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

Guidelines for the diagnosis and treatment of cutaneous squamous cell carcinoma: a GRADE approach for evidence evaluation and recommendations by the Italian Association of Medical Oncology

Cutaneous squamous cell carcinoma (CSCC) accounts for ∼20%-25% of all skin tumors. Its precise incidence is often challenging to determine due to limited statistics and its incorporation with mucosal forms. While most cases have a favorable prognosis, challenges arise in patients presenting with locally advanced or metastatic forms, mainly appearing in immunocompromised patients, solid organ transplantation recipients, or those facing social difficulties. Traditionally, chemotherapy and targeted therapy were the mainstays for advanced cases, but recent approvals of immunotherapeutic agents like cemiplimab and pembrolizumab have revolutionized treatment options. These guidelines, developed by the Italian Association of Medical Oncologists (AIOM) using the Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) approach, aim to guide clinicians in diagnosing, treating, and monitoring patients with CSCC, covering key aspects from primitive tumors to advanced stages, selected by a panel of experts selected by AIOM and other national scientific societies. The incorporation of these guidelines into clinical practice is expected to enhance patient care and address the evolving landscape of CSCC management.

Review of the application of the most current sophisticated image processing methods for the skin cancer diagnostics purposes

This paper presents the most current and innovative solutions applying modern digital image processing methods for the purpose of skin cancer diagnostics. Skin cancer is one of the most common types of cancers. It is said that in the USA only, one in five people will develop skin cancer and this trend is constantly increasing. Implementation of new, non-invasive methods plays a crucial role in both identification and prevention of skin cancer occurrence. Early diagnosis and treatment are needed in order to decrease the number of deaths due to this disease. This paper also contains some information regarding the most common skin cancer types, mortality and epidemiological data for Poland, Europe, Canada and the USA. It also covers the most efficient and modern image recognition methods based on the artificial intelligence applied currently for diagnostics purposes. In this work, both professional, sophisticated as well as inexpensive solutions were presented. This paper is a review paper and covers the period of 2017 and 2022 when it comes to solutions and statistics. The authors decided to focus on the latest data, mostly due to the rapid technology development and increased number of new methods, which positively affects diagnosis and prognosis.

Clinicopathological, dermoscopic features and circumstances of diagnosis of amelanotic or hypomelanotic melanoma: A prospective multicentric study in the French private medical sector

BACKGROUND

Amelanotic or hypomelanotic melanomas (AHM) are difficult to diagnose, and are often diagnosed late, with a high Breslow index and a poor prognosis.

PATIENTS AND METHODS

A total of 226 volunteer dermatologists consulting in private practice in France completed an online form for each new histologically proven case of melanoma diagnosed at their clinic in 2020. This anonymised survey collected data on the clinical, dermoscopic, and histological features of melanoma, as well as the circumstances of diagnosis and initial management. A group of 145 AHM was single out and compared to the 1503 pigmented melanomas (PM) from the same cohort.

RESULTS

1503 pigmented melanomas (PM) and 145 AHM (8.8% of these melanomas) were identified and included. In the AHM group, the mean age at diagnosis was 65 ± 16 years, with no significant difference from the PM control group. AHM were not predominantly on the face and neck area, and there were no differences based on gender. Warning signs (local progression and bleeding) were significantly more frequent in the AHM group than in the PM group. AHM were more frequently ulcerated and nodular, with a higher median Breslow thickness than in the PM group (1.56 vs. 0.5 mm), and mitoses were more frequent. Dermoscopy was widely used and proved useful for distinguishing benign lesions, and for highlighting the vascular polymorphous pattern of malignant lesions. Patients noticed the suspicious lesion themselves in most cases of AHM (73.2%), as opposed to their general practitioner (17.2%) or entourage (9.5%). A total body skin examination enabled detection of 19.3% of AHM and 21.3% of PM where the patient consulted for another lesion, or for an unrelated reason.

CONCLUSION

AHM are difficult to diagnose for the clinician because of the paucity or absence of pigmentary criteria. Knowledge of dermoscopic vascular patterns is critical and could help reduce the median Breslow index of AHM at the time of detection. Self-examination of the skin should be encouraged, and simple algorithms for earlier detection of skin cancers should be promoted among health professionals and the general population.

Digitally Enhanced Methods for the Diagnosis and Monitoring of Treatment Responses in Actinic Keratoses: A New Avenue in Personalized Skin Care

Non-melanocytic skin cancers represent an important public health problem due to the increasing incidence and the important local destructive potential. Thus, the early diagnosis and treatment of precancerous lesions (actinic keratoses) is a priority for the dermatologist. In recent years, non-invasive skin imaging methods have seen an important development, moving from simple observational methods used in clinical research, to true diagnostic and treatment methods that make the dermatologist's life easier. Given the frequency of these precancerous lesions, their location on photo-exposed areas, as well as the long treatment periods, with variable, imprecise end-points, the need to use non-invasive imaging devices is increasingly evident to complete the clinical observations in the diagnosis and treatment of these lesions, with the aim of increasing accuracy and decreasing the adverse effects due to long treatment duration. This is the first review that brings together all skin imaging methods (dermoscopy, reflectance confocal microscopy, ultrasonography, dermoscopy-guided high frequency ultrasonography, and optical coherence tomography) used in the evaluation of actinic keratoses and their response to different treatment regimens.

Dermoscopic Features of Cutaneous Vasculitis

INTRODUCTION

Dermoscopy has become widespread in the diagnosis of inflammatory skin diseases. Cutaneous vasculitis (CV) is characterized by inflammation of vessels, and a rapid and reliable technique is required for the diagnosis.

OBJECTIVES

We aimed to define CV dermoscopic features and increase the diagnostic accuracy of dermoscopy with machine learning (ML) methods.

METHODS

Eighty-nine patients with clinically suspected CV were included in the study. Dermoscopic images were obtained before biopsy using a polarized dermoscopy. Dermoscopic images were independently evaluated, and interobserver variability was calculated. Decision Tree, Random Forest, and K-Nearest Neighbors were used as ML classification models.

RESULTS

The histopathological diagnosis of 58 patients was CV. Three patterns were observed: homogeneous pattern, mottled pattern, and meshy pattern. There was a significant difference in background color between the CV and non-CV groups (P = 0.001). The milky red and livedoid background color were specific markers in the differential diagnosis of CV (sensitivity 56.7%, specificity 96.3%, sensitivity 29.4%, specificity 99.2%, respectively). Red blotches were significantly more common in CV lesions (P = 0.038). Red dots, comma vessels, and scales were more common in the non-CV group (P = 0.002, P = 0.002, P = 0.003, respectively). Interobserver agreement was very good for both pattern (κ = 0.869) and background color analysis (κ = 0.846) (P < 0.001). According to ML classifiers, the background color and lack of scales were the most significant dermoscopic aspects of CV.

