Observational study investigating the level of support from a convolutional neural network in face and scalp lesions deemed diagnostically 'unclear' by dermatologists.

BACKGROUND: The clinical diagnosis of face and scalp lesions (FSL) is challenging due to overlapping features. Dermatologists encountering diagnostically 'unclear' lesions may benefit from artificial intelligence support via convolutional neural networks (CNN). METHODS: In a web-based classification task, dermatologists (n = 64) diagnosed a convenience sample of 100 FSL as 'benign', 'malignant', or 'unclear' and indicated their management decisions ('no action', 'follow-up', 'treatment/excision'). A market-approved CNN (Moleanalyzer-Pro®, FotoFinder Systems, Germany) was applied for binary classifications (benign/malignant) of dermoscopic images. RESULTS: After reviewing one dermoscopic image per case, dermatologists labelled 562 of 6400 diagnoses (8.8%) as 'unclear' and mostly managed these by follow-up examinations (57.3%, n = 322) or excisions (42.5%, n = 239). Management was incorrect in 58.8% of 291 truly malignant cases (171 'follow-up' or 'no action') and 43.9% of 271 truly benign cases (119 'excision'). Accepting CNN classifications in unclear cases would have reduced false management decisions to 4.1% in truly malignant and 31.7% in truly benign lesions (both p < 0.01). After receiving full case information 239 diagnoses (3.7%) remained 'unclear' to dermatologists, now triggering more excisions (72.0%) than follow-up examinations (28.0%). These management decisions were incorrect in 32.8% of 116 truly malignant cases and 76.4% of 123 truly benign cases. Accepting CNN classifications would have reduced false management decisions to 6.9% in truly malignant lesions and to 38.2% in truly benign cases (both p < 0.01). CONCLUSIONS: Dermatologists mostly managed diagnostically 'unclear' FSL by treatment/excision or follow-up examination. Following CNN classifications as guidance in unclear cases seems suitable to significantly reduce incorrect decisions.

Does sex matter? Analysis of sex-related differences in the diagnostic performance of a market-approved convolutional neural network for skin cancer detection.

BACKGROUND: Advances in biomedical artificial intelligence may introduce or perpetuate sex and gender discriminations. Convolutional neural networks (CNN) have proven a dermatologist-level performance in image classification tasks but have not been assessed for sex and gender biases that may affect training data and diagnostic performance. In this study, we investigated sex-related imbalances in training data and diagnostic performance of a market-approved CNN for skin cancer classification (Moleanalyzer Pro®, Fotofinder Systems GmbH, Bad Birnbach, Germany). METHODS: We screened open-access dermoscopic image repositories widely used for CNN training for distribution of sex. Moreover, the sex-related diagnostic performance of the market-approved CNN was tested in 1549 dermoscopic images stratified by sex (female n = 773; male n = 776). RESULTS: Most open-access repositories showed a marked under-representation of images originating from female (40%) versus male (60%) patients. Despite these imbalances and well-known sex-related differences in skin anatomy or skin-directed behaviour, the tested CNN achieved a comparable sensitivity of 87.0% [80.9%-91.3%] versus 87.1% [81.1%-91.4%], specificity of 98.7% [97.4%-99.3%] versus 96.9% [95.2%-98.0%] and ROC-AUC of 0.984 [0.975-0.993] versus 0.979 [0.969-0.988] in dermoscopic images of female versus male origin, respectively. In the sample at hand, sex-related differences in ROC-AUCs were not statistically significant in the per-image analysis nor in an additional per-individual analysis (p ≥ 0.59). CONCLUSION: Design and training of artificial intelligence algorithms for medical applications should generally acknowledge sex and gender dimensions. Despite sex-related imbalances in open-access training data, the diagnostic performance of the tested CNN showed no sex-related bias in the classification of skin lesions.

Mikrovaskuläre Pathologien bei Patienten mit Psoriasis vulgaris mittels Nagelfalzkapillarmikroskopie identifiziert: Ergebnisse einer prospektiven kontrollierten Studie.

