Recurrent Phases of Strict Protein Limitation Inhibit Tumor Growth and Restore Lifespan in A Drosophila Intestinal Cancer Model.

Diets that restrict caloric or protein intake offer a variety of benefits, including decreasing the incidence of cancer. However, whether such diets pose a substantial therapeutic benefit as auxiliary cancer treatments remains unclear. We determined the effects of severe protein depletion on tumorigenesis in a Drosophila melanogaster intestinal tumor model, using a human RAF gain-of-function allele. Severe and continuous protein restriction significantly reduced tumor growth but resulted in premature death. Therefore, we developed a diet in which short periods of severe protein restriction alternated cyclically with periods of complete feeding. This nutritional regime reduced tumor mass, restored gut functionality, and rescued the lifespan of oncogene-expressing flies to the levels observed in healthy flies on a continuous, fully nutritious diet. Furthermore, this diet reduced the chemotherapy-induced stem cell activity associated with tumor recurrence. Transcriptome analysis revealed long-lasting changes in the expression of key genes involved in multiple major developmental signaling pathways. Overall, the data suggest that recurrent severe protein depletion effectively mimics the health benefits of continuous protein restriction, without undesired nutritional shortcomings. This provides seminal insights into the mechanisms of the memory effect required to maintain the positive effects of protein restriction throughout the phases of a full diet. Finally, the repetitive form of strict protein restriction is an ideal strategy for adjuvant cancer therapy that is useful in many tumor contexts.

PTPN11 Mosaicism Causes a Spectrum of Pigmentary and Vascular Neurocutaneous Disorders and Predisposes to Melanoma.

Phakomatosis pigmentovascularis is a diagnosis that denotes the coexistence of pigmentary and vascular birthmarks of specific types, accompanied by variable multisystem involvement, including CNS disease, asymmetrical growth, and a predisposition to malignancy. Using a tight phenotypic group and high-depth next-generation sequencing of affected tissues, we discover here clonal mosaic variants in gene PTPN11 encoding SHP2 phosphatase as a cause of phakomatosis pigmentovascularis type III or spilorosea. Within an individual, the same variant is found in distinct pigmentary and vascular birthmarks and is undetectable in blood. We go on to show that the same variants can cause either the pigmentary or vascular phenotypes alone, and drive melanoma development within pigmentary lesions. Protein structure modeling highlights that although variants lead to loss of function at the level of the phosphatase domain, resultant conformational changes promote longer ligand binding. In vitro modeling of the missense variants confirms downstream MAPK pathway overactivation and widespread disruption of human endothelial cell angiogenesis. Importantly, patients with PTPN11 mosaicism theoretically risk passing on the variant to their children as the germline RASopathy Noonan syndrome with lentigines. These findings improve our understanding of the pathogenesis and biology of nevus spilus and capillary malformation syndromes, paving the way for better clinical management.

UV Irradiation of Nevi: Impact on Performance of Electrical Impedance Spectroscopy and a Convolution Neural Network.

Introduction: UV irradiation of nevi induces transient melanocytic activation with dermoscopic and histological changes. Objectives: We investigated whether UV irradiation of nevi may influence electrical impedance spectroscopy (EIS) or convolution neural networks (CNN). Methods: Prospective, controlled trial in 50 patients undergoing phototherapy (selective UV phototherapy (SUP), UVA1, SUP/UVA1, or PUVA). EIS (Nevisense, SciBase AB) and CNN scores (Moleanalyzer-Pro, FotoFinder Systems) of nevi were assessed before (V1) and after UV irradiation (V2). One nevus (nevusirr) was exposed to UV light, another UV-shielded (nevusnon-irr). Results: There were no significant differences in EIS scores of nevusirr before (2.99 [2.51-3.47]) and after irradiation (3.32 [2.86-3.78]; P = 0.163), which was on average 13.28 (range 4-47) days later. Similarly, UV-shielded nevusnon-irr did not show significant changes of EIS scores (V1: 2.65 [2.19-3.11]), V2: 2.92 [2.50-3.34]; P = 0.094). Subgroup analysis by irradiation revealed a significant increase of EIS scores of nevusirr (V1: 2.69 [2.21-3.16], V2: 3.23 [2.72-3.73]; P = 0.044) and nevusnon-irr (V1: 2.57 [2.07-3.07], V2: 3.03 [2.48-3.57]; P = 0.033) for patients receiving SUP. In contrast, CNN scores of nevusirr (P = 0.995) and nevusnon-irr (P = 0.352) showed no significant differences before and after phototherapy. Conclusions: For the tested EIS system increased EIS scores were found in nevi exposed to SUP. In contrast, CNN results were more robust against UV exposure.