CONCLUSIONS

Dermoscopy may guide as a rapid and reliable technique in CV diagnosis. High accuracy rates obtained with ML methods may increase the success of dermoscopy.

Protocol for a systematic review of reviews on training primary care providers in dermoscopy to detect skin cancers

INTRODUCTION

Globally, incidence, prevalence and mortality rates of skin cancers are escalating. Earlier detection by well-trained primary care providers in techniques such as dermoscopy could reduce unnecessary referrals and improve longer term outcomes. A review of reviews is planned to compare and contrast the conduct, quality, findings and conclusions of multiple systematic and scoping reviews addressing the effectiveness of training primary care providers in dermoscopy, which will provide a critique and synthesis of the current body of review evidence.

METHODS AND ANALYSIS

Four databases (Cochrane, CINAHL, EMBASE and MEDLINE Complete) will be comprehensively searched from database inception to identify published, peer-reviewed English-language articles describing scoping and systematic reviews of the effectiveness of training primary care providers in the use of dermoscopy to detect skin cancers. Two researchers will independently conduct the searches and screen the results for potentially eligible studies using 'Research Screener' (a semi-automated machine learning tool). Backwards and forwards citation tracing will be conducted to supplement the search. A narrative summary of included reviews will be conducted. Study characteristics, for example, population; type of educational programme, including content, delivery method, duration and assessment; and outcomes for dermoscopy will be extracted into a standardised table. Data extraction will be checked by the second reviewer. Methodological quality will be evaluated by two reviewers independently using the Critical Appraisal Tool for Health Promotion and Prevention Reviews. Results of the assessments will be considered by the two reviewers and any discrepancies will be resolved by team consensus.

ETHICS AND DISSEMINATION

Ethics approval is not required to conduct the planned systematic review of peer-reviewed, published articles because the research does not involve human participants. Findings will be published in a peer-reviewed journal, presented at leading public health, cancer and primary care conferences, and disseminated via website postings and social media channels.

PROSPERO REGISTRATION NUMBER

CRD42023396276.

Implementation of a dermatoscopy curriculum during residency at Augsburg University Hospital in Germany

BACKGROUND AND OBJECTIVES

To date, there is no structured program for dermatoscopy training during residency in Germany. Whether and how much dermatoscopy training is acquired is left to the initiative of each resident, although dermatoscopy is one of the core competencies of dermatological training and daily practice. The aim of the study was to establish a structured dermatoscopy curriculum during residency at the University Hospital Augsburg.

PATIENTS AND METHODS

An online platform with dermatoscopy modules was created, accessible regardless of time and place. Practical skills were acquired under the personal guidance of a dermatoscopy expert. Participants were tested on their level of knowledge before and after completing the modules. Test scores on management decisions and correct dermatoscopic diagnosis were analyzed.

RESULTS

Results of 28 participants showed improvements in management decisions from pre- to posttest (74.0% vs. 89.4%) and in dermatoscopic accuracy (65.0% vs. 85.6%). Pre- vs. posttest differences in test score (7.05/10 vs. 8.94/10 points) and correct diagnosis were significant (p < 0.001).

CONCLUSIONS

The dermatoscopy curriculum increases the number of correct management decisions and dermatoscopy diagnoses. This will result in more skin cancers being detected, and fewer benign lesions being excised. The curriculum can be offered to other dermatology training centers and medical professionals.

Implementierung eines Dermatoskopie-Curriculums in der Facharztausbildung am Universitätsklinikum Augsburg

Hintergrund und Ziele

Bislang gibt es in Deutschland kein strukturiertes Programm für die Dermatoskopieausbildung während der Facharztausbildung. Es bleibt der Initiative des einzelnen Assistenzarztes überlassen, ob und in welchem Umfang er sich in der Dermatoskopie weiterbildet, obwohl die Dermatoskopie zu den Kernkompetenzen der dermatologischen Ausbildung und der täglichen Praxis gehört. Ziel der Studie war die Etablierung eines strukturierten Dermatoskopie‐Curriculums während der dermatologischen Facharztausbildung am Universitätsklinikum Augsburg.

Patienten und Methodik

Es wurde eine Online‐Plattform mit Dermatoskopie‐Modulen geschaffen, auf die von überall und jederzeit zugegriffen werden kann. Praktische Fertigkeiten wurden unter individueller Anleitung eines Dermatoskopie‐Experten erworben. Die Teilnehmer wurden vor und nach Abschluss der Module auf ihren Wissensstand getestet. Die Testergebnisse zum therapeutischen Management und zur korrekten dermatoskopischen Diagnose wurden analysiert.

Ergebnisse

Die Ergebnisse der 28 Teilnehmer verbesserten sich vom Eingangs‐ zum Abschlusstest bei der Managemententscheidung (74,0% vs. 89,4%) und bei der dermatoskopischen Genauigkeit (65,0% vs. 85,6%). Die Unterschiede zwischen Eingangs‐ und Abschlusstest bei der Gesamtpunktzahl (7,05/10 vs. 8,94/10 Punkte) und bei der richtigen Diagnose waren signifikant (p < 0,001).

Schlussfolgerungen

Das Dermatoskopie‐Curriculum verbessert die Managemententscheidungen und die dermatoskopische Diagnostik der Teilnehmer. Das wird dazu führen, dass mehr Hautkrebsfälle erkannt werden und weniger gutartige Läsionen reseziert werden müssen. Das Curriculum kann anderen dermatologischen Ausbildungszentren und Gesundheitsberufen angeboten werden.

