Melanomas vs. nevi in high-risk patients under long-term monitoring with digital dermatoscopy: do melanomas and nevi already differ at baseline?

Effect of patient-contextual skin images in human- and artificial intelligence-based diagnosis of melanoma: Results from the 2020 SIIM-ISIC melanoma classification challenge

BACKGROUND

While the high accuracy of reported AI tools for melanoma detection is promising, the lack of holistic consideration of the patient is often criticized. Along with medical history, a dermatologist would also consider intra-patient nevi patterns, such that nevi that are different from others on a given patient are treated with suspicion.

OBJECTIVE

To evaluate whether patient-contextual lesion-images improves diagnostic accuracy for melanoma in a dermoscopic image-based AI competition and a human reader study.

METHODS

An international online AI competition was held in 2020. The task was to classify dermoscopy images as melanoma or benign lesions. A multi-source dataset of dermoscopy images grouped by patient were provided, and additional use of public datasets was permitted. Competitors were judged on area under the receiver operating characteristic (AUROC) on a private leaderboard. Concurrently, a human reader study was hosted using a subset of the test data. Participants gave their initial diagnosis of an index case (melanoma vs. benign) and were then presented with seven additional lesion-images of that patient before giving a second prediction of the index case. Outcome measures were sensitivity and specificity.

RESULTS

The top 50 of 3308 AI competition entries achieved AUROC scores ranging from 0.943 to 0.949. Few algorithms considered intra-patient lesion patterns and instead most evaluated images independently. The median sensitivity and specificity of human readers before receiving contextual images were 60.0% and 86.7%, and after were 60.0% and 85.7%. Human and AI algorithm performance varied by image source.

CONCLUSION

This study provided an open-source state-of-the-art algorithm for melanoma detection that has been evaluated at multiple centres. Patient-contextual images did not positively impact performance of AI algorithms or human readers. Providing seven contextual images and no total body image may have been insufficient to test the applicability of the intra-patient lesion patterns.

The Role of Digital Dermoscopy and Follow-Up in the Detection of Amelanotic/Hypomelanotic Melanoma in a Group of High-Risk Patients-Is It Useful?

The prognosis, outcome, and overall survival of melanoma patients improve with early diagnosis which has been facilitated in the past few decades with the introduction of dermoscopy. Further advancements in dermoscopic research, coupled with skilled, educated dermatologists in dermoscopy, have contributed to timely diagnoses. However, detecting amelanotic and hypomelanotic melanoma remains a challenge even to the most skilled experts because these melanomas can mimic inflammatory diseases, numerous benign lesions, and non-melanoma skin cancers. The list of the possible differential diagnoses can be long. Melanoma prediction without the pigment relies only on vascular criteria, and all classic dermoscopic algorithms have failed to fulfill our expectations. In fact, the diagnosis of amelanotic and hypomelanotic melanomas is very challenging, which is why every tool in detecting these lesions is of significance. This review aims to explore the current knowledge and the literature on the possibility of detecting amelanotic/hypomelanotic melanomas using sequential monitoring with digital dermoscopy and total body skin photography.

Analyzing the Impact of Image Denoising and Segmentation on Melanoma Classification Using Convolutional Neural Networks

Early skin cancer detection and its treatment are crucial for reducing death rates worldwide. Deep learning techniques have been used successfully to develop an automatic lesion detection system. This study explores the impact of pre-processing steps such as data augmentation, contrast enhancement, and segmentation on improving the convolutional neural network (CNN) performance for lesion classification. The classification network was designed from scratch by uniquely organizing its layers and using a different number of kernels, depth of the network, size, and hyperparameters. In addition, the network's performance was improved by pre-processing and segmentation steps. The proposed network was compared with the current state-of-the-art to demonstrate its best performance on the benchmark HAM10000 lesion dataset. The experimental study revealed that the classification network using denoised+segmented data achieved an accuracy (ACC), precision (PRE), recall (REC), specificity (SPE), and F-score of 93.40%, 93.45%, 94.51%, 92.08%, and 93.98%, respectively. To conclude, classification performance can be improved by incorporating pre-processing and segmentation steps.

Dysplastic nevus part I: Historical perspective, classification, and epidemiology

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.