Multiarm study comparing patient-reported and clinical outcome measures in patients undergoing antipsoriatic therapy with non-biological systemic agents in a real-world setting.

BACKGROUND: Although the inclusion of patients' preferences and needs is essential for therapy adherence, the assessment of patient-reported outcome measures in clinical trials is often neglected. Therefore, the aim of this study was to quantify several patient-reported outcome measures in psoriasis patients undergoing systemic therapy in a real-life clinical setting. METHODS: This clinical trial has been designed as a prospective, multiarm study to investigate the treatment satisfaction, adherence to therapy, quality of life (QoL), and clinical response in a real-life clinical setting during the initial 6 months of treatment with apremilast, methotrexate, and fumaric acids in 80 patients suffering from plaque psoriasis. RESULTS: The treatment satisfaction for the three systemic therapies was rated 'sufficient' with a mean (±SD) Treatment Satisfaction Questionnaire for Medication (TSQM) score of 275.0 (±62.7). Most potential for improvement was seen in the 'effectiveness' domain (54.3 ± 21.5). The highest treatment satisfaction level in all four domains (convenience, effectiveness, global satisfaction, and side-effects) was seen in the methotrexate group with a mean TSQM score of 306.3 ± 50.9, followed by apremilast (267.1 ± 61.6) and fumaric acids (254.9 ± 65.0; p = 0.005). Analysis of the TSQM revealed a considerable discrepancy between patient-reported clinical response and the actual Psoriasis Area and Severity Index (PASI) reduction. This applies equally to the patient- vs. physician-reported side-effects. CONCLUSIONS: This real-life study demonstrates that an adequate assessment of antipsoriatic drugs by PASI-reduction alone is not sufficient and underlines the importance of patient-reported outcome measures not only in clinical trials, but also for improved patient care.

Impact of a synchronous prophylactic treatment of the anterior accessory saphenous vein on the recurrent varicose vein rate in patients undergoing thermal ablation of an insufficient great saphenous vein (SYNCHRONOUS-Study): study protocol for a prospective, multicentre, controlled observational study.

INTRODUCTION: To date, there are no prospective studies evaluating the prevention of recurrent veins by the simultaneous treatment of a sufficient anterior accessory saphenous vein (AASV) in patients undergoing endovenous laser ablation (EVLA) of an insufficient great saphenous vein (GSV). This study will provide important information about the impact of the AASV on the development of recurrent veins after EVLA of the GSV. Additionally, it will be clarified whether patients benefit from a preventive ablation of a sufficient AASV. METHODS AND ANALYSIS: This is a multicentre, prospective, controlled, exploratory clinical study in 1150 patients with a medical indication for EVLA of a refluxing great saphenous vein. Patients will be enrolled into two study groups: in half of the patients EVLA will be performed on the insufficient GSV only. In the other half of the patients EVLA will be performed on the insufficient GSV and additionally on the sufficient AASV. Within seven study visits, patients will be followed-up over a time period of 5 years. Primary study endpoint is the recurrence rate; secondary endpoints include inter alia, complication rate, postoperative pain intensity, quality of life and patient satisfaction. ETHICS AND DISSEMINATION: Before initiation of the study, the protocol was presented and approved by the independent ethics committee of the medical faculty of the University of Heidelberg (Ethics approval number S-596/2018). This study was prospectively registered at the German Clinical Trial Register (https://www.germanctr.de/). Research findings will be disseminated in a peer-reviewed journal and at relevant conferences. TRIAL REGISTRATION NUMBER: German Clinical Trial Registry (DRKS00015486).