Sensitivity investigation of open-ended coaxial probe in skin cancer detection

Open-ended coaxial probe method is one of the most common modalities in measuring dielectric properties (DPs) of biological tissues. Due to the significant differences between the tumors and normal tissues in DPs, the technique can be used to detect skin cancer in the early stage. Although various studies have been reported, systematic assessment is in urgent need to advance it to clinical applications, for its parameters interactions and detecting limitations remained unclear. In this study, we aim to provide a comprehensive examination of this method, including the minimum detectable tumor size by using a three-layer skin model via simulation and demonstrated that open-ended coaxial probe method can be used for detection of early-stage skin cancer. The smallest detecting size are subject to different subtypes: for BCC, inside the skin is 0.5 mm radius × 0.1 mm height; for SCC, inside the skin is 1.4 mm × 1.3 mm in radius and height; the smallest distinguishing size of BCC is 0.6 mm × 0.7 mm in radius and height; for SCC is 1.0 mm × 1.0 mm in radius and height; for MM is 0.7 mm × 0.4 mm in radius and height. The experiment results showed that sensitivity was affected by tumor dimension, probe size, skin height, and cancer subtype. The probe is more sensitive to cylinder tumor radius than height growing on the surface of the skin while the smallest size probe is the most sensitive among the working probes. We provide a detailed systematic evaluation of the parameters employed in the method for further applications.

An Ensemble of Transfer Learning Models for the Prediction of Skin Cancers with Conditional Generative Adversarial Networks

Skin cancer is one of the most severe forms of the disease, and it can spread to other parts of the body if not detected early. Therefore, diagnosing and treating skin cancer patients at an early stage is crucial. Since a manual skin cancer diagnosis is both time-consuming and expensive, an incorrect diagnosis is made due to the high similarity between the various skin cancers. Improved categorization of multiclass skin cancers requires the development of automated diagnostic systems. Herein, we propose a fully automatic method for classifying several skin cancers by fine-tuning the deep learning models VGG16, ResNet50, and ResNet101. Prior to model creation, the training dataset should undergo data augmentation using traditional image transformation techniques and Generative Adversarial Networks (GANs) to prevent class imbalance issues that may lead to model overfitting. In this study, we investigate the feasibility of creating dermoscopic images that have a realistic appearance using Conditional Generative Adversarial Network (CGAN) techniques. Thereafter, the traditional augmentation methods are used to augment our existing training set to improve the performance of pre-trained deep models on the skin cancer classification task. This improved performance is then compared to the models developed using the unbalanced dataset. In addition, we formed an ensemble of finely tuned transfer learning models, which we trained on balanced and unbalanced datasets. These models were used to make predictions about the data. With appropriate data augmentation, the proposed models attained an accuracy of 92% for VGG16, 92% for ResNet50, and 92.25% for ResNet101, respectively. The ensemble of these models increased the accuracy to 93.5%. A comprehensive discussion on the performance of the models concluded that using this method possibly leads to enhanced performance in skin cancer categorization compared to the efforts made in the past.

Color-invariant skin lesion semantic segmentation based on modified U-Net deep convolutional neural network

Melanoma is a type of skin lesion that is less common than other types of skin lesions, but it is fast growing and spreading. Therefore, it is classified as a serious disease that directly threatens human health and life. Recently, the number of deaths due to this disease has increased significantly. Thus, researchers are interested in creating computer-aided diagnostic systems that aid in the proper diagnosis and detection of these lesions from dermoscopy images. Relying on manual diagnosis is time consuming in addition to requiring enough experience from dermatologists. Current skin lesion segmentation systems use deep convolutional neural networks to detect skin lesions from RGB dermoscopy images. However, relying on RGB color model is not always the optimal choice to train such networks because some fine details of lesion parts in the dermoscopy images can not clearly appear using RGB color model. Other color models exhibit invariant features of the dermoscopy images so that they can improve the performance of deep neural networks. In the proposed Color Invariant U-Net (CIU-Net) model, a color mixture block is added at the beginning of the contracting path of U-Net. The color mixture block acts as a mixer to learn the fusion of various input color models and create a new one with three channels. Furthermore, a new channel-attention module is included in the connection path between encoder and decoder paths. This channel attention module is developed to enrich the extracted color features. From the experimental result, we found that the proposed CIU-Net works in harmony with the new proposed hybrid loss function to enhance skin segmentation results. The performance of the proposed CIU-Net architecture is evaluated using ISIC 2018 dataset and the results are compared with other recent approaches. Our proposed method outperformed other recent approaches and achieved the best Dice and Jaccard coefficient with values 92.56% and 91.40%, respectively.

Dermoscopy practice guidelines for use in telemedicine

Teledermoscopy, or the utilization of dermatoscopic images in telemedicine, can help diagnose dermatologic disease remotely, triage lesions of concern (i.e., determine whether in-person consultation with a dermatologist is necessary, biopsy, or reassure the patient), and monitor dermatologic lesions over time. Handheld dermatoscopes, a magnifying apparatus, have become a commonly utilized tool for providers in many healthcare settings and professions and allows users to view microstructures of the epidermis and dermis. This Dermoscopy Practice Guideline reflects current knowledge in the field of telemedicine to demonstrate the correct capture, usage, and incorporation of dermoscopic images into everyday practice.

System for the Recognizing of Pigmented Skin Lesions with Fusion and Analysis of Heterogeneous Data Based on a Multimodal Neural Network

Simple Summary

Skin cancer is one of the most common cancers in humans. This study aims to create a system for recognizing pigmented skin lesions by analyzing heterogeneous data based on a multimodal neural network. Fusing patient statistics and multidimensional visual data allows for finding additional links between dermoscopic images and medical diagnostic results, significantly improving neural network classification accuracy. The use by specialists of the proposed system of neural network recognition of pigmented skin lesions will enhance the efficiency of diagnosis compared to visual diagnostic methods.

Abstract

Today, skin cancer is one of the most common malignant neoplasms in the human body. Diagnosis of pigmented lesions is challenging even for experienced dermatologists due to the wide range of morphological manifestations. Artificial intelligence technologies are capable of equaling and even surpassing the capabilities of a dermatologist in terms of efficiency. The main problem of implementing intellectual analysis systems is low accuracy. One of the possible ways to increase this indicator is using stages of preliminary processing of visual data and the use of heterogeneous data. The article proposes a multimodal neural network system for identifying pigmented skin lesions with a preliminary identification, and removing hair from dermatoscopic images. The novelty of the proposed system lies in the joint use of the stage of preliminary cleaning of hair structures and a multimodal neural network system for the analysis of heterogeneous data. The accuracy of pigmented skin lesions recognition in 10 diagnostically significant categories in the proposed system was 83.6%. The use of the proposed system by dermatologists as an auxiliary diagnostic method will minimize the impact of the human factor, assist in making medical decisions, and expand the possibilities of early detection of skin cancer.

