criterion that may add specificity and sensitivity to the early diagnosis of LM located on the face. We postulate that PLP constitutes an intermediary step in the LM progression model.

A Physician's Guide to the Use of Gene Expression Profile Ancillary Diagnostic Testing for Cutaneous Melanocytic Neoplasms.

Objectives: Some melanocytic neoplasms suspicious for melanoma require additional workup to arrive at a final diagnosis. Within the last eight years, gene expression profiling (GEP) has become an important ancillary tool to aid in the diagnosis of melanocytic neoplasms with uncertain malignant potential. As the usage of two commercially available tests (23-GEP and 35-GEP) evolves, it is important to answer key questions about optimal utilization and their impact on patient care. Methods: Recent and relevant articles answering the following questions were included in the review. First, how do dermatopathologists synthesize the available literature, the latest guidelines, and their clinical experience to determine which cases would be most likely to benefit from GEP testing? Second, how best can a dermatologist convey to their dermatopathologist that the use of GEP in the diagnostic process could provide a more clearly defined result and thereby help empower the dermatologist to provide higher-quality patient care when making specific patient management decisions for otherwise pathologically ambiguous lesions? Results: When interpreted in the context of the clinical, pathologic, and laboratory information, GEP results can facilitate the rendering of timely, accurate, and definitive diagnoses for melanocytic lesions with otherwise uncertain malignant potential to inform personalized treatment and management plans. Limitations: This was a narrative review focused on clinical use of GEP compared to other ancillary diagnostic tests performed postbiopsy. Conclusion: Open communication between dermatopathologists and dermatologists, especially regarding GEP testing, can be a vital component to achieve appropriate clinicopathologic correlation for otherwise ambiguous melanocytic lesions.

Dermoscopy of Linear Basal Cell Carcinomas, a Potential Mimicker of Linear Lesions: a Descriptive Case-series.

Introduction: Among the various widely recognized basal cell carcinoma (BCC) clinical patterns, linear basal cell carcinoma (LBCC) is an uncommon morphologic variant of BCC. Objectives: Describe the clinical and dermoscopic characteristics of LBCC. Methods: Retrospective study including LBCC cases from 5 dermatology centers in North and South America. Biopsy-proven primary BCCs, that presented with at least 3:1 length:width ratio on physical examination, irrespective of tumor subtype or location, were included. Clinical and dermoscopic analysis were performed by 2 experts in dermoscopy. Results: Eighteen cases of LBCC met our inclusion criteria and were included in the study. Median age at diagnosis was 86.0 years, 10 patients (58.8%) were males. Regarding anatomic location, 11/18 (61.1%) were located on the head and neck, 5/18 (27.7%) cases were found on the trunk, and 2 on lower extremities (11.1%). Under dermoscopy, 15/18 (83.3%) of LBCC were pigmented. All tumors displayed at least one of the BCC-specific dermoscopic criteria the most common being blue-grey globules (72.2%). Conclusions: Dermoscopy might be useful in the differentiation of LBCC from other diagnoses presenting as linear lesions such as scars, scratches/erosions, and tattoos, among others. Some of these lesions might be confused by naked eye examination alone.

Deep Learning and Handcrafted Method Fusion: Higher Diagnostic Accuracy for Melanoma Dermoscopy Images.

This paper presents an approach that combines conventional image processing with deep learning by fusing the features from the individual techniques. We hypothesize that the two techniques, with different error profiles, are synergistic. The conventional image processing arm uses three handcrafted biologically inspired image processing modules and one clinical information module. The image processing modules detect lesion features comparable to clinical dermoscopy information-atypical pigment network, color distribution, and blood vessels. The clinical module includes information submitted to the pathologist-patient age, gender, lesion location, size, and patient history. The deep learning arm utilizes knowledge transfer via a ResNet-50 network that is repurposed to predict the probability of melanoma classification. The classification scores of each individual module from both processing arms are then ensembled utilizing logistic regression to predict an overall melanoma probability. Using cross-validated results of melanoma classification measured by area under the receiver operator characteristic curve (AUC), classification accuracy of 0.94 was obtained for the fusion technique. In comparison, the ResNet-50 deep learning based classifier alone yields an AUC of 0.87 and conventional image processing based classifier yields an AUC of 0.90. Further study of fusion of conventional image processing techniques and deep learning is warranted.