Efficacy and safety of endovenous laser ablation with the 1470 nm diode laser using a novel optical probe.

Objectives: Outcome assessment of a novel optical fiber probe for the 1470 nm diode laser under real-world conditions. Methods: Prospective clinical pilot study in 10 patients undergoing endovenous laser ablation with a follow-up period of 1 year. Primary endpoints were efficacy and safety. Secondary endpoints include, inter alia, quality of life and patient satisfaction. Results: After a follow-up period of 1 year all treated vein segments were still occluded. Only mild and short-term side effects (hematoma, ecchymosis and hyperpigmentation) were observed. No intake of pain medication was needed and a quick return to normal activity was documented (0.9 days). Clinical hallmarks of the venous disease (VCSS) improved significantly (p= .003). All patients were very satisfied with the treatment and quality of life (AVVQ) was significantly improved after the procedure (p=.008). Conclusions: The study demonstrates that the endoluminal treatment with the novel fiber probe is highly effective and safe.

Skin Microbiome Variation with Cancer Progression in Human Cutaneous Squamous Cell Carcinoma.

The skin microbiome plays a critical role in skin homeostasis and disorders. UVR is the major cause of nonmelanoma skin cancer, but other risk factors, including immune suppression, chronic inflammation, and antibiotic usage, suggest the microbiome as an additional, unexplored risk factor and potential disease biomarker. The overarching goal was to study the skin microbiome in squamous cell carcinoma (SCC) and premalignant actinic keratosis compared with that in healthy skin to identify skin cancer‒associated changes in the skin microbiome. We performed a high-resolution analysis of shotgun metagenomes of actinic keratosis and SCC in healthy skin, revealing the microbial community shifts specific to actinic keratosis and SCC. Most prominently, the relative abundance of pathobiont Staphylococcus aureus was increased at the expense of commensal Cutibacterium acnes in SCC compared with that in healthy skin, and enrichment of functional pathways in SCC reflected this shift. Notably, C. acnes associated with lesional versus healthy skin differed at the strain level, suggesting the specific functional changes associated with its depletion in SCC. Our study revealed a transitional microbial dysbiosis from healthy skin to actinic keratosis to SCC, supporting further investigation of the skin microbiome for use as a biomarker and providing hypotheses for studies investigating how these microbes might influence skin cancer progression.

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.

Primary care disease management for venous leg ulceration-study protocol for the Ulcus Cruris Care [UCC] randomized controlled trial (DRKS00026126).

