Search

Background: PD-1-based immune checkpoint inhibition (ICI) is the major backbone of current melanoma therapy. Tumor PD-L1 expression represents one of few biomarkers predicting ICI therapy outcome. The objective of the present study was to systematically investigate whether the type of tumor tissue examined for PD-L1 expression has an impact on the correlation with ICI therapy outcome., Methods: Pre-treatment tumor tissue was collected within the prospective DeCOG cohort study ADOREG/TRIM (CA209-578; NCT05750511) between February 2014 and May 2020 from 448 consecutive patients who received PD-1-based ICI for non-resectable metastatic melanoma. The primary study endpoint was best overall response (BOR), secondary endpoints were progression-free (PFS) and overall survival (OS). All endpoints were correlated with tumor PD-L1 expression (quantified with clone 28-8; cutoff ≥5%) and stratified by tissue type., Findings: Tumor PD-L1 was determined in 95 primary tumors (PT; 36.8% positivity), 153 skin/subcutaneous (34.0% positivity), 115 lymph node (LN; 50.4% positivity), and 85 organ (40.8% positivity) metastases. Tumor PD-L1 correlated with BOR if determined in LN (OR = 0.319; 95% CI = 0.138-0.762; P = 0.010), but not in skin/subcutaneous metastases (OR = 0.656; 95% CI = 0.311-1.341; P = 0.26). PD-L1 positivity determined on LN metastases was associated with favorable survival (PFS, HR = 0.490; 95% CI = 0.310-0.775; P = 0.002; OS, HR = 0.519; 95% CI = 0.307-0.880; P = 0.014). PD-L1 positivity determined in PT (PFS, HR = 0.757; 95% CI = 0.467-1.226; P = 0.27; OS; HR = 0.528; 95% CI = 0.305-0.913; P = 0.032) was correlated with survival to a lesser extent. No relevant survival differences were detected by PD-L1 determined in skin/subcutaneous metastases (PFS, HR = 0.825; 95% CI = 0.555-1.226; P = 0.35; OS, HR = 1.083; 95% CI = 0.698-1.681; P = 0.72)., Interpretation: For PD-1-based immunotherapy in melanoma, tumor PD-L1 determined in LN metastases was stronger correlated with therapy outcome than that assessed in PT or organ metastases. PD-L1 determined in skin/subcutaneous metastases showed no outcome correlation and therefore should be used with caution for clinical decision making., Funding: Bristol-Myers Squibb (ADOREG/TRIM, NCT05750511); German Research Foundation (DFG; Clinician Scientist Program UMEA); Else Kröner-Fresenius-Stiftung (EKFS; Medical Scientist Academy UMESciA)., Competing Interests: Declaration of interests Jürgen C. Becker is receiving speaker's bureau honoraria from Amgen, Pfizer, Recordati and Sanofi, and is a paid consultant/advisory board member/DSMB member for Almirall, Boehringer Ingelheim, InProTher, ICON, MerckSerono, Pfizer, 4SC, and Sanofi/Regeneron. His group received research grants from Bristol-Myers Squibb, Merck Serono, HTG, IQVIA, and Alcedis. Ralf Gutzmer reported Personal Honoraria from Roche, BMS, MSD, Novartis, Amgen, Merck Serono, Almirall, SUN, Sanofi, Pierre-Fabre; Consultant or Advisory Role (personal) for BMS, Roche, Novartis, Almirall, MSD, Amgen, SUN, Sanofi, Pierre-Fabre, 4SC, Immunocore; Research Funding (to institution) from Novartis, Pfizer, Amgen, Merck-Serono, SUN, KyowaKirin, Almirall; and Travel, Accommodations, Expenses from SUN, Pierre-Fabre, Boehringer-Ingelheim; outside the submitted work. Rudolf Herbst is employee of Helios Klinikum Erfurt GmbH. Joachim Klode reported grants and or personal fees from Novartis, LaVision Bio Tec and Sastomed. Sophia Kreft has received honoraria from Sun Pharma and reports travel support from Sanofi Genzyme. Frederik Krefting received travel support for participation in congresses and/or (speaker) honoraria from Novartis, Almirall and Boehringer Ingelheim outside the submitted work. Elisabeth Livingstone received honoraria from Novartis, Medac, Bristol Myers Squibb, Sanofi, Sun Pharma, and Pierre Fabre, reports consulting/advisory roles with Bristol Myers Squibb, Pierre Fabre and Novartis; and received travel/accommodations/expenses from Pierre Fabre, Bristol Myers Squibb, Medac, and Sun Pharma. Georg Lodde received travel support from Sun Pharma. Friedegund Meier has received travel support or/and speaker's fees or/and advisor's honoraria by Novartis, Roche, BMS, MSD, Pierre Fabre, Sanofi and Immunocore and research funding from Novartis and Roche. Peter Mohr declares research support from Bristol Myers Squibb, Merck Sharp & Dohme and Novartis; speakers and advisory board honoraria from Bristol Myers Squibb, Beiersdorf, Merck Sharp & Dohme, Pierre Fabre, Sun Pharma, Immunocore, Sanofi and Novartis, and travel support from Bristol Myers Squibb, Merck Sharp & Dohme, Sanofi, Sun Pharma, and Pierre Fabre, outside the submitted work. Claudia Pföhler received honoraria (speaker honoraria or honoraria as a consultant) and travel support from Novartis, BMS, MSD, Merck Serono, MSD, Celgene, AbbVie, Sunpharma, Pierre Fabre, UCB, Nutricia Milupa, Janssen and LEO, outside the submitted work. Jan-Malte Placke served as consultant and/or has received honoraria from Bristol-Myers Squibb, Novartis, Sanofi and received travel support from Bristol-Myers Squibb, Novartis, Pierre Fabre and Therakos. Alexander Roesch reported grants from Novartis, Bristol Myers Squibb, and Adtec; personal fees from Merck Sharp & Dohme; and nonfinancial support from Amgen, Roche, Merck Sharp & Dohme, Novartis, Bristol Myers Squibb, and Teva. Dirk Schadendorf reports partial financial support from Bristol Myers Squibb for the conduct of this study and drug supply (nivolumab and ipilimumab) support; grants (or contracts) from Amgen, Array/Pfizer, Bristol-Myers Squibb, MSD, Novartis and Roche; consulting fees from 4SC, Amgen, Array Biopharma, AstraZeneca, Bristol-Myers Squibb, Daiichi Sankyo, Haystick, Immunocore, InFlarX, Innocent, LabCorp, Merck Serono, MSD, Nektar, NeraCare, Novartis, OncoSec, Pfizer, Philogen, Pierre Fabre, Replimune, Roche, Sandoz, Sanofi/Regeneron, Sun Pharma; honoraria from Bristol-Myers Squibb, MSD/Merck, Merck Serono, Novartis, Roche, Sanofi and Sun Pharma; support for attendings meetings or travel support from Bristol-Myers Squibb, MSD, Merck Serono, Novartis, Pierre Fabre and Sanofi; participation on drug safety monitoring or advisory boards for 4SC, Amgen, Array Biopharma, AstraZeneca, Bristol-Myers Squibb, Daiichi Sankyo, Immunocore, InFlarX, Merck Serono, MSD, Nektar, NeraCare, Novartis, OncoSec, Pfizer, Philogen, Pierre Fabre, Replimune, Roche, Sandoz, Sanofi/Regeneron and SunPharma; leadership roles for DeCOG, German Cancer Society, Hiege-Stiftung, Deutsche Hautkrebsstiftung, NVKH e.V. and EuMelaReg. Patrick Terheyden has received honoraria from Bristol Myers Squibb, Novartis, Merck Sharp & Dohme, Pierre Fabre, CureVac, Merck Serono, Sanofi, Roche, Kyowa Kirin and Biofrontera and travel support from Bristol-Myers Squibb and Pierre Fabre. Selma Ugurel declares research support from Bristol Myers Squibb and Merck Serono; speakers and advisory board honoraria from Bristol Myers Squibb, Merck Sharp & Dohme, Merck Serono, and Novartis, and travel support from Bristol Myers Squibb, Merck Sharp & Dohme, and Pierre Fabre. Jens Ulrich received honoraria (speaker honoraria or honoraria as a consultant) and travel support from Bristol-Myers Squibb, Kyowa Kirin, Merck Sharp & Dohme, Novartis, Pfizer, Pierre Fabre, Roche, Sanofi/Regeneron, Sunpharma outside the submitted work. Jochen Utikal is on the advisory board or has received honoraria and travel support from Amgen, Bristol Myers Squibb, GSK, Immunocore, LeoPharma, Merck Sharp and Dohme, Novartis, Pierre Fabre, Roche, Sanofi outside the submitted work. Michael Weichenthal received grants from Bristol-Myers Squibb and Merck Sharp & Dohme, consulting fees from Merck Sharp & Dohme, Immunocore and Novartis, lecture honoraria from Bristol-Myers Squibb and Merck Sharp & Dohme and Pierre-Fabre, and advisory board honoraria from Merck Sharp & Dohme. Julia Welzel received travel grants from Bristol-Myers Squibb and Almriall as well as lecture honoraria from Bristol-Myers Squibb, Merck Sharp & Dohme, Novartis and Almirall. Lisa Zimmer declares speakers and advisory board honoraria from Bristol-Myers Squibb, Merck Sharp & Dohme, Novartis, Pierre Fabre, Sanofi, Sunpharma, research support from Novartis and travel support from Merck Sharp & Dohme, Bristol-Myers Squibb, Pierre Fabre, Sanofi, Sunpharma and Novartis; outside the submitted work. The other authors did not report conflicts of interest., (Copyright © 2023 The Author(s). Published by Elsevier B.V. All rights reserved.)