Expert-Level Diagnosis of Nonpigmented Skin Cancer by Combined Convolutional Neural Networks.

Importance: Convolutional neural networks (CNNs) achieve expert-level accuracy in the diagnosis of pigmented melanocytic lesions. However, the most common types of skin cancer are nonpigmented and nonmelanocytic, and are more difficult to diagnose. Objective: To compare the accuracy of a CNN-based classifier with that of physicians with different levels of experience. Design, Setting, and Participants: A CNN-based classification model was trained on 7895 dermoscopic and 5829 close-up images of lesions excised at a primary skin cancer clinic between January 1, 2008, and July 13, 2017, for a combined evaluation of both imaging methods. The combined CNN (cCNN) was tested on a set of 2072 unknown cases and compared with results from 95 human raters who were medical personnel, including 62 board-certified dermatologists, with different experience in dermoscopy. Main Outcomes and Measures: The proportions of correct specific diagnoses and the accuracy to differentiate between benign and malignant lesions measured as an area under the receiver operating characteristic curve served as main outcome measures. Results: Among 95 human raters (51.6% female; mean age, 43.4 years; 95% CI, 41.0-45.7 years), the participants were divided into 3 groups (according to years of experience with dermoscopy): beginner raters (<3 years), intermediate raters (3-10 years), or expert raters (>10 years). The area under the receiver operating characteristic curve of the trained cCNN was higher than human ratings (0.742; 95% CI, 0.729-0.755 vs 0.695; 95% CI, 0.676-0.713; P < .001). The specificity was fixed at the mean level of human raters (51.3%), and therefore the sensitivity of the cCNN (80.5%; 95% CI, 79.0%-82.1%) was higher than that of human raters (77.6%; 95% CI, 74.7%-80.5%). The cCNN achieved a higher percentage of correct specific diagnoses compared with human raters (37.6%; 95% CI, 36.6%-38.4% vs 33.5%; 95% CI, 31.5%-35.6%; P = .001) but not compared with experts (37.3%; 95% CI, 35.7%-38.8% vs 40.0%; 95% CI, 37.0%-43.0%; P = .18). Conclusions and Relevance: Neural networks are able to classify dermoscopic and close-up images of nonpigmented lesions as accurately as human experts in an experimental setting.

Lichen planus-like keratosis: clinical applicability of in vivo reflectance confocal microscopy for an indeterminate cutaneous lesion.

Lichen planus-like keratosis (LPLK) is an involuting cutaneous lesion often presenting between the fifth and seventh decades of life. These lesions typically appear abruptly as a solitary macule, papule, or plaque that continuously evolves as it undergoes regression. Clinical and dermoscopic features of LPLK can mimic both benign and malignant lesions, often prompting biopsy for accurate diagnosis. We describe a case of LPLK developing in a patient with a history of multiple skin cancers, including melanoma. Dermoscopy revealed peripheral granules and a central area with pinkish-brown pigmentation and a disorganized pattern with shiny white structures and rosettes. Handheld reflectance confocal microscopy (RCM) showed a typical honeycomb pattern with millia-like cysts and comedo-like openings, and lacked pagetoid and dendritic cells. Based on the benign features seen with RCM, the lesion was followed until complete regression was observed. In conclusion, we describe a case of LPLK with clinically and dermoscopically indeterminate features that was successfully monitored with RCM. We intend to highlight the utility of RCM as a diagnostic aid in equivocal lesions in order to prevent unnecessary excisional procedures.

Confocal Microscopy in Skin Cancer.

PURPOSE OF REVIEW: Reflectance confocal microscopy (RCM) enables imaging of skin lesions at cellular level resolution at the bedside (in vivo) or in freshly excised tissue (ex vivo). This article provides an overview of strengths and limitations of non-invasive RCM in skin cancer diagnosis. RECENT FINDINGS: RCM features of common melanocytic and non-melanocytic skin neoplasms such as melanoma, actinic keratosis/squamous cell carcinoma, basal cell carcinoma, and nevi have been well defined and show good correlation with dermoscopic and histopathologic findings. Due to its technical properties, RCM is especially suitable for the examination of flat skin lesions. SUMMARY: In vivo RCM has been shown to increase the accuracy of non-invasive diagnosis of common skin neoplasms and is a valuable adjunct to dermoscopy, particularly in cosmetically and functionally sensitive areas such as the face or the genital area.