Sub-macroscopic skin presentation of acromegaly and effect of pituitary tumor surgery: A study using dermatoscopy and ultra-high-frequency ultrasound

OBJECTIVE

Excessive growth hormone and insulin-like growth factor 1 contribute to cutaneous changes in acromegaly. We investigated the sub-macroscopic skin manifestation of acromegaly patients and explored its reversibility upon hormone reduction after pituitary adenoma surgery.

DESIGN

Prospectively cohort study.

METHODS

We enrolled 26 patients with acromegaly and 26 patients with non-functioning pituitary adenomas undergoing pituitary adenomectomy at Peking Union Medical College Hospital from July 2021 to March 2022. Skin presentations were evaluated by dermatoscopy and ultra-high-frequency ultrasound before and after surgery.

RESULTS

Skin thickening, follicular plugs, perifollicular pigmentations, perifollicular orange haloes, red structureless areas, increased hair shafts, honeycomb-like pigmentations, widened dermatoglyphics, dilated appendage openings, excessive seborrhea, hyperhidrosis, enlarged pores, and acne-like lesions were commonly occurring in acromegaly patients, and their incidences were higher than the controls (P<0.05). At 3-month follow-up after surgery, the thickness of skin reduced (4.0 ± 0.4 to 3.7 ± 0.4, P=0.007), the incidences of hyperhidrosis (92.3% to 69.2%, P=0.035) and acne-like lesions (53.8% to 26.9%, P=0.048) declined, and the severity of multiple cutaneous lesions improved. Patients with surgical endocrine remission (53.8%) had greater declines in the thickness of skin than those without remission. Patients with improvement of >1 skin lesions were younger (P=0.028) and had higher baseline GH levels (P=0.021) than those with improvement of ≤1 skin lesion.

CONCLUSIONS

Dermatoscopy and ultra-high-frequency ultrasound provided augmented visual examination of the cutaneous changes in acromegaly. Some of the skin lesions could improve or reverse after pituitary surgery. Baseline GH levels, age, and endocrine remission were correlated with skin improvement at 3-month follow-up.

Auswirkungen des „dunklen Rand‐Artefakts“ in dermatoskopischen Bildern auf die diagnostische Leistungsfähigkeit eines deep learning neuronalen Netzwerkes mit Marktzulassung

HINTERGRUND UND ZIELE

Systeme künstlicher Intelligenz (durch "deep learning" faltende neuronale Netzwerke; engl. convolutional neural networks, CNN) erreichen inzwischen bei der Klassifikation von Hautläsionen vergleichbar gute Ergebnisse wie Dermatologen. Allerdings müssen die Limitationen solcher Systeme vor flächendeckendem klinischem Einsatz bekannt sein. Daher haben wir den Einfluss des "dunklen Rand-Artefakts" (engl. dark corner artefact; DCA) in dermatoskopischen Bildern auf die diagnostische Leistung eines CNN mit Marktzulassung zur Klassifikation von Hautläsionen untersucht.

PATIENTEN UND METHODEN

Ein Datensatz aus 233 Bildern von Hautläsionen (60 maligne und 173 benigne) ohne DCA (Kontrolle) wurde digital so modifiziert, dass kleine, mittlere oder große DCA zu sehen waren. Alle 932 Bilder wurden dann mittels CNN mit Marktzulassung (Moleanalyzer-Pro^® , FotoFinder Systems) auf Malignitätsscores hin analysiert. Das Spektrum reichte von 0-1; ein Score von > 0,5 wurde als maligne klassifiziert.

ERGEBNISSE

In der Kontrollserie ohne DCA erreichte das CNN eine Sensitivität von 90,0 % (79,9 %-95,3 %), eine Spezifität von 96,5 % (92,6 %-98,4 %) sowie eine Fläche unter der Kurve (AUC, area under the curve) der "receiver operating characteristic" (ROC) von 0,961 (0,932-0,989). In den Datensätzen mit kleinen beziehungsweise mittleren DCA war die diagnostische Leistung vergleichbar. In den Bildersätzen mit großen DCA wurden allerdings signifikant höhere Malignitätsscores erzielt. Dies führte zu einer signifikant verminderten Spezifität (87,9 % [82,2 %-91,9 %], P < 0,001) sowie einer nicht signifikant erhöhten Sensitivität (96,7 % [88,6 %-99,1 %]). Die ROC-AUC blieb mit 0,962 (0,935-0,989) unverändert.

SCHLUSSFOLGERUNGEN

Die Klassifizierung mittels des CNN war bei dermatoskopischen Bildern mit kleinen oder mittleren DCA nicht beeinträchtigt, das System zeigte jedoch Schwächen bei großen DCA. Wenn Ärzte solche Bilder zur Klassifikation mittels CNN einreichen, sollten sie sich dieser Grenzen der Technologie bewusst sein.

Dark corner artefact and diagnostic performance of a market-approved neural network for skin cancer classification

BACKGROUND AND OBJECTIVES

Convolutional neural networks (CNN) have proven dermatologist-level performance in skin lesion classification. Prior to a broader clinical application, an assessment of limitations is crucial. Therefore, the influence of a dark tubular periphery in dermatoscopic images (also called dark corner artefact [DCA]) on the diagnostic performance of a market-approved CNN for skin lesion classification was investigated.

PATIENTS AND METHODS

A prospective image set of 233 skin lesions (60 malignant, 173 benign) without DCA (control-set) was modified to show small, medium or large DCA. All 932 images were analyzed by a market-approved CNN (Moleanalyzer-Pro^® , FotoFinder Systems), providing malignancy scores (range 0-1) with the cut-off > 0.5 indicating malignancy.

RESULTS

In the control-set the CNN achieved a sensitivity of 90.0 % (79.9 % - 95.3 %), a specificity of 96.5 % (92.6 % - 98.4 %), and an area under the curve (AUC) of receiver operating characteristics (ROC) of 0.961 (0.932 - 0.989). Comparable diagnostic performance was observed in the DCAsmall-set and DCAmedium-set. Conversely, in the DCAlarge-set significantly increased malignancy scores triggered a significantly decreased specificity (87.9 % [82.2 % - 91.9 %], P < 0.001), non-significantly increased sensitivity (96.7 % [88.6 % - 99.1 %]) and unchanged ROC-AUC of 0.962 (0.935 - 0.989).

CONCLUSIONS

Convolutional neural network classification was robust in images with small and medium DCA, but impaired in images with large DCA. Physicians should be aware of this limitation when submitting images to CNN classification.