Introduction: Many cancer guidelines include sentinel lymph node (SLN) staging to identify microscopic metastatic disease. Current SLN analysis of melanoma patients is effective but has the substantial drawback that only a small representative portion of the node is sampled, whereas most of the tissue is discarded. This might explain the high clinical false-negative rate of current SLN diagnosis in melanoma. Furthermore, the quantitative assessment of metastatic load and microanatomical localisation might yield prognosis with higher precision. Thus, methods to analyse entire SLNs with cellular resolution apart from tedious sequential physical sectioning are required., Patients and Methods: Eleven melanoma patients eligible to undergo SLN biopsy were included in this prospective study. SLNs were fixed, optically cleared, whole-mount stained and imaged using light sheet fluorescence microscopy (LSFM). Subsequently, compatible and unbiased gold standard histopathological assessment allowed regular patient staging. This enabled intrasample comparison of LSFM and histological findings. In addition, the development of an algorithm, RAYhance, enabled easy-to-handle display of LSFM data in a browsable histologic slide-like fashion., Results: We comprehensively quantify total tumour volume while simultaneously visualising cellular and anatomical hallmarks of the associated SLN architecture. In a first-in-human study of 21 SLN of melanoma patients, LSFM not only confirmed all metastases identified by routine histopathological assessment but also additionally revealed metastases not detected by routine histology alone. This already led to additional therapeutic options for one patient., Conclusion: Our three-dimensional digital pathology approach can increase sensitivity and accuracy of SLN metastasis detection and potentially alleviate the need for conventional histopathological assessment in the future. GERMAN CLINICAL TRIALS REGISTER: (DRKS00015737)., (Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Introduction: The coronavirus disease 2019 (COVID-19) pandemic has changed the lives of people around the world. Fortunately, sufficient vaccines are now available. Local reactions with ipsilateral lymphadenopathy are among the most common side effects. We investigated the impact of lymphadenopathy after COVID-19 vaccination on the value of ultrasound in tumour patients., Patients and Methods: Patients with melanoma or Merkel cell carcinoma were included who underwent lymph node excision and received COVID-19 vaccination within 6 weeks before surgery. The consistency of the preoperative ultrasound findings with the histopathologic findings was investigated., Results: Eight patients were included (two Merkel cell carcinoma and six melanoma patients) who underwent lymph node excision between 16th April 2021 and 19th May 2021 and had previously received COVID-19 vaccination. In three of the eight patients (one Merkel cell carcinoma and two melanoma patients), lymph node metastases were erroneously diagnosed preoperatively during tumour follow-up with physical examination, ultrasound, and or fluorodeoxyglucose (FDG)-positron emission tomography (PET)/computed tomography (CT). In these three patients, the suspected lymph node metastases were located in the left axilla after COVID-19 vaccination in the left upper arm, which resulted in selective lymph node removal in two patients and complete lymphadenectomy in one patient., Conclusion: COVID-19 vaccine-associated lymphadenopathy is expected to be observed much more frequently in the near future because of increasing vaccination rates. This cause of lymphadenopathy, which may in ultrasound as well as in FDG PET/CT resemble lymph node metastases, must be considered, especially in oncologic patients undergoing tumour follow-up. In addition, COVID-19 vaccination should be given as far away as possible from an underlying primary on the contralateral side to avoid oncologic misdiagnosis followed by malpractice., Competing Interests: Conflict of interest statement J.M.P. served as consultant and/or has received honoraria from Bristol-Myers Squibb and Novartis and has received travel support from Bristol-Myers Squibb, Novartis, and Therakos. J.K. reported grants and or personal fees from Novartis, LaVision Bio Tec, and SastoMed. A.R. reported grants from Novartis, Bristol Myers Squibb, and ADTEC; personal fees from Merck Sharp & Dohme; and nonfinancial support from Amgen, Roche, Merck Sharp & Dohme, Novartis, Bristol Myers Squibb, and Teva. D.S. received grants and other support from Bristol-Myers Squibb, personal fees from Bristol-Myers Squibb during the conduct of the study; personal fees from Amgen; personal fees from Boehringer Ingelheim; personal fees from InFlarX; personal fees and other support from Roche; grants, personal fees, and other support from Novartis; personal fees from Incyte; personal fees and other support from Regeneron; personal fees from 4SC; personal fees from Sanofi; personal fees from NeraCare; personal fees from Pierre-Fabre; personal fees and other support from Merck-EMD; personal fees from Pfizer; personal fees and other support from Philogen; personal fees from Array; and personal fees and other support from MSD Sharp & Dohme, outside the submitted work. H.R. is on the advisory board of Bristol-Myers Squibb, received honoraria from Roche and Bristol-Myers Squibb, received travel support from Philips, Roche, and Bristol-Myers Squibb, received grants from Bristol-Myers Squibb, and holds shares of Bayer. I.S. and E.H. declared that they have no conflicts of interest with respect to the authorship or the publication of this article., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