[Artificial intelligence-based classification for the diagnostics of skin cancer]

Convolutional neural networks (CNN) achieve a level of performance comparable or even superior to dermatologists in the assessment of pigmented and nonpigmented skin lesions. In the analysis of images by artificial neural networks, images on a pixel level pass through various layers of the network with different graphic filters. Based on excellent study results, a first deep learning network (Moleanalyzer pro, Fotofinder Systems GmBH, Bad Birnbach, Germany) received market approval in Europe. However, such neural networks also reveal relevant limitations, whereby rare entities with insufficient training images are classified less adequately and image artifacts can lead to false diagnoses. Best results can ultimately be achieved in a cooperation of "man with machine". For future skin cancer screening, automated total body mapping is evaluated, which combines total body photography, automated data extraction and assessment of all relevant skin lesions.

Indications for Digital Monitoring of Patients With Multiple Nevi: Recommendations from the International Dermoscopy Society

Introduction

In patients with multiple nevi, sequential imaging using total body skin photography (TBSP) coupled with digital dermoscopy (DD) documentation reduces unnecessary excisions and improves the early detection of melanoma. Correct patient selection is essential for optimizing the efficacy of this diagnostic approach.

Objectives

The purpose of the study was to identify, via expert consensus, the best indications for TBSP and DD follow-up.

Methods

This study was performed on behalf of the International Dermoscopy Society (IDS). We attained consensus by using an e-Delphi methodology. The panel of participants included international experts in dermoscopy. In each Delphi round, experts were asked to select from a list of indications for TBSP and DD.

Results

Expert consensus was attained after 3 rounds of Delphi. Participants considered a total nevus count of 60 or more nevi or the presence of a CDKN2A mutation sufficient to refer the patient for digital monitoring. Patients with more than 40 nevi were only considered an indication in case of personal history of melanoma or red hair and/or a MC1R mutation or history of organ transplantation.

Conclusions

Our recommendations support clinicians in choosing appropriate follow-up regimens for patients with multiple nevi and in applying the time-consuming procedure of sequential imaging more efficiently. Further studies and real-life data are needed to confirm the usefulness of this list of indications in clinical practice.

Monitoring patients at risk for melanoma: May convolutional neural networks replace the strategy of sequential digital dermoscopy?

BACKGROUND

Sequential digital dermoscopy (SDD) is applied for early melanoma detection by uncovering dynamic changes of monitored lesions. Convolutional neural networks (CNN) are capable of high diagnostic accuracies similar to trained dermatologists.

OBJECTIVES

To investigate the capability of CNN to correctly classify melanomas originally diagnosed by mere dynamic changes during SDD.

METHODS

A retrospective cross-sectional study using image quartets of 59 high-risk patients each containing one melanoma diagnosed by dynamic changes during SDD and three nevi (236 lesions). Two validated CNN classified quartets at baseline or after SDD follow-up at the time of melanoma diagnosis. Moreover, baseline quartets were rated by 26 dermatologists. The main outcome was the number of quartets with correct classifications.

RESULTS

CNN-1 correctly classified 9 (15.3%) and CNN-2 8 (13.6%) of 59 baseline quartets. In baseline images, CNN-1 attained a sensitivity of 25.4% (16.1%-37.8%) and specificity of 92.7% (87.8%-95.7%), whereas CNN-2 of 28.8% (18.8%-41.4%) and 75.7% (68.9%-81.4%). Expectedly, after SDD follow-up CNN more readily detected melanomas resulting in improved sensitivities (CNN-1: 44.1% [32.2%-56.7%]; CNN-2: 49.2% [36.8%-61.6%]). Dermatologists were told that each baseline quartet contained one melanoma, and on average, correctly classified 24 (22-27) of 59 quartets. Correspondingly, accepting a baseline quartet to be appropriately classified whenever the highest malignancy score was assigned to the melanoma within, CNN-1 and CNN-2 correctly classified 28 (47.5%) and 22 (37.3%) of 59 quartets, respectively.

CONCLUSIONS

The tested CNN could not replace the strategy of SDD. There is a need for CNN capable of integrating information on dynamic changes into analyses.