Clinical Diagnosis has a High Negative Predictive Value in Evaluation of Malignant Skin Lesions

Background

The increasing incidence of skin cancers in fair-skinned population and its relatively good response to treatment make its accurate diagnosis of great importance. We evaluated the accuracy of clinical diagnosis of malignant skin lesions by comparing the clinical diagnosis with histological diagnosis as the gold standard.

Materials and Methods

In this retrospective study, we assessed all the pathology reports from specimens sent to a university hospital laboratory in 3 consecutive years from March 2008 to March 2010. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and positive and negative likelihood ratios were calculated for clinical diagnosis of malignant skin lesions stratified by their histological subtype.

Results

A total 4,123 specimen were evaluated. The sensitivity and specificity for clinical diagnosis of malignancy were 90.48% and 82.85%, respectively, whereas the negative predictive value was shown to be 99.06%. The positive and negative likelihood ratios were 5.23 and 0.11, respectively.

Conclusion

Pathological assessment of skin lesions remains the cornerstone of skin cancer diagnosis. The high NPV and the relatively low PPV indicate that clinical diagnosis is more efficient in ruling out malignancies rather than diagnosing them.

Association of Multiple Aggregated Yellow-White Globules With Nonpigmented Basal Cell Carcinoma

Importance

Basal cell carcinoma (BCC) is the most common skin cancer. Dermoscopic imaging has improved diagnostic accuracy; however, diagnosis of nonpigmented BCC remains limited to arborizing vessels, ulceration, and shiny white structures.

Objective

To assess multiple aggregated yellow-white (MAY) globules as a diagnostic feature for BCC.

Design, Setting, and Participants

In this retrospective, single-center, case-control study, nonpigmented skin tumors, determined clinically, were identified from a database of lesions consecutively biopsied during a 7-year period (January 1, 2009, to December 31, 2015). A subset of tumors was prospectively diagnosed, and reflectance confocal microscopy, optical coherence tomography, and histopathologic correlation were performed. Data analysis was conducted from July 1 to September 31, 2019.

Exposures

Investigators evaluated for the presence or absence of known dermoscopic criteria. MAY globules were defined as aggregated, white-yellow structures visualized in polarized and nonpolarized light.

Main Outcomes and Measures

The primary outcome was the diagnostic accuracy of MAY globules for the diagnosis of BCC. Secondary objectives included the association with BCC location and subtype. Interrater agreement was estimated.

Results

A total of 656 nonpigmented lesions from 643 patients (mean [SD] age, 63.1 [14.9] years; 381 [58.1%] male) were included. In all, 194 lesions (29.6%) were located on the head and neck. A total of 291 (44.4%) were BCCs. MAY globules were seen in 61 of 291 BCC cases (21.0%) and in 3 of 365 other diagnoses (0.8%) (P < .001). The odds ratio for diagnosis of BCC was 32.0 (96% CI, 9.9-103.2). The presence of MAY globules was associated with a diagnosis of histologic high-risk BCC (odds ratio, 6.5; 95% CI, 3.1-14.3). The structure was never seen in cases of superficial BCCs.

Conclusions and Relevance

The findings suggest that MAY globules may have utility as a new BCC dermoscopic criterion with a high specificity. MAY globules were negatively associated with superficial BCC and positively associated with deeper-seated, histologic, higher-grade tumor subtypes.

Artificial Intelligence and Its Effect on Dermatologists' Accuracy in Dermoscopic Melanoma Image Classification: Web-Based Survey Study

BACKGROUND

Early detection of melanoma can be lifesaving but this remains a challenge. Recent diagnostic studies have revealed the superiority of artificial intelligence (AI) in classifying dermoscopic images of melanoma and nevi, concluding that these algorithms should assist a dermatologist's diagnoses.

OBJECTIVE

The aim of this study was to investigate whether AI support improves the accuracy and overall diagnostic performance of dermatologists in the dichotomous image-based discrimination between melanoma and nevus.

METHODS

Twelve board-certified dermatologists were presented disjoint sets of 100 unique dermoscopic images of melanomas and nevi (total of 1200 unique images), and they had to classify the images based on personal experience alone (part I) and with the support of a trained convolutional neural network (CNN, part II). Additionally, dermatologists were asked to rate their confidence in their final decision for each image.

RESULTS

While the mean specificity of the dermatologists based on personal experience alone remained almost unchanged (70.6% vs 72.4%; P=.54) with AI support, the mean sensitivity and mean accuracy increased significantly (59.4% vs 74.6%; P=.003 and 65.0% vs 73.6%; P=.002, respectively) with AI support. Out of the 10% (10/94; 95% CI 8.4%-11.8%) of cases where dermatologists were correct and AI was incorrect, dermatologists on average changed to the incorrect answer for 39% (4/10; 95% CI 23.2%-55.6%) of cases. When dermatologists were incorrect and AI was correct (25/94, 27%; 95% CI 24.0%-30.1%), dermatologists changed their answers to the correct answer for 46% (11/25; 95% CI 33.1%-58.4%) of cases. Additionally, the dermatologists' average confidence in their decisions increased when the CNN confirmed their decision and decreased when the CNN disagreed, even when the dermatologists were correct. Reported values are based on the mean of all participants. Whenever absolute values are shown, the denominator and numerator are approximations as every dermatologist ended up rating a varying number of images due to a quality control step.

CONCLUSIONS

The findings of our study show that AI support can improve the overall accuracy of the dermatologists in the dichotomous image-based discrimination between melanoma and nevus. This supports the argument for AI-based tools to aid clinicians in skin lesion classification and provides a rationale for studies of such classifiers in real-life settings, wherein clinicians can integrate additional information such as patient age and medical history into their decisions.

Clinicopathological and dermoscopic features of amelanotic and hypomelanotic melanoma: a retrospective multicentric study

BACKGROUND

Amelanotic and hypomelanotic melanoma (AHM) has a higher risk of delayed diagnosis and a significant lower 5-year melanoma-specific survival compared to pigmented melanoma. Our aim was the evaluation of the clinicopathological/dermoscopic features of amelanotic melanoma (AM) and hypomelanotic melanoma (HM).

METHODS

All participants had a personal history of AHM. We defined HM as showing clinical/dermoscopic pigmentation in < 25% of the lesion's surface and histopathological focal pigmentation, while AM as melanomas with clinical/dermoscopic and histopathological absence of pigmentation.