Aim: Sentinel lymph node status is a central prognostic factor for melanomas. However, the surgical excision involves some risks for affected patients. In this study, we therefore aimed to develop a digital biomarker that can predict lymph node metastasis non-invasively from digitised H&E slides of primary melanoma tumours., Methods: A total of 415 H&E slides from primary melanoma tumours with known sentinel node (SN) status from three German university hospitals and one private pathological practice were digitised (150 SN positive/265 SN negative). Two hundred ninety-one slides were used to train artificial neural networks (ANNs). The remaining 124 slides were used to test the ability of the ANNs to predict sentinel status. ANNs were trained and/or tested on data sets that were matched or not matched between SN-positive and SN-negative cases for patient age, ulceration, and tumour thickness, factors that are known to correlate with lymph node status., Results: The best accuracy was achieved by an ANN that was trained and tested on unmatched cases (61.8% ± 0.2%) area under the receiver operating characteristic (AUROC). In contrast, ANNs that were trained and/or tested on matched cases achieved (55.0% ± 3.5%) AUROC or less., Conclusion: Our results indicate that the image classifier can predict lymph node status to some, albeit so far not clinically relevant, extent. It may do so by mostly detecting equivalents of factors on histological slides that are already known to correlate with lymph node status. Our results provide a basis for future research with larger data cohorts., Competing Interests: Conflict of interest statement The authors declare the following financial interests/personal relationships which may be considered as potential competing interests:T.J.B. would like to disclose that he owns a health technology company (Smart Health Heidelberg GmbH, Handschuhsheimer Landstr. 9/1, 69120 Heidelberg, Germany, https://smarthealth.de), which develops mobile apps, outside the submitted work. All remaining authors have declared no conflicts of interest., (Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Background: Sentinel lymph node excision (SLNE) can be performed in tumescent local anesthesia (TLA) or general anesthesia (GA). Perioperative cortisol level changes and anxiety are common in surgical interventions and might be influenced by the type of anesthesia. In this study, we intended to determine whether the type of anesthesia impacts the patients' perioperative levels of salivary cortisol (primary outcome) and the feeling of anxiety evaluated by psychological questionnaires (secondary outcome)., Methods: All melanoma patients of age undergoing SLNE at the University Hospital Essen, Germany, could be included in the study. Exclusion criteria were patients' intake of glucocorticoids or psychotropic medication during the former 6 months, pregnancy, age under 18 years, and BMI ≥ 30 as salivary cortisol levels were reported to be significantly impacted by obesity and might confound results., Results: In total, 111 melanoma patients undergoing SLNE were included in our prospective study between May 2011 and April 2017 and could choose between TLA or GA. Salivary cortisol levels were measured three times intraoperatively, twice on the third and second preoperative day and twice on the second postoperative day. To assess anxiety, patients completed questionnaires (Hospital Anxiety and Depression Scale (HADS), State-Trait Anxiety Inventory (STAI)) perioperatively. Patients of both groups exhibited comparable baseline levels of cortisol and perioperative anxiety levels. Independent of the type of anesthesia, all patients showed significantly increasing salivary cortisol level from baseline to 30 min before surgery (T3) (TLA: t = 5.07, p < 0.001; GA: t = 3.09, p = 0.006). Post hoc independent t tests showed that the TLA group exhibited significantly higher cortisol concentrations at the beginning of surgery (T4; t = 3.29, p = 0.002) as well as 20 min after incision (T5; t = 277, p = 0.008) compared to the GA group., Conclusions: The type of anesthesia chosen for SLNE surgery significantly affects intraoperative cortisol levels in melanoma patients. Further studies are mandatory to evaluate the relevance of endogenous perioperative cortisol levels on the postoperative clinical course., Trial Registration: German Clinical Trials Register DRKS00003076, registered 1 May 2011.

The manifestation of brain metastases in patients with advanced melanoma is a common event that limits patient's survival and quality of life. The immunosuppressive properties of the brain parenchyma are very different compared to the rest of the body, making it plausible that the current success of cancer immunotherapies is specifically limited here. In melanoma brain metastases, the reciprocal interplay between immunosuppressive mediators such as indoleamine 2, 3-dioxygenase (IDO) or programmed cell death-ligand 1 (PD-L1) in the context of neoplastic transformation are far from being understood. Therefore, we analyzed the immunoreactive infiltrate (CD45, CD3, CD8, Forkhead box P3 [FoxP3], CD11c, CD23, CD123, CD68, Allograft Inflammatory factor 1[AIF-1]) and PD-L1 with respect to IDO expression and localization in melanoma brain metastases but also in matched metastases at extracranial sites to correlate intra- and interpatient data with therapy response and survival. Comparative tissue analysis identified macrophages/microglia as the major source of IDO expression in melanoma brain metastases. In contrast to the tumor infiltrating lymphocytes, melanoma cells per se exhibited low IDO expression levels paralleled by cell surface presentation of PD-L1 in intracranial metastases. Absolute numbers and pattern of IDO-expressing cells in metastases of the brain correlated with recruitment and localization of CD8 + T cells, implicating dynamic impact on the regulation of T cell function in the brain parenchyma. However, paired analysis of matched intra- and extracranial metastases identified significantly lower fractions of cytotoxic CD8 + T cells in intracranial metastases while all other immune cell populations remain unchanged. In line with the already established clinical benefit for PD-L1 expression in extracranial melanoma metastases, Kaplan-Meier analyses correlated PD-L1 expression in brain metastases with favorable outcome in advanced melanoma patients undergoing immune checkpoint therapy. In summary, our data provide new insights into the landscape of immunosuppressive factors in melanoma brain metastases that may be useful in the implication of novel therapeutic strategies for patients undergoing cancer immunotherapy., (Copyright © 2020 Herrera-Rios, Mughal, Teuber-Hanselmann, Pierscianek, Sucker, Jansen, Schimming, Klode, Reifenberger, Felsberg, Keyvani, Brors, Sure, Reifenberger, Schadendorf and Helfrich.)