Hintergrund: Die Psoriasis gilt als unabhängiger kardiovaskulärer Risikofaktor und Treiber einer Atherogenese. Mikrovaskuläre Veränderungen in psoriatischen Plaques sind gut beschrieben, wohingegen Veränderungen außerhalb betroffener Hautareale kaum untersucht wurden. In dieser Studie wurden Nagelfalzkapillaren von Psoriasispatienten in nicht betroffener Haut systematisch untersucht. Patienten und Methodik: Prospektive Studie mit Untersuchung von Nagelfalzkapillaren bei Psoriasispatienten im Vergleich zu gesunden Kontrollen mittels digitaler Videokapillarmikroskopie. Es wurden 21 kapillarmikroskopische Parameter bewertet und die Ergebnisse mit Charakteristika der Patienten und der Psoriasiserkrankung, mit Laborparametern und Messungen der Intima-Media-Dicke der Arteria carotis communis korreliert. Ergebnisse: Die 77 Psoriasispatienten (24 mit zusätzlicher Psoriasisarthritis) und 71 Kontrollen zeigten sich hinsichtlich demographischer Merkmale und relevanter Einflussfaktoren für eine Mikroangiopathie ausbalanciert. Im Vergleich zur Kontrollgruppe zeigten Psoriasispatienten eine signifikante Minderung der kapillaren Dichte, häufigere Kapillarerweiterung mit mehr Verzweigungen, Torquierungen und kapillaren Unregelmäßigkeiten. Zusätzlich zeigten Psoriasispatienten signifikant höhere inflammatorische Serummarker und eine gesteigerte Intima-Media-Dicke. In unserem Kollektiv bestand kein Zusammenhang zwischen Krankheitsdauer oder Schweregrad der Psoriasis und spezifischen Kapillarveränderungen. Schlussfolgerungen: Die Nagelfalzkapillaren der untersuchten Psoriasispatienten zeigten ausgeprägte mikrovaskuläre Veränderungen, welche mit erhöhten Markern einer systemischen Entzündung und Frühzeichen einer Atherosklerose korrelierten. Weitere Studien sind erforderlich, um die Rolle der digitalen Videokapillarmikroskopie in der Bewertung des kardiovaskulären Risikos von Psoriasispatienten zu untersuchen.

Nailfold videocapillaroscopy identifies microvascular pathologies in psoriasis vulgaris: Results of a prospective controlled study.

BACKGROUND: Psoriasis is considered an independent cardiovascular risk factor, evidentially driving atherosclerosis. However, little is known about changes in the microvasculature of non-lesional skin in psoriasis patients. This study systematically examined capillary pathologies in psoriasis patients by digital video nailfold capillaroscopy. PATIENTS AND METHODS: Prospective study comparing nailfold capillaries of psoriasis patients with those of healthy controls. Nailfold capillaries were evaluated for 21 parameters and results were correlated with characteristics of patients and psoriatic disease, laboratory parameters, and measurements of carotid intima-media thickness. RESULTS: 77 psoriasis patients (24 patients with additional psoriatic arthritis) and 71 controls were well-matched for demographic features and for relevant confounding factors causing microangiopathy. In comparison with controls, psoriasis patients showed a significant loss of capillaries, capillary expansion with increased ramifications and tortuosity and capillary irregularities. Moreover, in psoriasis patients we found significantly elevated serum markers of inflammation and significantly increased intima-media-thickness measurements. We found no effect of disease duration nor disease activity on capillary changes. CONCLUSIONS: Nailfold capillaries of psoriasis patients showed marked microvascular abnormalities accompanied by increased markers of systemic inflammation and atherosclerosis. Prospective cohort studies are needed to assess the role of nailfold capillaroscopy for predicting the cardiovascular risk of psoriasis patients.

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.

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.

Evaluation of capillary pathologies by nailfold capillaroscopy in patients with psoriasis vulgaris: study protocol for a prospective, controlled exploratory study.

INTRODUCTION: Psoriasis vulgaris was shown to be an independent factor increasing the risk of several comorbidities such as obesity, diabetes and dyslipidaemia with an increased risk of stroke and myocardial infarction. We hypothesise that early endothelial dysfunction, which plays a crucial role in the pathogenesis of atherosclerosis, may be detected by digital video nailfold capillaroscopy (DVNC) at the level of the dermal capillary microvasculature as a surrogate parameter. Nailfolds represent the only body site allowing for a non-invasive assessment of the capillary microvasculature at a horizontal plane. DVNC is a well-established diagnostic tool for in vivo assessment of the peripheral microcirculation by evaluating the morphology of dermal papillary capillaries. To date, reports on morphological changes of the non-lesional nailfold capillaries in patients with psoriasis vulgaris are scarce and the existing data are not conclusive. METHODS AND ANALYSIS: This is a prospective, single-centre, non-randomised, controlled, exploratory study assessing the capillary patterns in 100 subjects affected by psoriasis vulgaris. Non-lesional nailfold capillaries will be imaged by means of DVNC (Optilia Digital Capillaroscopy System, Optilia Instruments AB, Sollentuna, Sweden) in 50 patients affected by psoriasis vulgaris and 50 healthy controls. Assessments will include a qualitative, descriptive analysis of the nailfold capillaries' morphology, as well as a quantitative investigation (frequency, extent) of changes in capillary patterns. Moreover, patients' characteristics associated with the manifestation of nailfold capillaries' pathologies including well-known cardiovascular risk markers will be studied. ETHICS AND DISSEMINATION: Ethical approval was provided by the ethic committee of the medical faculty of the University of Heidelberg (Ethics approval number S-447/2017). The design and the final results of the study will be published and made available to the public. TRIAL REGISTRATION NUMBER: DRKS00012856.