BACKGROUND: Venous leg ulcers (VLU) have a prevalence of 1-2% in developed countries, and affected patients are severely and long-term impaired in daily activities, work, and social participation. Evidence-based outpatient treatment based on compression therapy is frequently not implemented. The "Ulcus Cruris Care" project was established to develop a disease management concept to improve outpatient treatment for patients with VLU in German primary care. For this purpose, a multifaceted intervention was conceived consisting of an online training for general practitioners and medical assistants, standardized treatment recommendations, e-learning and print-based information for patients, and a software support for case management. The main aims of the Ulcus Cruris Care intervention are to promote standardized treatment according to current scientific knowledge, to facilitate case management for VLU patients exerted by medical assistants, and to support patient education and participation in the treatment process. The UCC trial was designed to evaluate the effectiveness of the Ulcus Cruris Care intervention. METHODS: The UCC trial is a prospective cluster-randomized controlled multicenter trial. Fifty GP practices are intended to be recruited and randomized 1:1 to intervention or control arm. Patients with venous leg ulcers will be recruited by participating GP practices, to include a total of 63 patients in each arm. The primary outcome is time to ulcer healing. Secondary outcomes comprise number and sizes of ulcers, recurrence, pain intensity according to the visual analog scale, health-related quality of life according to EQ-5D-5L, depressiveness according to Patient Health Questionnaire (PHQ-9), patient satisfaction according to the Patient Assessment of Chronic Illness Care (PACIC-5A) query, and adherence to VLU treatment. The outcome analysis of the UCC trial is accompanied by a health economic analysis and a process evaluation. DISCUSSION: The UCC trial will evaluate whether the Ulcus Cruris Care intervention may lead to faster wound healing, higher health-related quality of life, and lower use of medical resources. If the intervention turns out to have a positive impact on assessed outcomes, comprehensive implementation in primary care may be considered. TRIAL REGISTRATION: The trial protocol (version 1 as of July 19, 2021) has been registered in the German Clinical Trials Register on August 30, 2021 ( DRKS00026126 ).

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.

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.

Altered Cytokine Response of Human Brain Endothelial Cells after Stimulation with Malaria Patient Plasma.

Infections with the deadliest malaria parasite, Plasmodium falciparum, are accompanied by a strong immunological response of the human host. To date, more than 30 cytokines have been detected in elevated levels in plasma of malaria patients compared to healthy controls. Endothelial cells (ECs) are a potential source of these cytokines, but so far it is not known if their cytokine secretion depends on the direct contact of the P. falciparum-infected erythrocytes (IEs) with ECs in terms of cytoadhesion. Culturing ECs with plasma from malaria patients (27 returning travellers) resulted in significantly increased secretion of IL-11, CXCL5, CXCL8, CXCL10, vascular endothelial growth factor (VEGF) and angiopoietin-like protein 4 (ANGPTL4) if compared to matching controls (22 healthy individuals). The accompanying transcriptome study of the ECs identified 43 genes that were significantly increased in expression (≥1.7 fold) after co-incubation with malaria patient plasma, including cxcl5 and angptl4. Further bioinformatic analyses revealed that biological processes such as cell migration, cell proliferation and tube development were particularly affected in these ECs. It can thus be postulated that not only the cytoadhesion of IEs, but also molecules in the plasma of malaria patients exerts an influence on ECs, and that not only the immunological response but also other processes, such as angiogenesis, are altered.

In vivo two-photon-excited cellular fluorescence of melanin, NAD(P)H, and keratin enables an accurate differential diagnosis of seborrheic keratosis and pigmented cutaneous melanoma.

SIGNIFICANCE: Seborrheic keratoses (SKs) are harmless pigmented skin lesions (PSLs) that may be confused clinically not only with other benign conditions but also with cutaneous melanoma (CM). As SKs are one of the most common neoplasms in adults, the importance of their correct diagnosis is high. Misclassifying SK as malignant is not rare and leads to a high number of unnecessary biopsies. On the other hand, misdiagnosing CM as SK may have a large impact on prognosis or therapy. AIM: In the non-invasive technique of dermatofluoroscopy, the fluorophores in melanocytes and keratinocytes are excited in vivo with nanosecond laser pulses and the resulting spectrally resolved, melanin-dominated fluorescence signals are used to differentiate between pigmented benign lesions and CM. APPROACH: In this single-center, non-interventional study, 33 PSLs of 20 patients were scanned with dermatofluoroscopy in vivo. For all included cases, dermatofluoroscopic signals were compared to pathology classification. RESULTS: The characteristic spectral features of SK were identified, where the signals are dominated by keratin, NAD(P)H, and melanin. The fluorescence spectra of SKs differed substantially from those of CM: a characteristic spectrum of SK has been identified in 27 of 28 SKs. CONCLUSIONS: The high-accuracy differential diagnosis between CM and SK is possible with dermatofluoroscopy.

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.