Background: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports on 25-26% of discordance for classifying a benign nevus versus malignant melanoma. A recent study indicated the potential of deep learning to lower these discordances. However, the performance of deep learning in classifying histopathologic melanoma images was never compared directly to human experts. The aim of this study is to perform such a first direct comparison., Methods: A total of 695 lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi/345 melanoma). Only the haematoxylin & eosin (H&E) slides of these lesions were digitalised via a slide scanner and then randomly cropped. A total of 595 of the resulting images were used to train a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison to 11 histopathologists. Three combined McNemar tests comparing the results of the CNNs test runs in terms of sensitivity, specificity and accuracy were predefined to test for significance (p < 0.05)., Findings: The CNN achieved a mean sensitivity/specificity/accuracy of 76%/60%/68% over 11 test runs. In comparison, the 11 pathologists achieved a mean sensitivity/specificity/accuracy of 51.8%/66.5%/59.2%. Thus, the CNN was significantly (p = 0.016) superior in classifying the cropped images., Interpretation: With limited image information available, a CNN was able to outperform 11 histopathologists in the classification of histopathological melanoma images and thus shows promise to assist human melanoma diagnoses., (Copyright © 2019 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Background: Melanoma is the most dangerous type of skin cancer but is curable if detected early. Recent publications demonstrated that artificial intelligence is capable in classifying images of benign nevi and melanoma with dermatologist-level precision. However, a statistically significant improvement compared with dermatologist classification has not been reported to date., Methods: For this comparative study, 4204 biopsy-proven images of melanoma and nevi (1:1) were used for the training of a convolutional neural network (CNN). New techniques of deep learning were integrated. For the experiment, an additional 804 biopsy-proven dermoscopic images of melanoma and nevi (1:1) were randomly presented to dermatologists of nine German university hospitals, who evaluated the quality of each image and stated their recommended treatment (19,296 recommendations in total). Three McNemar's tests comparing the results of the CNN's test runs in terms of sensitivity, specificity and overall correctness were predefined as the main outcomes., Findings: The respective sensitivity and specificity of lesion classification by the dermatologists were 67.2% (95% confidence interval [CI]: 62.6%-71.7%) and 62.2% (95% CI: 57.6%-66.9%). In comparison, the trained CNN achieved a higher sensitivity of 82.3% (95% CI: 78.3%-85.7%) and a higher specificity of 77.9% (95% CI: 73.8%-81.8%). The three McNemar's tests in 2 × 2 tables all reached a significance level of p < 0.001. This significance level was sustained for both subgroups., Interpretation: For the first time, automated dermoscopic melanoma image classification was shown to be significantly superior to both junior and board-certified dermatologists (p < 0.001)., (Copyright © 2019 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Recent research revealed the superiority of artificial intelligence over dermatologists to diagnose melanoma from images. However, 30-50% of all melanomas and more than half of those in young patients evolve from initially benign lesions. Despite its high relevance for melanoma screening, neither clinicians nor computers are yet able to reliably predict a nevus' oncologic transformation. The cause of this lies in the static nature of lesion presentation in the current standard of care, both for clinicians and algorithms. The status quo makes it difficult to train algorithms (and clinicians) to precisely assess the likelihood of a benign skin lesion to transform into melanoma. In addition, it inhibits the precision of current algorithms since 'evolution' image features may not be part of their decision. The current literature reveals certain types of melanocytic nevi (i.e. 'spitzoid' or 'dysplastic' nevi) and criteria (i.e. visible vasculature) that, in general, appear to have a higher chance to transform into melanoma. However, owing to the cumulative nature of oncogenic mutations in melanoma, a more fine-grained early morphologic footprint is likely to be detectable by an algorithm. In this perspective article, the concept of melanoma prediction is further explored by the discussion of the evolution of melanoma, the concept for training of such a nevi classifier and the implications of early melanoma prediction for clinical practice. In conclusion, the authors believe that artificial intelligence trained on prospective image data could be transformative for skin cancer diagnostics by (a) predicting melanoma before it occurs (i.e. pre-in situ) and (b) further enhancing the accuracy of current melanoma classifiers. Necessary prospective images for this research are obtained via free mole-monitoring mobile apps., (Copyright © 2019 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Background: Recently, convolutional neural networks (CNNs) systematically outperformed dermatologists in distinguishing dermoscopic melanoma and nevi images. However, such a binary classification does not reflect the clinical reality of skin cancer screenings in which multiple diagnoses need to be taken into account., Methods: Using 11,444 dermoscopic images, which covered dermatologic diagnoses comprising the majority of commonly pigmented skin lesions commonly faced in skin cancer screenings, a CNN was trained through novel deep learning techniques. A test set of 300 biopsy-verified images was used to compare the classifier's performance with that of 112 dermatologists from 13 German university hospitals. The primary end-point was the correct classification of the different lesions into benign and malignant. The secondary end-point was the correct classification of the images into one of the five diagnostic categories., Findings: Sensitivity and specificity of dermatologists for the primary end-point were 74.4% (95% confidence interval [CI]: 67.0-81.8%) and 59.8% (95% CI: 49.8-69.8%), respectively. At equal sensitivity, the algorithm achieved a specificity of 91.3% (95% CI: 85.5-97.1%). For the secondary end-point, the mean sensitivity and specificity of the dermatologists were at 56.5% (95% CI: 42.8-70.2%) and 89.2% (95% CI: 85.0-93.3%), respectively. At equal sensitivity, the algorithm achieved a specificity of 98.8%. Two-sided McNemar tests revealed significance for the primary end-point (p < 0.001). For the secondary end-point, outperformance (p < 0.001) was achieved except for basal cell carcinoma (on-par performance)., Interpretation: Our findings show that automated classification of dermoscopic melanoma and nevi images is extendable to a multiclass classification problem, thus better reflecting clinical differential diagnoses, while still outperforming dermatologists at a significant level (p < 0.001)., (Copyright © 2019 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Importance: The metastatic status of sentinel lymph nodes (SLNs) is the most relevant prognostic factor in breast cancer, melanoma, and other tumors. The conventional standard to label SLNs is lymphoscintigraphy with technetium Tc 99m. A worldwide shortage and known disadvantages of Tc 99m have intensified efforts to establish alternative, nonradioactive imaging techniques., Objective: To assess a new nonradioactive method using multispectral optoacoustic tomographic (MSOT) imaging in comparison with conventional lymphoscintigraphic imaging for SLN biopsy (SLNB) in melanoma., Design, Setting, and Participants: Analysis of a cross-sectional study was conducted at the University Hospital-Essen, Skin Cancer Center, Essen, Germany. Between June 2, 2014, and February 22, 2019, 83 patients underwent SLNB with an additional preoperative indocyanine green (ICG) application. Sentinel lymph node basins were preoperatively identified by MSOT imaging, and ICG-labeled SLNs were intraoperatively detected using a near-infrared camera. The surgeons were blinded to the lymphoscintigraphic imaging results in the beginning of the SLNB. Use of a γ probe was restricted until the SLNB procedure was attempted by the nonradioactive method., Main Outcomes and Measures: Concordance of SLN basins and SLNs identified by MSOT imaging plus near-infrared camera vs lymphoscintigraphic imaging plus single-photon emission computed tomographic or computed tomographic imaging was assessed., Results: Of the 83 patients (mean [SD] age, 54.61 [17.53] years), 47 (56.6%) were men. In 83 surgical procedures, 165 SLNs were excised. The concordance rate of ICG-labeled and Tc 99m-marked detected SLN basins was 94.6% (n = 106 of 112). Intraoperatively, 159 SLNs were detected using a near-infrared camera and 165 were detected by a γ probe, resulting in a concordance rate of 96.4%. Multispectral optoacoustic tomographic imaging visualized SLNs in all anatomic regions with high penetration depth (5 cm)., Conclusions and Relevance: The findings of this study suggest that nonradioactive SLN detection via MSOT imaging allows identification of SLNs at a frequency equivalent to that of the current radiotracer conventional standard. Multispectral optoacoustic tomographic imaging appears to be a viable nonradioactive alternative to detect SLNs in malignant tumors.