RESULTS

The most common phenotypic traits among the 145 AHM patients were as follows: phototype II, blue-grey eyes, and dark brown hair. Red hair was present in 23.8% AHM cases (AM = 22.60%; HM = 25.80%). The most affected area was the back (29.5%). A total of 67.1% were classified as AM and 32.9% as HM. The most represented hair colors in AM and HM were, respectively, blonde and dark brown hair. Median Breslow thickness was 1.7 mm, superficial spreading melanoma (SSM) and nodular melanoma (NM) were the most represented histotypes, and mitotic rate > 1 × mm² was reported in 73.3% cases, and regression was significantly more present in HM. Dermoscopy showed high prevalence of white structureless zones (63.4%), linear looped vessels (58.8%), linear irregular vessels (50.0%), and arborizing vessels (47.2%). Multivariate logistic regression confirmed the association between the presence of pigmentation and the following: histological regression, dermoscopic globules, and arborizing vessels.

CONCLUSIONS

Predominance of red hair in AHM patients was not confirmed. AHM affects mostly intermittent sun-exposed body areas. The deeper median Breslow thickness (versus pigmented melanoma), the association of AM with the nodular histotype, and the high mitotic rate highlight the AHM's aggressiveness. HM's higher levels of regression can be explained by the presence of pigmentation, driving the underlying immune response. AHM showed a polymorphous vascular pattern and significant presence of arborizing vessels (especially HM).

Dark pigmented lesions: Diagnostic accuracy of dermoscopy and reflectance confocal microscopy in a tertiary referral center for skin cancer diagnosis

BACKGROUND

There is lack of studies on the diagnostic accuracy of dermoscopy and reflectance confocal microscopy (RCM) for dark pigmented lesions.

OBJECTIVE

To assess the diagnostic accuracy of dermoscopy plus confocal microscopy for melanoma diagnosis of dark pigmented lesions in real life.

METHODS

Prospective analysis of difficult dark lesions with clinical/dermoscopic suspicion of melanoma referred for RCM for further analysis. The outcome could be excision or dermoscopic digital follow-up.

RESULTS

We included 370 clinically dark lesions from 350 patients (median age, 45 y). Because of the clinical/dermoscopic/RCM approach, we saved 129 of 213 unnecessary biopsies (specificity of 60.6%), with a sensitivity of 98.1% (154/157). The number needed to excise with the addition of RCM was 1.5 for melanoma diagnosis.

LIMITATIONS

Single institution based; Italian population only.

CONCLUSIONS

This study showed that RCM coupled with dermoscopy increases the specificity for diagnosing melanoma, and it helps correctly identify benign lesions. Our findings provide the basis for subsequent prospective studies on melanocytic neoplasms belonging to patients in different countries.

Past and present of computer-assisted dermoscopic diagnosis: performance of a conventional image analyser versus a convolutional neural network in a prospective data set of 1,981 skin lesions

BACKGROUND

Convolutional neural networks (CNNs) have shown a dermatologist-level performance in the classification of skin lesions. We aimed to deliver a head-to-head comparison of a conventional image analyser (CIA), which depends on segmentation and weighting of handcrafted features, to a CNN trained by deep learning.

METHODS

Cross-sectional study using a real-world, prospectively acquired, dermoscopic dataset of 1981 skin lesions to compare the diagnostic performance of a market-approved CNN (Moleanalyzer-Pro™, developed in 2018) to a CIA (Moleanalyzer-3™/Dynamole™; developed in 2004, all FotoFinder Systems Inc, Germany). As a reference standard, we used histopathological diagnoses (n = 785) or, in non-excised benign lesions (n = 1196), expert consensus plus an uneventful follow-up by sequential digital dermoscopy for at least 2 years.

RESULTS

A total of 281 malignant lesions and 1700 benign lesions from 435 patients (62.2% male, mean age: 52 years) were prospectively imaged. The CNN showed a sensitivity of 77.6% (95% confidence interval [CI]: [72.4%-82.1%]), specificity of 95.3% (95% CI: [94.2%-96.2%]), and receiver operating characteristic (ROC)-area under the curve (AUC) of 0.945 (95% CI: [0.930-0.961]). In contrast, the CIA achieved a sensitivity of 53.4% (95% CI: [47.5%-59.1%]), specificity of 86.6% (95% CI: [84.9%-88.1%]) and ROC-AUC of 0.738 (95% CI: [0.701-0.774]). The data set included melanomas originally diagnosed by dynamic changes during sequential digital dermoscopy (52 of 201, 20.6%), which reduced the sensitivities of both classifiers. Pairwise comparisons of sensitivities, specificities, and ROC-AUCs indicated a clear outperformance by the CNN (all p < 0.001).

CONCLUSIONS

The superior diagnostic performance of the CNN argues against a continued application of former CIAs as an aide to physicians' clinical management decisions.

Classification of Lentigo Maligna at Patient-Level by Means of Reflectance Confocal Microscopy Data

Reflectance confocal microscopy is an appropriate tool for the diagnosis of lentigo maligna. Compared with dermoscopy, this device can provide abundant information as a mosaic and/or a stack of images. In this particular context, the number of images per patient varied between 2 and 833 images and the objective, ultimately, is to be able to discern between benign and malignant classes. First, this paper evaluated classification at the image level, with the help of handcrafted methods derived from the literature and transfer learning methods. The transfer learning feature extraction methods outperformed the handcrafted feature extraction methods from literature, with a F 1 score value of 0.82. Secondly, this work proposed patient-level supervised methods based on image decisions and a comparison of these with multi-instance learning methods. This study achieved comparable results to those of the dermatologists, with an auc score of 0.87 for supervised patient diagnosis and an auc score of 0.88 for multi-instance learning patient diagnosis. According to these results, computer-aided diagnosis methods presented in this paper could be easily used in a clinical context to save time or confirm a diagnosis and can be oriented to detect images of interest. Also, this methodology can be used to serve future works based on multimodality.

Diagnosis and treatment of low-risk superficial basal cell carcinoma in a single visit

Introduction: Surgical excision remains the most commonly utilized treatment for superficial basal cell carcinoma (sBCC). In the era of cost containment of healthcare, the rising incidence of BCC and the high cost of excision require a continuous search for efficient and cost-effective management.Objective: Examine the feasibility of the diagnosis and treatment of low-risk sBCC in a single visit.Materials and methods: Retrospective chart review of sBCCs diagnosed and treated in a single visit.Results: The study identified 151 histologically confirmed sBCCs in 86 patients over a 5-year period, 93 (61.6%) cases of which were diagnosed as low-risk sBCC and treated in a single appointment. The majority of the cases (n = 86) were treated with curettage alone and the rest (n = 7) with a shave removal technique. The average size of the lesion was 0.82 cm located primarily on the trunk and extremities (95.7%). One recurrence on the trunk was observed in the single appointment group. Overall, diagnostic sensitivity was 95.4% and specificity was 92.0%.Conclusions: Diagnosis and treatment of sBCC in a single visit is an efficient and cost-effective management option for those who are proficient in identifying low-risk sBCC.

