Refine
Has Fulltext
- yes (14)
Is part of the Bibliography
- yes (14)
Document Type
- Journal article (14)
Language
- English (14) (remove)
Keywords
- melanoma (6)
- deep learning (4)
- artificial intelligence (3)
- CTLA-4 (2)
- Merkel cell carcinoma (2)
- PD-1 (2)
- apoptosis (2)
- immune checkpoint blockade (2)
- skin cancer (2)
- treatment resistance (2)
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).
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.
Background
Merkel cell carcinoma (MCC) is a rare and aggressive neuroendocrine cutaneous malignancy with poor prognosis. In Europe, approved systemic therapies are limited to the PD-L1 inhibitor avelumab. For avelumab-refractory patients, efficient and safe treatment options are lacking.
Methods
At three different sites in Germany, clinical and molecular data of patients with metastatic MCC being refractory to the PD-L1 inhibitor avelumab and who were later on treated with combined IPI/NIVO were retrospectively collected and evaluated.
Results
Five patients treated at three different academic sites in Germany were enrolled. Three out of five patients investigated for this report responded to combined IPI/NIVO according to RECIST 1.1. Combined immunotherapy was well tolerated without any grade II or III immune-related adverse events. Two out of three responders to IPI/NIVO received platinum-based chemotherapy in between avelumab and combined immunotherapy.
Conclusion
In this small retrospective study, we observed a high response rate and durable responses to subsequent combined immunotherapy with IPI/NIVO in avelumab-refractory metastatic MCC patients. In conclusion, our data suggest a promising activity of second- or third-line PD-1- plus CTLA-4-blockade in patients with anti-PD-L1-refractory MCC.
Merkel cell carcinoma is a rare, highly aggressive skin cancer with neuroendocrine differentiation. Immune checkpoint inhibition has significantly improved treatment outcomes in metastatic disease with response rates to programmed cell death protein 1/programmed cell death 1 ligand 1 (PD-1/PD-L1) inhibition of up to 62%. However, primary and secondary resistance to PD-1/PD-L1 inhibition remains a so far unsolved clinical challenge since effective and safe treatment options for these patients are lacking.Fourteen patients with advanced (non-resectable stage III or stage IV, Union international contre le cancer 2017) Merkel cell carcinoma with primary resistance to the PD-L1 inhibitor avelumab receiving subsequent therapy (second or later line) with ipilimumab plus nivolumab (IPI/NIVO) were identified in the prospective multicenter skin cancer registry ADOREG. Five of these 14 patients were reported previously and were included in this analysis with additional follow-up. Overall response rate, progression-free survival (PFS), overall survival (OS) and adverse events were analyzed.All 14 patients received avelumab as first-line treatment. Thereof, 12 patients had shown primary resistance with progressive disease in the first tumor assessment, while two patients had initially experienced a short-lived stabilization (stable disease). Six patients had at least one systemic treatment in between avelumab and IPI/NIVO. In total, 7 patients responded to IPI/NIVO (overall response rate 50%), and response was ongoing in 4 responders at last follow-up. After a median follow-up of 18.85 months, median PFS was 5.07 months (95% CI 2.43—not available (NA)), and median OS was not reached. PFS rates at 12 months and 24 months were 42.9% and 26.8 %, respectively. The OS rate at 36 months was 64.3%. Only 3 (21%) patients did not receive all 4 cycles of IPI/NIVO due to immune-related adverse events.In this multicenter evaluation, we observed high response rates, a durable benefit and promising OS rates after treatment with later-line combined IPI/NIVO. In conclusion, our patient cohort supports our prior findings with an encouraging activity of second-line or later-line IPI/NIVO in patients with anti-PD-L1-refractory Merkel cell carcinoma.
Approximately half of all melanoma patients harbour activating mutations in the serine/threonine kinase BRAF. This is the basis for one of the main treatment strategies for this tumor type, the targeted therapy with BRAF and MEK inhibitors. While the initial responsiveness to these drugs is high, resistance develops after several months, frequently at sites of the previously responding tumor. This indicates that tumor response is incomplete and that a certain tumor fraction survives even in drug-sensitive patients, e.g., in a therapy-induced senescence-like state. Here, we show in several melanoma cell lines that BRAF inhibition induces a secretome with stimulating effect on fibroblasts and naive melanoma cells. Several senescence-associated factors were found to be transcribed and secreted in response to BRAF or MEK inhibition, among them members of the fibroblast growth factor family. We identified the growth factor FGF1 as mediator of resilience towards BRAF inhibition, which limits the pro-apoptotic effects of the drug and activates fibroblasts to secrete HGF. FGF1 regulation was mediated by the PI3K pathway and by FRA1, a direct target gene of the MAPK pathway. When FGFR inhibitors were applied in parallel to BRAF inhibitors, resilience was broken, thus providing a rationale for combined therapeutical application.