Background: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports 25-26% of discordance for classifying a benign nevus versus malignant melanoma. Deep learning was successfully implemented to enhance the precision of lung and breast cancer diagnoses. The aim of this study is to illustrate the potential of deep learning to assist human assessment for a histopathologic melanoma diagnosis., Methods: Six hundred ninety-five lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi and 345 melanomas). Only the haematoxylin and eosin stained (H&E) slides of these lesions were digitalised using a slide scanner and then randomly cropped. Five hundred ninety-five of the resulting images were used for the training of a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison with the original class labels., Findings: The total discordance with the histopathologist was 18% for melanoma (95% confidence interval [CI]: 7.4-28.6%), 20% for nevi (95% CI: 8.9-31.1%) and 19% for the full set of images (95% CI: 11.3-26.7%)., Interpretation: Even in the worst case, the discordance of the CNN was about the same compared with the discordance between human pathologists as reported in the literature. Despite the vastly reduced amount of data, time necessary for diagnosis and cost compared with the pathologist, our CNN archived on-par performance. Conclusively, CNNs indicate to be a valuable tool to assist human melanoma diagnoses., (Copyright © 2019 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Background: Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy., Methods: We used methods from enhanced deep learning to train a convolutional neural network (CNN) with 12,378 open-source dermoscopic images. We used 100 images to compare the performance of the CNN to that of the 157 dermatologists from 12 university hospitals in Germany. Outperformance of dermatologists by the deep neural network was measured in terms of sensitivity, specificity and receiver operating characteristics., Findings: The mean sensitivity and specificity achieved by the dermatologists with dermoscopic images was 74.1% (range 40.0%-100%) and 60% (range 21.3%-91.3%), respectively. At a mean sensitivity of 74.1%, the CNN exhibited a mean specificity of 86.5% (range 70.8%-91.3%). At a mean specificity of 60%, a mean sensitivity of 87.5% (range 80%-95%) was achieved by our algorithm. Among the dermatologists, the chief physicians showed the highest mean specificity of 69.2% at a mean sensitivity of 73.3%. With the same high specificity of 69.2%, the CNN had a mean sensitivity of 84.5%., Interpretation: A CNN trained by open-source images exclusively outperformed 136 of the 157 dermatologists and all the different levels of experience (from junior to chief physicians) in terms of average specificity and sensitivity., (Copyright © 2019 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Background: Several recent publications have demonstrated the use of convolutional neural networks to classify images of melanoma at par with board-certified dermatologists. However, the non-availability of a public human benchmark restricts the comparability of the performance of these algorithms and thereby the technical progress in this field., Methods: An electronic questionnaire was sent to dermatologists at 12 German university hospitals. Each questionnaire comprised 100 dermoscopic and 100 clinical images (80 nevi images and 20 biopsy-verified melanoma images, each), all open-source. The questionnaire recorded factors such as the years of experience in dermatology, performed skin checks, age, sex and the rank within the university hospital or the status as resident physician. For each image, the dermatologists were asked to provide a management decision (treat/biopsy lesion or reassure the patient). Main outcome measures were sensitivity, specificity and the receiver operating characteristics (ROC)., Results: Total 157 dermatologists assessed all 100 dermoscopic images with an overall sensitivity of 74.1%, specificity of 60.0% and an ROC of 0.67 (range = 0.538-0.769); 145 dermatologists assessed all 100 clinical images with an overall sensitivity of 89.4%, specificity of 64.4% and an ROC of 0.769 (range = 0.613-0.9). Results between test-sets were significantly different (P < 0.05) confirming the need for a standardised benchmark., Conclusions: We present the first public melanoma classification benchmark for both non-dermoscopic and dermoscopic images for comparing artificial intelligence algorithms with diagnostic performance of 145 or 157 dermatologists. Melanoma Classification Benchmark should be considered as a reference standard for white-skinned Western populations in the field of binary algorithmic melanoma classification., (Copyright © 2019 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Background: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists., Methods: We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists. Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics., Findings: The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4% (range: 55.0%-100%) and 64.4% (range: 22.5%-92.5%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2% (range 47.5%-86.25%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8% at a mean specificity of 57.7%. With the same high sensitivity of 92.8%, the CNN had a mean specificity of 61.1%., Interpretation: For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks., (Copyright © 2019 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Background: Melanoma has become a growing interdisciplinary problem in public health worldwide. According to the World Health Organization, the incidence of melanoma is increasing faster than any other cancer in the world. Because melanoma metastasizes early into the regional lymph nodes, sentinel lymph node excision (SLNE) is included in the current American Joint Committee of Cancer guidelines. However SLNE of melanoma has a high false-negative rate of up to 44%., Methods: The gold standard for detection and extirpation of the sentinel lymph node is preoperative lymphoscintigraphy. SPECT/CT provides complementary information: the advantages include accurate anatomical localization, identification of false positives, reduction in the number of false negatives, and alteration of the surgical approach. Therefore, sentinel lymph node-SPECT/CT provides valuable information before sentinel lymph node excision and advocates its use in melanoma. We present a multicenter, unblinded superiority randomized controlled trial to compare SPECT/CT-aided SLNE versus standard SLNE in melanoma patients., Discussion: The primary efficacy endpoint is distant metastasis-free survival. Secondary endpoints comprise overall survival, disease-free survival, rate of local relapses within the follow-up period (false-negative rate of sentinel lymph node), number of positive sentinel lymph nodes (sensitivity, false-positive rate), complication rate, quality of life, quality-adjusted life years, inpatient days, and overall costs during hospital stays., Trial Registration: ClinicalTrials.gov, NCT03683550 . Registered on 20 September 2018.

Purpose: To compare the sensitivity and specificity of 18F-fluordesoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT), 18F-FDG PET/magnetic resonance (18F-FDG PET/MR) and 18F-FDG PET/MR including diffusion weighted imaging (DWI) in the detection of sentinel lymph node metastases in patients suffering from malignant melanoma., Material & Methods: Fifty-two patients with malignant melanoma (female: n = 30, male: n = 22, mean age 50.5 ± 16.0 years, mean tumor thickness 2.28 ± 1.97 mm) who underwent 18F-FDG PET/CT and subsequent PET/MR & DWI for distant metastasis staging were included in this retrospective study. After hybrid imaging, lymphoscintigraphy including single photon emission computed tomography/CT (SPECT/CT) was performed to identify the sentinel lymph node prior to sentinel lymph node biopsy (SLNB). In a total of 87 sentinel lymph nodes in 64 lymph node basins visible on SPECT/CT, 17 lymph node metastases were detected by histopathology. In separate sessions PET/CT, PET/MR, and PET/MR & DWI were assessed for sentinel lymph node metastases by two independent readers. Discrepant results were resolved in a consensus reading. Sensitivities, specificities, positive predictive values and negative predictive values were calculated with histopathology following SPECT/CT guided SLNB as a reference standard., Results: Compared with histopathology, lymph nodes were true positive in three cases, true negative in 65 cases, false positive in three cases and false negative in 14 cases in PET/CT. PET/MR was true positive in four cases, true negative in 63 cases, false positive in two cases and false negative in 13 cases. Hence, we observed a sensitivity, specificity, positive predictive value and negative predictive value of 17.7, 95.6, 50.0 and 82.3% for PET/CT and 23.5, 96.9, 66.7 and 82.3% for PET/MR. In DWI, 56 sentinel lymph node basins could be analyzed. Here, the additional analysis of DWI led to two additional false positive findings, while the number of true positive findings could not be increased., Conclusion: In conclusion, integrated 18F-FDG PET/MR does not reliably differentiate N-positive from N-negative melanoma patients. Additional DWI does not increase the sensitivity of 18F-FDG PET/MR. Hence, sentinel lymph node biopsy cannot be replaced by 18F-FDG-PE/MR or 18F-FDG-PET/CT.