The Role of Teledermatology and Teledermoscopy in the Diagnosis of Actinic Keratosis and Field Cancerization

Actinic keratosis (AK) and field cancerization are increasing health problems insufficiently diagnosed by primary care physicians. The objective of this study was to assess the validity and reliability of teledermatology (TD) and teledermoscopy in the diagnosis of AK and field cancerization in a gatekeeper healthcare model. A prospective diagnostic test evaluation was done to assess the diagnostic concordance, accuracy, and performance parameters and the interobserver and intraobserver concordances of TD and teledermoscopy compared with dermatologists' face-to-face evaluation or histopathology. A total of 636 patients with 1,000 keratotic skin lesions were included. TD diagnostic concordance for AK and field cancerization evaluation was very high and superior to primary care physicians' diagnosis (92.4% vs. 62.4% and 96.7% vs. 51.8%, P < 0.001). TD sensitivity, specificity, and positive and negative predictive values for AK diagnosis and field cancerization were high (range = 82.2-95.0) and better than primary care physicians' diagnosis. Teledermoscopy yielded better results in diagnostic concordance, performance parameters, and AK subtypes. Intraobserver and interobserver agreement was >0.83. TD and, to a greater extent, teledermoscopy may be valid and reliable tools for the diagnosis of AK and field cancerization and may improve diagnosis and correct allocation and management in gatekeeper healthcare systems. It can be an alternative tool to training primary care physicians in direct diagnosis of these lesions.

Accuracy of dermoscopic criteria for the differential diagnosis between irritated seborrheic keratosis and squamous cell carcinoma

BACKGROUND

Even with the addition of dermoscopy, a significant morphologic overlap exists between irritated seborrheic keratosis (ISK) and squamous cell carcinoma (SCC).

OBJECTIVE

The aim of this study was to investigate the dermoscopic criteria that could serve as potent predictors for the differential diagnosis between ISK and SCC.

METHODS

Dermoscopic images of histopathologically diagnosed ISKs and SCCs were evaluated by 3 independent investigators for the presence of predefined criteria.

RESULTS

A total of 104 SCCs and 61 ISKs were included. The main dermoscopic predictors of SCC were dotted vessels (odds ratio [OR], 10.4), branched linear vessels (OR, 5.30), white structureless areas (OR, 6.78), white circles surrounding follicles (OR, 23.45), a diffuse irregular (OR, 2.55) or peripheral (OR, 2.8) vessel arrangement, and a central scale arrangement (OR, 3.35). Dermoscopic predictors of ISK were hairpin vessels (OR, 0.38), a diffuse regular vessel arrangement (OR, 0.39 and OR, 0.36), and white halos surrounding vessels covering more than 10% of the lesion (OR, 0.29 and OR, 0.12).

LIMITATIONS

First, the retrospective design of the study; second, the differential diagnosis included in the study was restricted to ISK and SCC.

CONCLUSIONS

We confirmed the significant morphologic overlap between ISK and SCC, but we also identified potent predictors for the differential diagnosis between these 2 entities.

An Analysis of Biopsies for Suspected Skin Cancer at a Tertiary Care Dermatology Clinic in the Western Cape Province of South Africa

BACKGROUND

Skin cancer is a growing health concern worldwide. It is the most common malignancy in South Africa and places a large burden on the public healthcare sector. There is a paucity of published scientific data on skin cancer in South Africa.

OBJECTIVES

To report the findings of biopsies performed in patients with suspected skin cancer attending the Tygerberg Academic Hospital (TAH) Dermatology outpatient department (OPD) in the Western Cape Province of South Africa. Methodology: A retrospective chart review identified all patients who underwent a biopsy for a suspected skin cancer diagnosis between September 2015 and August 2016 at the TAH dermatology OPD.

RESULTS

A total number of 696 biopsies from 390 participants were identified, of which 460 were histologically confirmed as malignant lesions. The proportion of clinically suspected skin cancers that were histologically confirmed as cancer was 68%. The most commonly occurring malignancies were basal cell carcinoma (BCC) (54.8%), squamous cell carcinoma (SCC) (18.9%), squamous cell carcinoma in-situ (SCCI) (8.0%), Kaposi's sarcoma (KS) (6.7%), malignant melanoma (MM) (6.1%), and keratoacanthoma (KA) (4.6%). The number needed to treat (NTT) for all cancers diagnosed and for MM was 1.5 and 4 respectively. BCC (89.3%) and KS (67.7%) was the most common skin cancer in the white and black population respectively. The ratio of BCC to SCC was 2.03.

CONCLUSION

This study provides valuable scientific data on the accuracy of skin cancer diagnosis, distribution and patient demographics in the Western Cape Province of South Africa, on which further research can be based. The study highlights the burden of skin cancer on this specific population group and calls for standardised reporting methods and increased surveillance of skin cancers.

Analysis of Collective Human Intelligence for Diagnosis of Pigmented Skin Lesions Harnessed by Gamification Via a Web-Based Training Platform: Simulation Reader Study

Background

The diagnosis of pigmented skin lesion is error prone and requires domain-specific expertise, which is not readily available in many parts of the world. Collective intelligence could potentially decrease the error rates of nonexperts.

Objective

The aim of this study was to evaluate the feasibility and impact of collective intelligence for the detection of skin cancer.

Methods

We created a gamified study platform on a stack of established Web technologies and presented 4216 dermatoscopic images of the most common benign and malignant pigmented skin lesions to 1245 human raters with different levels of experience. Raters were recruited via scientific meetings, mailing lists, and social media posts. Education was self-declared, and domain-specific experience was tested by screening tests. In the target test, the readers had to assign 30 dermatoscopic images to 1 of the 7 disease categories. The readers could repeat the test with different lesions at their own discretion. Collective human intelligence was achieved by sampling answers from multiple readers. The disease category with most votes was regarded as the collective vote per image.