Reflectance Confocal Microscopy Criteria of Pigmented Squamous Cell Carcinoma In Situ.

Pigmented squamous cell carcinoma in situ (pSCCis) is difficult to diagnose based on clinical and dermoscopic examination. Reflectance confocal microscopy (RCM) allows noninvasive differentiation between malignant and benign pigmented skin lesions. We determined the frequency of key RCM features of pSCCis and correlated the RCM criteria with the corresponding dermoscopic and histopathologic criteria. The study included 28 lesions with biopsy-proven diagnosis of pSCCis derived from 28 patients. Clinical, dermoscopic, and RCM images of these lesions were retrospectively analyzed by 3 independent observers. Assessment for the presence of RCM criteria revealed scale or parakeratosis (20/28; 71%); irregular honeycomb pattern in the spinous-granular layer (28/28; 100%); spindle-shaped cells with dendritic branches infiltrating the epidermis (12/28; 43%); edged papillae (24/28; 86%), and dilated looped blood vessels within the papillae (18/28; 64%). Fifty-three percent of the cases displayed at least 4 RCM criteria and 96% of cases displayed at least 3 RCM criteria. We propose that the diagnosis of pSCCis could be established based on 1 major criterion-irregular honeycomb pattern-and 2 of the following minor criteria-scale or parakeratosis, spindle-shaped cells with dendritic branches infiltrating the epidermis, edged papillae, and dilated looped blood vessels within the papillae.

Reflectance confocal microscopy of an inverted follicular keratosis mimicking a squamous cell carcinoma.

Distinguishing between benign and malignant neoplasms of the skin is a daily challenge to dermatologists. With the use of a dermatoscope and other imaging devices, the diagnosis is often more precise. The confocal microscope is a device that uses a near-infrared laser to perform noninvasive imaging of the skin. The benefit is that the images immediately provide additional, cellular-level information that can assist in diagnosis. However, lesions may share overlapping characteristics on confocal microscopy, and hence, benign lesions can still display confocal features concerning for a cancerous process, justifying a biopsy. Here, we present a case of an inverted follicular keratosis imitating a squamous cell carcinoma on confocal microscopy.

Collision skin lesions-results of a multicenter study of the International Dermoscopy Society (IDS).

BACKGROUND: Collision lesions as two independent and unrelated skin tumors often manifest an atypical morphology. OBJECTIVE: To determine the combinations of collision skin lesions (CSLs). METHODS: Twenty-one pigmented lesion clinics in nine countries included 77 histopathologically proven CSLs in this retrospective observational study. RESULTS: Seventy-seven CSLs from 75 patients (median age 59.8 years) were analyzed; 24.7% of CSLs were located on the head and neck area, 5.2% on the upper extremities, 48.1% on the trunk, and 11.7% on the lower extremities; 40.3% revealed a melanocytic component (median age 54.7 years), followed by 45.5% with a basal cell carcinoma (BCC) (median age 62.4 years) and 11.7% with a seborrheic keratosis (median age 64.7 years). CSLs with a BCC component were more often found on the head and neck area compared to tumors with a melanocytic component (34.3% versus 16.1%). Lesions with a melanocytic component were more often detected on the trunk compared to lesions with a BCC (64.5% versus 37.1%). Patients with CSLs with epidermal-epidermal cell combination were older than patients with epidermal-dermal cell combination (63 versus 55.2 years), were more often male than female (63% versus 43.3%), more often had the lesion on the head and neck area (32.6% versus 13.3%), and less often on the upper (2.2 % versus 10%) or lower extremities (8.7% versus 16.6%). CONCLUSIONS: CSLs consist of a heterogeneous group of lesions of varying cell types. They are associated with advancing age and cumulative UV-exposure. CSLs manifest a complex morphology making it challenging to diagnose correctly.

Accuracy of dermatoscopy for the diagnosis of nonpigmented cancers of the skin.