Background: Around 90% of melanomas are caused by exposure to ultraviolet (UV) radiation and are therefore eminently preventable. Tanning behavior is mostly initiated in early adolescence, often with the belief that it increases attractiveness; the problems related to malignant melanoma and other skin cancers are too far in the future to fathom. Given the substantial amount of time children and adolescents spend in schools, as well as with their mobile phones, addressing melanoma prevention via both of these ways is crucial. However, no school-based intervention using mobile apps has been evaluated to date. We recently released a photoaging mobile app, in which a selfie is altered to predict future appearance dependent on UV protection behavior and skin type., Objective: In this pilot study, we aimed to use mobile phone technology to improve school-based melanoma prevention and measure its preliminary success in different subgroups of students with regard to their UV protection behavior, Fitzpatrick skin type and age., Methods: We implemented a free photoaging mobile phone app (Sunface) in 2 German secondary schools via a method called mirroring. We "mirrored" the students' altered 3-dimensional (3D) selfies reacting to touch on mobile phones or tablets via a projector in front of their whole grade. Using an anonymous questionnaire capturing sociodemographic data as well as risk factors for melanoma we then measured their perceptions of the intervention on a 5-point Likert scale among 205 students of both sexes aged 13-19 years (median 15 years)., Results: We measured more than 60% agreement in both items that measured motivation to reduce UV exposure and only 12.5% disagreement: 126 (63.0%) agreed or strongly agreed that their 3D selfie motivated them to avoid using a tanning bed, and 124 (61.7%) to increase use of sun protection. However, only 25 (12.5%) disagreed with both items. The perceived effect on motivation was increased in participants with Fitzpatrick skin types 1-2 in both tanning bed avoidance (n=74, 71.8% agreement in skin types 1-2 vs n=50, 53.8% agreement in skin types 3-6) and increased use of sun protection (n=70, 68.0% agreement in skin types 1-2 vs n=52, 55.3% agreement in skin types 3-6), and also positively correlated with higher age., Conclusions: We present a novel way of integrating photoaging in school-based melanoma prevention that affects the students' peer group, considers the predictors of UV exposure in accordance with the theory of planned behavior, and is particularly effective in changing behavioral predictors in fair-skinned adolescents (Fitzpatrick skin types 1-2). Further research is required to evaluate the intervention's prospective effects on adolescents of various cultural backgrounds., (©Titus Josef Brinker, Christian Martin Brieske, Christoph Matthias Schaefer, Fabian Buslaff, Martina Gatzka, Maximilian Philip Petri, Wiebke Sondermann, Dirk Schadendorf, Ingo Stoffels, Joachim Klode. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 08.09.2017.)

Acral melanoma has been reported to be associated with poorer outcomes than melanoma occurring on other cutaneous sites. It has been suggested that part of this disparity in outcomes may be related to delay in diagnosis. Therefore, we have analyzed the rate of misdiagnoses in patients with melanoma located on the foot and have characterized the influence on the clinical course and survival of the patients. A prospective, computerized melanoma database at the Skin Cancer Center of the University Hospital Essen, Germany was used to identify patients with histologically confirmed melanoma located on the foot between 2002 and July 2013 for subsequent analysis. A cohort of 151 patients diagnosed with primary melanoma located on the foot was identified. One hundred seven patients qualified for subsequent analysis. Forty-two patients were male (39.3%) and 65 (60.7%) were female; the mean age at first diagnosis was 61.6 years (median 66 years). The youngest patient was 19 years, the oldest 88 years old.Of the 107 patients analyzed, 32 (30%) were initially misdiagnosed. Misdiagnoses included chronic wounds, nevi, hematoma, fungal infections, warts, and paronychia. Misdiagnosis caused a median delay in diagnosis of 9 months. The 5-year disease-free survival rate (47.8% vs 72.7%) and the 5-year overall survival rate (63.5% vs 88.4%) were statistically significant lower in the misdiagnosis cohort.The awareness of potentially overlooked melanoma located on the foot has to increase among physicians.To improve early detection and, thus, the prognosis of patients with melanoma located on the foot, taking a biopsy from any suspicious lesion should be taken into consideration as soon as possible., Competing Interests: WS has received honoraria from Roche and Novartis and travel support from Bristol-Myers Squibb, Novartis, and MSD. LZ served as consultant and received speaker's honoraria and meeting support from Roche, Bristol-Myers Squibb, MSD, Novartis, Merck, and GlaxoSmithKline. DS reports grant support and study fees to his institution from MSD and BMS; personal fees for serving as an advisory board, steering committee, and speaker's bureau member and for travel and hotel support from GlaxoSmithKline, Novartis, BMS, MSD, Merck-Serrono, Novartis, and Roche-Genentech; and personal fees for advisory board and speaker's bureau membership from Amgen and Boehringer Ingelheim. DS is the unpaid chairman of Dermatologic Cooperative Oncology Group (DeCOG) and is an unpaid member of guideline panel melanoma. AR received travel grants and honoraria from Roche, TEVA, GlaxoSmithKline, Bristol-Myers Squibb and travel and research grants from Novartis. JD and JK declare that they have no competing interests.

Sentinel lymph node (SLN) excision is included in various cancer guidelines to identify microscopic metastatic disease. Although effective, SLN excision is an invasive procedure requiring radioactive tracing. Novel imaging approaches assessing SLN metastatic status could improve or replace conventional lymph node excision protocols. In our first-in-human study, we used noninvasive multispectral optoacoustic tomography (MSOT) to image SLNs ex vivo and in vivo in patients with melanoma, to determine metastatic status. MSOT significantly improved the tumor metastasis detection rate in excised SLN (506 SLNs from 214 melanoma patients) compared with the conventional EORTC (European Organisation for Research and Treatment of Cancer) Melanoma Group protocol (22.9% versus 14.2%). MSOT combined with the near-infrared fluorophore indocyanine green reliably visualized SLNs in vivo in 20 patients, up to 5-cm penetration and with 100% concordance with (99m)Tc-marked SLN lymphoscintigraphy. MSOT identified cancer-free SLNs in vivo and ex vivo without a single false negative (189 total lymph nodes), with 100% sensitivity and 48 to 62% specificity. Our findings indicate that a noninvasive, nonradioactive MSOT-based approach can identify and determine SLN status and confidently rule out the presence of metastasis. The study further demonstrates that optoacoustic imaging strategies can improve the identification of SLN metastasis as an alternative to current invasive SLN excision protocols., (Copyright © 2015, American Association for the Advancement of Science.)