Evolution of the Clinical, Dermoscopic and Pathologic Diagnosis of Melanoma

The conventional narrative states that the steadily rising incidence of melanoma among fair-skinned Caucasian populations during the last decades is caused by excessive UV-exposure. There is, however, no doubt that other factors had a significant impact on the rising incidence of melanoma. Pre-1980s the clinical diagnosis of melanoma was based on gross criteria such as ulceration or bleeding. Melanomas were often diagnosed in advanced stages when the prognosis was grim. In the mid-1980s education campaigns such as the propagation of the ABCD criteria, which addressed health care professionals and the public alike, shifted the focus towards early recognition. Dermatoscopy, which became increasingly popular in the mid-1990s, improved the accuracy for the diagnosis of melanoma in comparison to inspection with the unaided eye, especially for flat and small lesions lacking ABCD criteria. At the same time, pathologists began to lower their thresholds, particularly for the diagnosis of melanoma in situ. The melanoma epidemic that followed was mainly driven by an increase in the number of in situ or microinvasive melanomas. In a few decades, the landscape shifted from an undercalling to an overcalling of melanomas, a development that is now met with increased criticism. The gold standard of melanoma diagnosis is still conventional pathology, which is faced with low to moderate interobserver agreement. New insights in the molecular landscape of melanoma did not translate into techniques for the reliable diagnosis of gray zone lesions including small lesions. The aim of this review is to put our current view of melanoma diagnosis in historical context and to provide a narrative synthesis of its evolution. Based on this narrative I will provide suggestions on how to rebuild the trust in melanoma diagnosis accuracy and in the benefit of early recognition.

Skin cancer detection by deep learning and sound analysis algorithms: A prospective clinical study of an elementary dermoscope

Background

Skin cancer (SC), especially melanoma, is a growing public health burden. Experimental studies have indicated a potential diagnostic role for deep learning (DL) algorithms in identifying SC at varying sensitivities. Previously, it was demonstrated that diagnostics by dermoscopy are improved by applying an additional sonification (data to sound waves conversion) layer on DL algorithms. The aim of the study was to determine the impact of image quality on accuracy of diagnosis by sonification employing a rudimentary skin magnifier with polarized light (SMP).

Methods

Dermoscopy images acquired by SMP were processed by a first deep learning algorithm and sonified. Audio output was further analyzed by a different secondary DL. Study criteria outcomes of SMP were specificity and sensitivity, which were further processed by a F2-score, i.e. applying a twice extra weight to sensitivity over positive predictive values.

Findings

Patients (n = 73) fulfilling inclusion criteria were referred to biopsy. SMP analysis metrics resulted in a receiver operator characteristic curve AUC's of 0.814 (95% CI, 0.798–0.831). SMP achieved a F2-score sensitivity of 91.7%, specificity of 41.8% and positive predictive value of 57.3%. Diagnosing the same set of patients' lesions by an advanced dermoscope resulted in a F2-score sensitivity of 89.5%, specificity of 57.8% and a positive predictive value of 59.9% (P=NS).

Interpretation

DL processing of dermoscopic images followed by sonification results in an accurate diagnostic output for SMP, implying that the quality of the dermoscope is not the major factor influencing DL diagnosis of skin cancer. Present system might assist all healthcare providers as a feasible computer-assisted detection system.

Fund

Bostel Technologies.

Trial Registration clinicaltrials.gov Identifier: NCT03362138

Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies

BACKGROUND

Early diagnosis of skin cancer lesions by dermoscopy, the gold standard in dermatological imaging, calls for a diagnostic upscale. The aim of the study was to improve the accuracy of dermoscopic skin cancer diagnosis through use of novel deep learning (DL) algorithms. An additional sonification-derived diagnostic layer was added to the visual classification to increase sensitivity.

METHODS

Two parallel studies were conducted: a laboratory retrospective study (LABS, n = 482 biopsies) and a non-interventional prospective observational study (OBS, n = 63 biopsies). A training data set of biopsy-verified reports, normal and cancerous skin lesions (n = 3954), were used to develop a DL classifier exploring visual features (System A). The outputs of the classifier were sonified, i.e. data conversion into sound (System B). Derived sound files were analyzed by a second machine learning classifier, either as raw audio (LABS, OBS) or following conversion into spectrograms (LABS) and by image analysis and human heuristics (OBS). The OBS criteria outcomes were System A specificity and System B sensitivity as raw sounds, spectrogram areas or heuristics.