Results

We collected 111,019 single ratings, with a mean of 25.2 (SD 18.5) ratings per image. As single raters, nonexperts achieved a lower mean accuracy (58.6%) than experts (68.4%; mean difference=−9.4%; 95% CI −10.74% to −8.1%; P<.001). Collectives of nonexperts achieved higher accuracies than single raters, and the improvement increased with the size of the collective. A collective of 4 nonexperts surpassed single nonexperts in accuracy by 6.3% (95% CI 6.1% to 6.6%; P<.001). The accuracy of a collective of 8 nonexperts was 9.7% higher (95% CI 9.5% to 10.29%; P<.001) than that of single nonexperts, an improvement similar to single experts (P=.73). The sensitivity for malignant images increased for nonexperts (66.3% to 77.6%) and experts (64.6% to 79.4%) for answers given faster than the intrarater mean.

Conclusions

A high number of raters can be attracted by elements of gamification and Web-based marketing via mailing lists and social media. Nonexperts increase their accuracy to expert level when acting as a collective, and faster answers correspond to higher accuracy. This information could be useful in a teledermatology setting.

Dermoscopy and the experienced clinicians

For several decades, melanoma diagnosis was based on symptoms rather than clinical features. In fact, until the 1970s melanoma was widely not recognized and only diagnosed when presenting as a large, ulcerated, and bleeding nodule. Today it is well known that ulceration and bleeding are symptoms of an advanced stage; thus, it comes not as a surprise that the prognosis of melanoma at that time was very poor. This paper was developed to recognize dermoscopy as an integrative part of the clinical examination, bearing in mind that naked eye diagnosis can change after dermoscopy outcomes, and to help clinicians avoid the concept: "If in doubt, cut it out".

The impact of patient clinical information on automated skin cancer detection

Skin cancer is one of the most common types of cancer worldwide. Over the past few years, different approaches have been proposed to deal with automated skin cancer detection. Nonetheless, most of them are based only on dermoscopic images and do not take into account the patient clinical information, an important clue towards clinical diagnosis. In this work, we present an approach to fill this gap. First, we introduce a new dataset composed of clinical images, collected using smartphones, and clinical data related to the patient. Next, we propose a straightforward method that includes an aggregation mechanism in well-known deep learning models to combine features from images and clinical data. Last, we carry out experiments to compare the models' performance with and without using this mechanism. The results present an improvement of approximately 7% in balanced accuracy when the aggregation method is applied. Overall, the impact of clinical data on models' performance is significant and shows the importance of including these features on automated skin cancer detection.

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.

Dermatoscopy for the rapid diagnosis of Talaromyces marneffei infection: a case report

Background

Talaromyces marneffei is a thermally dimorphic fungus endemic in south-east Asia. It predominantly occurs in both immunocompromised and immunosuppressed patients and can be fatal if diagnosis and treatment are delayed. The clinical manifestations of T. marneffei infection are nonspecific and rapid diagnosis of T. marneffei infection remains challenging.

Case presentation

A 24-year-old man came to our outpatient department with the sign of common skin lesions. The lesions were cuticolor follicular papules with or without central umbilication, nodules and acne-like lesions, which are common in syringoma, steatocystoma multiplex and trichoepithelioma. A dermatoscopy examination was performed to differentiate these skin lesions. The dermatoscopic images revealed circular or quasi-circular whitish amorphous structure with a central brownish keratin plug, providing the diagnostic clues of T. marneffei infection. Therefore, a skin scrapings culture, skin biopsy and serological detection for human immunodeficiency virus (HIV) were performed. The final diagnosis of this patient was T. marneffei and HIV co-infection.

Conclusion

Rapid diagnosis of T. marneffei infection is clinically challenging since presenting clinical manifestations are nonspecific with significant overlap with other common conditions. This case highlights that dermatoscopy is a promising tool for the rapid diagnosis of T. marneffei infection in patients with nonspecific skin lesions, assisting clinicians to avoid delayed diagnosis or misdiagnosis.

Skin Lesion Segmentation in Dermoscopic Images with Combination of YOLO and GrabCut Algorithm

Skin lesion segmentation has a critical role in the early and accurate diagnosis of skin cancer by computerized systems. However, automatic segmentation of skin lesions in dermoscopic images is a challenging task owing to difficulties including artifacts (hairs, gel bubbles, ruler markers), indistinct boundaries, low contrast and varying sizes and shapes of the lesion images. This paper proposes a novel and effective pipeline for skin lesion segmentation in dermoscopic images combining a deep convolutional neural network named as You Only Look Once (YOLO) and the GrabCut algorithm. This method performs lesion segmentation using a dermoscopic image in four steps: 1. Removal of hairs on the lesion, 2. Detection of the lesion location, 3. Segmentation of the lesion area from the background, 4. Post-processing with morphological operators. The method was evaluated on two publicly well-known datasets, that is the PH2 and the ISBI 2017 (Skin Lesion Analysis Towards Melanoma Detection Challenge Dataset). The proposed pipeline model has achieved a 90% sensitivity rate on the ISBI 2017 dataset, outperforming other deep learning-based methods. The method also obtained close results according to the results obtained from other methods in the literature in terms of metrics of accuracy, specificity, Dice coefficient, and Jaccard index.

Multimodal skin lesion classification using deep learning

While convolutional neural networks (CNNs) have successfully been applied for skin lesion classification, previous studies have generally considered only a single clinical/macroscopic image and output a binary decision. In this work, we have presented a method which combines multiple imaging modalities together with patient metadata to improve the performance of automated skin lesion diagnosis. We evaluated our method on a binary classification task for comparison with previous studies as well as a five class classification task representative of a real-world clinical scenario. We showed that our multimodal classifier outperforms a baseline classifier that only uses a single macroscopic image in both binary melanoma detection (AUC 0.866 vs 0.784) and in multiclass classification (mAP 0.729 vs 0.598). In addition, we have quantitatively showed the automated diagnosis of skin lesions using dermatoscopic images obtains a higher performance when compared to using macroscopic images. We performed experiments on a new data set of 2917 cases where each case contains a dermatoscopic image, macroscopic image and patient metadata.

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.

Sequential digital dermatoscopic imaging of patients with multiple atypical nevi

Patients with multiple atypical nevi are at higher risk of developing melanoma. Among different techniques, sequential digital dermatoscopic imaging (SDDI) is a state-of-the art method to enhance diagnostic accuracy in evaluating pigmented skin lesions. It relies on analyzing digital dermatoscopic images of a lesion over time to find specific dynamic criteria inferring biologic behavior. SDDI can reduce the number of necessary excisions and finds melanomas in an early—and potentially curable—stage, but precautions in selecting patients and lesions have to be met to reach those goals.