Importance: The metastatic status of regional lymph nodes is the most relevant prognostic factor in breast cancer, melanoma, and other solid organ tumors with a lymphatic spread. The current gold standard for detection and targeted excision of the sentinel lymph node is preoperative lymphoscintigraphy with technetium Tc 99m. Because of the worldwide shortage of technetium Tc 99m, physicians are looking for nonradioactive dyes for sentinel lymph node labeling. Based on several retrospective studies, the fluorescent dye indocyanine green is considered a possible alternative to technetium Tc 99m., Objective: To analyze the feasibility and clinical benefit of intraoperative near infrared fluorescence sentinel lymph node excision (SLNE) compared with standard technetium Tc 99m-guided SLNE using malignant melanoma in which SLNE is firmly established., Design, Setting, and Participants: Analysis of a prospective clinical trial at the Skin Cancer Center, University Hospital Essen. Eighty patients with malignant melanoma on the trunk or extremities (upper and lower) who were scheduled to undergo SLNE were included in this study from January 1, 2013, to June 27, 2014., Main Outcomes and Measures: Concordance of preoperative and intraoperative sentinel lymph node detection rates., Results: During the study period, 80 patients were operated on with an additional intraoperative application of a near infrared fluorescent dye. In these 80 surgical procedures, 147 SLNs were excised. Detection of a technetium Tc 99m-marked SLN before surgery was possible in all cases. Intraoperative visualization of the SLN by indocyanine green before skin incision was successful in only 17 of 80 patients (21%). The number of SLNs identified using the near infrared fluorescence technique in the operative site after skin incision and initial tissue preparation was 141 of 147 (96%)., Conclusions and Relevance: Among patients in whom the lymph node basin cannot be predicted correctly (eg, in cutaneous melanoma on the trunk), the use of indocyanine green for SLN detection is severely limited compared with SLNE using standard technique guided by technetium Tc 99m. Therefore, SLNE with the use of radiocolloid, followed if possible by single-photon emission computed tomography, remains the gold standard., Trial Registration: German Clinical Trials Register identifier DRKS00004619.

CEACAM1 is a widely expressed multifunctional cell-cell adhesion protein reported to serve as a poor prognosis marker in melanoma patients. In this study, we examine the functional and clinical contributions of the four splice isoforms of CEACAM1. Specifically, we present in vitro and in vivo evidence that they affect melanoma progression and immune surveillance in a negative or positive manner that is isoform specific in action. In contrast with isoforms CEACAM1-4S and CEACAM1-4L, expression of isoforms CEACAM1-3S and CEACAM1-3L is induced during disease progression shown to correlate with clinical stage. Unexpectedly, overall survival was prolonged in patients with advanced melanomas expressing CEACAM1-3S. The favorable effects of CEACAM1-3S related to enhanced immunogenicity, which was mediated by cell surface upregulation of NKG2D receptor ligands, thereby sensitizing melanoma cells to lysis by natural killer cells. Conversely, CEACAM1-4L downregulated cell surface levels of the NKG2D ligands MICA and ULBP2 by enhanced shedding, thereby promoting malignant character. Overall, our results define the splice isoform-specific immunomodulatory and cell biologic functions of CEACAM1 in melanoma pathogenesis., (©2015 American Association for Cancer Research.)

Purpose: Malignant melanoma has become a major growing interdisciplinary problem in public health worldwide. Sentinel lymph node excision (SLNE) in conjunction with preoperative SPECT/CT is considered the most sensitive and specific staging test for the detection of micrometastatic melanoma in regional lymph nodes. Among patients with clinically lymph node-negative melanoma, the use of SPECT/CT-aided SLNE compared with SLNE alone has been found to be associated with a higher frequency of metastatic involvement and a higher rate of disease-free survival. The aim of this study was to analyse the cost-effectiveness of SLNE with preoperative SPECT/CT for detecting sentinel lymph nodes versus that of standard SLNE with preoperative lymphoscintigraphy from a single-institution database., Methods: Cost-effectiveness analysis of two surgical approaches for SLNE for malignant melanoma at the University Hospital Essen, Skin Cancer Center in Essen, Germany. Between March 2003 and April 2011 464 patients eligible for SLNE were identified . Of these patients, 403 with clinically negative lymph nodes who underwent SLNE with or without preoperative SPECT/CT qualified for subsequent analysis., Results: Between March 2003 and October 2008, 254 patients were operated upon with the standard technique. From November 2008, 149 patients underwent the SPECT/CT technique. Cost analysis showed a mean cost saving of 710.50 when SPECT/CT was added to preoperative imaging. This was achieved by a reduction in operative time (median, Q1;Q3, 40 min, 40;50 min, vs. 45 min, 35;60 min; p = 0.002), hospital stay duration (5 days, 3;8 days, vs. 8 days, 4.5;14.5 days; p < 0.001) and more frequent use of local anaesthesia (90.6 % vs. 70.5 %; p < 0.001). The median cost of SLNE using SPECT/CT was 1,619.7 (Q1;Q3 1,317.0;2,603.4) and of SLNE without SPECT/CT was 2,330.2 ( 1,468.3;4,058.1; p < 0.001), a cost saving of 30.5 %., Conclusion: In patients with cutaneous melanoma, the use of preoperative SPECT/CT-aided SLNE compared with standard SLNE was associated not only with higher detection of metastatic involvement but also with a significant cost reduction.

Context: Malignant melanoma has become an increasing interdisciplinary public health challenge worldwide. Sentinel lymph node excision (SLNE) is considered the most sensitive and specific staging test for the detection of micrometastatic melanoma in regional lymph nodes., Objective: To compare metastatic node detection and disease-free survival using single-photon emission computed tomography/computed tomography (SPECT/CT)-aided SLNE vs standard SLNE in patients with melanoma., Design, Setting, and Patients: A prospective, computerized melanoma patient database at the University Hospital Essen, Skin Cancer Center, Essen, Germany, was used to identify a cohort of 464 patients eligible for SLNE between March 2003 and April 2011. A total of 403 patients with clinically negative lymph nodes, who underwent SLNE with or without preoperative SPECT/CT, qualified for subsequent analysis., Main Outcome Measures: Metastatic node detection and disease-free survival., Results: Between March 2003 and October 2008, 254 patients underwent the standard SLNE technique. After November 2008, 149 patients underwent the SPECT/CT technique. Patients who did not receive SNLE in both intervals (46/300 [15.34%] for standard cohort vs 15/164 [9.15%] for SPECT/CT cohort; P = .06) did not differ in either age (difference, 69.20 years; 95% CI, 62.84-72.07 years; P = .38), tumor depth (difference, 2.90 mm; 95% CI, 2.87-4.54 mm; P = .54), or ulceration of the primary tumor (difference, -8.00%; 95% CI, -35.74% to 19.81%; P = .59). However, using SPECT/CT allowed SLNE in the head and neck area more frequently (2.0% for standard vs 23.5% for SPECT/CT; difference, 21.1%; 95% CI, 14.1%-28.2%; P < .001). In the SPECT/CT cohort, more sentinel lymph nodes per patient were detected than in the standard cohort (2.40 vs 1.87; 95% CI, 1.93-2.18; P < .001). The number of positive sentinel lymph nodes per patient was significantly higher in the SPECT/CT cohort than in the standard cohort (0.34 vs 0.21; 95% CI, 0.21-0.31; P = .04). The local relapse rate in the SPECT/CT cohort was lower than in the standard cohort (6.8% vs 23.8%, P = .03), which prolonged 4-year disease-free survival (93.9% vs 79.2%; P = .02)., Conclusion: Among patients with clinically lymph node-negative melanoma, the use of SPECT/CT-aided SLNE compared with SLNE alone was associated with a higher frequency of metastatic involvement and a higher rate of disease-free survival.