FINDINGS

LABS employed dermoscopies, half benign half malignant, and compared the accuracy of Systems A and B. System A algorithm resulted in a ROC AUC of 0.976 (95% CI, 0.965-0.987). Secondary machine learning analysis of raw sound, FFT and Spectrogram ROC curves resulted in AUC's of 0.931 (95% CI 0.881-0.981), 0.90 (95% CI 0.838-0.963) and 0.988 (CI 95% 0.973-1.001), respectively. OBS analysis of raw sound dermoscopies by the secondary machine learning resulted in a ROC AUC of 0.819 (95% CI, 0.7956 to 0.8406). OBS image analysis of AUC for spectrograms displayed a ROC AUC of 0.808 (CI 95% 0.6945 To 0.9208). By applying a heuristic analysis of Systems A and B a sensitivity of 86% and specificity of 91% were derived in the clinical study.

INTERPRETATION

Adding a second stage of processing, which includes a deep learning algorithm of sonification and heuristic inspection with machine learning, significantly improves diagnostic accuracy. A combined two-stage system is expected to assist clinical decisions and de-escalate the current trend of over-diagnosis of skin cancer lesions as pathological. FUND: Bostel Technologies. Trial Registration clinicaltrials.gov Identifier: NCT03362138.

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.

[Dermatoscopic-pathological correlation of melanocytic skin lesions]

There is no doubt that dermatopathology is the most important method to decide if a melanocytic lesion is benign or malignant; however, like most morphologic examinations, dermatopathology is subjective. A recent study demonstrated that the pathologic diagnosis of melanocytic skin lesions has a high variability. Reports with false-positive or false-negative diagnoses are relatively common. The pathologic examination of melanocytic lesions also has observer-independent limitations and one has to accept that some melanocytic lesions cannot be classified as benign or malignant with confidence by dermatopathology alone. If a confident diagnosis is not possible a dermatoscopic-pathologic correlation may be helpful. This, however, is only possible if dermatoscopic images are available and if the dermatopathologist knows how to interpret dermatoscopic structures. A dermatoscopic-pathologic correlation is not useful in all difficult melanocytic lesions but it should be considered in difficult flat pigmented lesions. In these cases dermatoscopy may provide even more important additional information than molecular findings.

The status of dermoscopy in Germany - results of the cross-sectional Pan-Euro-Dermoscopy Study

BACKGROUND

Survey on the current status of dermoscopy in Germany.

METHODS

In the context of a pan-European internet-based study (n = 7,480) conducted by the International Dermoscopy Society, 880 German dermatologists were asked to answer questions with respect to their level of training as well as their use and perceived benefit of dermoscopy.

RESULTS

Seven hundred and sixty-two (86.6 %) participants practiced dermatology in a publicly funded health care setting; 98.4 % used a dermoscope in routine clinical practice. About 93 % (n = 814) stated to have had more than five years of experience in the use of dermoscopy. Dermoscopy was considered useful in the diagnosis of melanoma by 93.6 % (n = 824); for pigmented skin tumors, by 92.4 % (n = 813); in the follow-up of melanocytic lesions, by 88.6 % (n = 780); for non-pigmented lesions, by 71.4 % (n = 628), in the follow-up of non-melanocytic lesions, by 52.7 % (n = 464); and for inflammatory skin lesions, by 28.5 % (n = 251). Overall, 86.5 % (n = 761) of participants felt that - compared to naked-eye examination - dermoscopy increased the number of melanomas diagnosed; 77,7 % (n = 684) considered the number of unnecessary excisions of benign lesions to be decreased. Participants who personally felt that dermoscopy improved their ability to diagnose melanoma were significantly i) younger, ii) had been practicing dermatology for a shorter period of time, iii) were less commonly employed by an university-affiliated dermatology department, iv) were more frequently working in an office-based public health care setting, and v) had more frequently been trained in dermoscopy during their dermatology residency.

CONCLUSIONS

The findings presented herein ought to be integrated into future residency and continuing medical education programs with the challenge to improve dermato-oncological care and to expand the diagnostic spectrum of dermoscopy to include inflammatory skin diseases.