BACKGROUND: Nonpigmented skin cancer is common, and diagnosis with the unaided eye is error prone. OBJECTIVE: To investigate whether dermatoscopy improves the diagnostic accuracy for nonpigmented (amelanotic) cutaneous neoplasms. METHODS: We collected a sample of 2072 benign and malignant neoplastic lesions and inflammatory conditions and presented close-up images taken with and without dermatoscopy to 95 examiners with different levels of experience. RESULTS: The area under the curve was significantly higher with than without dermatoscopy (0.68 vs 0.64, P < .001). Among 51 possible diagnoses, the correct diagnosis was selected in 33.1% of cases with and 26.4% of cases without dermatoscopy (P < .001). For experts, the frequencies of correct specific diagnoses of a malignant lesion improved from 40.2% without to 51.3% with dermatoscopy. For all malignant neoplasms combined, the frequencies of appropriate management strategies increased from 78.1% without to 82.5% with dermatoscopy. LIMITATIONS: The study deviated from a real-life clinical setting and was potentially affected by verification and selection bias. CONCLUSIONS: Dermatoscopy improves the diagnosis and management of nonpigmented skin cancer and should be used as an adjunct to examination with the unaided eye.

Dermoscopic and confocal features of an axillary "special site" nevus.

"Nevi of special sites" is a term that denotes melanocytic nevi presenting in specific anatomic locations including the scalp, genital area, flexural sites, and acral sites [1]. Nevi from these anatomic sites display at times histopathologic features that may lead the reading pathologist to recommend re-excision of these benign nevi. Reflectance confocal microscopy (RCM) is a noninvasive imaging tool that allows for visualization of epidermal, dermal-epidermal junctional (DEJ), and superficial dermal tissue structures at cellular level resolution. RCM features of special site nevi have not been previously described in the literature. Defining the RCM characteristics of special site nevi may increase diagnostic accuracy and assist in ruling out melanoma. Here, we report a case of a pigmented lesion appearing in the axilla of a patient with a recently diagnosed melanoma. Dermoscopic and histopathologic results were consistent with the diagnosis of nevus in flexural anatomic sites. In this case, RCM showed a regular honeycomb pattern of epidermal keratinocytes and enlarged, non-homogenous, discohesive nests at the DEJ, a pattern that corresponded well with the histopathologic findings. Larger studies are needed to establish RCM features of special site nevi in order to reliably rule out melanoma and lower the rate of unnecessary excisions of these benign nevi.

In vivo reflectance confocal microscopy features of a melanoacanthoma.

Efforts have been expended to evaluate the reflectance confocal microscopy (RCM) features of different clinical entities in order to more thoroughly delineate benign versus malignant features. In this way, RCM can help clinicians to be more selective in regard to undertaking appropriate skin biopsies and improving their benign to malignant ratio. Herein, we report a case of a histopathologically proven melanoacanthoma, a variant of seborrheic keratosis. There are scarce reports describing the RCM features of melanoacanthoma. Our case demonstrated RCM features that were suspicious for melanoma. More RCM images of this benign entity are needed to establish definitive diagnostic criteria.

Application of Handheld Confocal Microscopy for Skin Cancer Diagnosis: Advantages and Limitations Compared with the Wide-Probe Confocal.

The clinical diagnosis of tumors on the curved surfaces of the face, around the eyes, and on the mucosal surfaces can be difficult, while biopsies and excisions can have functional and aesthetic consequences. To avoid unnecessary surgery, clinicians have been aiming to attain accurate noninvasive diagnosis of lesions at these sites. However, acquisition of high-quality images with dermoscopy and with traditional wide-probe reflectance confocal microscopy (WP-RCM) have been hampered with technical difficulties. This article discusses the technical parameters of the handheld reflectance confocal microscope and discusses its advantages and limitations compared with the WP-RCM.

In vivo reflectance confocal microscopy features of a large cell acanthoma: report of a case.

Reflectance confocal microscopy (RCM) is an FDA approved noninvasive optical imaging technique that acquires cellular level-resolution skin images in vivo. Herein, we report a case of histopathologically proven large cell acanthoma (LCA) whose RCM features simulate those of squamous cell carcinoma in situ.