Background: Sentinel lymph node biopsy (SLNB) for cutaneous malignancies usually carried out with radioactive nanocolloids (Tc-99m). The SLNE is controversially discussed internationally. This is especially given to the high false-negative rate up to 44 %. An alternative could be the fluorescent dye indocyanine green (ICG)., Material and Methods: We investigated the advantage of intraoperative fluorescence detection of lymphatic vessels and SLN with a Near-Infrared (NIR) camera in comparison to conventional methods using preoperative lymphoscintigraphy and SPECT/CT in 22 patients with malignant melanoma., Results: A total of 61 SLNs were removed in 22 operative procedures. In 7 SLN (10.3 %; 7/68) the histopathological assessment could demonstrate a metasta-tic involvement. 11 additional SLN (19.1 %) in 8 patients were only identified using the fluorescent labeling. Two of these additional SLN (9.1 %; 2/22) showed metastatic involvement., Conclusion: The ICG fluorescence-guided SLNB is an innovative imaging technique for dermato-oncology, reliable and providing additional information in the detection of SLN. Therefore SLNB with fluorescence-dye is an attractive option with intraoperative real-time lymphoscintigraphy to improve the detection of SLN in cutaneous malignancies and potential reduction of the false negative rate in SLN., (© The Authors • Journal compilation © Blackwell Verlag GmbH, Berlin.)

Background and Objectives: Sentinel lymph node excision (SLNE) for the detection of regional nodal metastases and staging of malignant melanoma has resulted in some controversies in international discussions. Positron emission tomography with computerized tomography (PET-CT), a noninvasive imaging procedure for the detection of regional nodal metastases, has increasingly become of interest. Our study is a direct comparison of SLNE and PET-CT in patients with early-stage malignant melanoma., Materials and Methods: We retrospectively analyzed data from 61 patients with primary malignant melanoma with a Breslow index greater than 1.0 mm., Results: Metastatic SLNs were found in 14 patients (23%); 17 metastatic lymph nodes were detected overall, only one of which was identified preoperatively using PET-CT. Thus, PET-CT showed a sensitivity of 5.9% and a negative predictive value of 78%., Conclusion: SLNE is much more sensitive than PET-CT in discovering small lymph node metastases. We consider PET-CT unsuitable for the evaluation of early regional lymphatic tumor dissemination in this patient population and recommend that it be limited to malignant melanomas of American Joint Committee on Cancer stages III and IV. We therefore recommend the routine use of SLNE for tumor staging and stratification for adjuvant therapy of patients with stage I and II malignant melanoma.

A letter to the editor is presented in response to the article "Association between sentinel lymph node excision with or without preoperative SPECT/CT and metastatic node detection and disease-free survival in melanoma," by Ingo Stoffels and colleagues in a 2012 issue, along with a response from the authors of the article on the letter.

Radiological imaging such as computed tomography (CT) is used frequently for disease staging and therapy monitoring in advanced skin cancer patients. Detected lesions of unclear dignity are a common challenge for treating physicians. The aim of this study was to assess the frequency and outcome of CT-guided biopsy (CTGB) of radiologically unclear, suspicious lesions and to depict its usefulness in different clinical settings. This retrospective monocentric study included advanced skin cancer patients (melanoma, Merkel cell carcinoma, squamous cell carcinoma, angiosarcoma, cutaneous lymphoma) with radiologically unclear lesions who underwent CTGB between 2010 and 2018. Of 59 skin cancer patients who received CTGB, 47 received CTGB to clarify radiologically suspicious lesions of unclear dignity. 32 patients had no systemic therapy (cohort A), while 15 patients received systemic treatment at CTGB (cohort B). In both cohorts, CTGB revealed skin cancer metastasis in a large proportion of patients (37.5%, 40.0%, respectively), but benign tissue showing inflammation, fibrosis or infection in an equally large percentage (37.5%, 46.7%, respectively). Additionally, a significant number of other cancer entities was found (25.0%, 13.3%, respectively). In patients receiving BRAF/MEK inhibitors, CTGB confirmed suspicious lesions as skin cancer metastasis in 83.3%, leading to treatment change. In immune checkpoint inhibitor-treated patients, skin cancer metastasis was confirmed in 11.1% of patients only, whereas benign tissue changes (inflammation/fibrosis) were found in 77.8%. Our results highlight the relevance of clarifying radiologically unclear lesions by CTGB before start or change of an anti-tumour therapy to exclude benign alterations and secondary malignancies. • Lesions of unclear dignity are frequent in imaging of skin cancer patients. • CT-guided biopsy (CTGB) can be helpful for clarification. • Frequency, outcome and clinical impact of CTGB of such lesions were assessed. • CTGB revealed >50% unexpected findings (benign findings and secondary carcinomas). • CTGB can therefore prevent unnecessary treatment initiation or discontinuation. [ABSTRACT FROM AUTHOR]

In recent studies, convolutional neural networks (CNNs) outperformed dermatologists in distinguishing dermoscopic images of melanoma and nevi. In these studies, dermatologists and artificial intelligence were considered as opponents. However, the combination of classifiers frequently yields superior results, both in machine learning and among humans. In this study, we investigated the potential benefit of combining human and artificial intelligence for skin cancer classification. Using 11,444 dermoscopic images, which were divided into five diagnostic categories, novel deep learning techniques were used to train a single CNN. Then, both 112 dermatologists of 13 German university hospitals and the trained CNN independently classified a set of 300 biopsy-verified skin lesions into those five classes. Taking into account the certainty of the decisions, the two independently determined diagnoses were combined to a new classifier with the help of a gradient boosting method. The primary end-point of the study was the correct classification of the images into five designated categories, whereas the secondary end-point was the correct classification of lesions as either benign or malignant (binary classification). Regarding the multiclass task, the combination of man and machine achieved an accuracy of 82.95%. This was 1.36% higher than the best of the two individual classifiers (81.59% achieved by the CNN). Owing to the class imbalance in the binary problem, sensitivity, but not accuracy, was examined and demonstrated to be superior (89%) to the best individual classifier (CNN with 86.1%). The specificity in the combined classifier decreased from 89.2% to 84%. However, at an equal sensitivity of 89%, the CNN achieved a specificity of only 81.5% Our findings indicate that the combination of human and artificial intelligence achieves superior results over the independent results of both of these systems. • This article describes the first experiment on combining human and artificial intelligence for the classification of images suspicious of skin cancer. • The combination achieved a superior accuracy of 82.95% (compared to 81.59%/42.94% achieved by artificial/human intelligence alone). • The combination of human and artificial intelligence indicates superiority over a separated approach. [ABSTRACT FROM AUTHOR]