p53 is a central tumor suppressor protein and its inhibition is believed to be a prerequisite for cancer development. In approximately 50% of all malignancies this is achieved by inactivating mutations in the p53 gene. However, in several cancer entities, including melanoma, p53 mutations are rare. It has been recently proposed that tyrosinase related protein 2 (TRP2), a protein involved in melanin synthesis, may act as suppressor of the p53 pathway in melanoma. To scrutinize this notion we analyzed p53 and TRP2 expression by immunohistochemistry in 172 melanoma tissues and did not find any correlation. Furthermore, we applied three different TRP2 shRNAs to five melanoma cell lines and could not observe a target specific effect of the TRP2 knockdown on either p53 expression nor p53 reporter gene activity. Likewise, ectopic expression of TRP2 in a TRP2 negative melanoma cell line had no impact on p53 expression. In conclusion our data suggest that p53 repression critically controlled by TRP2 is not a general event in melanoma.
Cutaneous squamous cell carcinoma (cSCC) is a common malignancy of the skin and has an overall favorable outcome, except for patients with an advanced stage of the disease. The efficacy of checkpoint inhibitors (CPI) for advanced cSCC has been demonstrated in recent clinical studies, but data from real-world cohorts and trial-ineligible cSCC patients are limited. We retrospectively investigated patients with advanced cSCC who have been treated with CPI in a first-line setting at eight German skin cancer centers registered within the multicenter registry ADOReg. Clinical outcome parameters including response, progression-free (PFS) and overall survival (OS), time-to-next-treatment (TTNT), and toxicity were analyzed and have been stratified by the individual immune status. Among 39 evaluable patients, the tumor response rate (rwTRR) was 48.6%, the median PFS was 29.0 months, and the median OS was not reached. In addition, 9 patients showed an impaired immune status due to immunosuppressive medication or hematological diseases. Our data demonstrated that CPI also evoked tumor responses among immunocompromised patients (rwTRR: 48.1 vs. 50.0%), although these responses less often resulted in durable remissions. In line with this, the median PFS (11 vs. 40 months, p = 0.059), TTNT (12 months vs. NR, p = 0.016), and OS (29 months vs. NR, p < 0.001) were significantly shorter for this patient cohort. CPI therapy was well tolerated in both subcohorts with 15% discontinuing therapy due to toxicity. Our real-world data show that first-line CPI therapy produced strong and durable responses among patients with advanced cSCC. Immunocompromised patients were less likely to achieve long-term benefit from anti-PD1 treatment, despite similar tumor response rates.
The pocket protein (PP) family consists of the three members RB1, p107 and p130 all possessing tumor suppressive properties. Indeed, the PPs jointly control the G1/S transition mainly by inhibiting E2F transcription factors. Notably, several viral oncoproteins are capable of binding and inhibiting PPs. Merkel cell polyomavirus (MCPyV) is considered as etiological factor for Merkel cell carcinoma (MCC) with expression of the viral Large T antigen (LT) harboring an intact PP binding domain being required for proliferation of most MCC cells. Therefore, we analyzed the interaction of MCPyV-LT with the PPs. Co-IP experiments indicate that MCPyV-LT binds potently only to RB1. Moreover, MCPyV-LT knockdown-induced growth arrest in MCC cells can be rescued by knockdown of RB1, but not by p107 or p130 knockdown. Accordingly, cell cycle arrest and E2F target gene repression mediated by the single PPs can only in the case of RB1 be significantly reverted by MCPyV-LT expression. Moreover, data from an MCC patient indicate that loss of RB1 rendered the MCPyV-positive MCC cells LT independent. Thus, our results suggest that RB1 is the dominant tumor suppressor PP in MCC, and that inactivation of RB1 by MCPyV-LT is largely sufficient for its growth supporting function in established MCPyV-positive MCC cells.
Pigment cells and neuronal cells both are derived from the neural crest. Here, we describe the Pit-Oct-Unc (POU) domain transcription factor Brn3a, normally involved in neuronal development, to be frequently expressed in melanoma, but not in melanocytes and nevi. RNAi-mediated silencing of Brn3a strongly reduced the viability of melanoma cell lines and decreased tumour growth in vivo. In melanoma cell lines, inhibition of Brn3a caused DNA double-strand breaks as evidenced by Mre11/Rad50-containing nuclear foci. Activated DNA damage signalling caused stabilization of the tumour suppressor p53, which resulted in cell cycle arrest and apoptosis. When Brn3a was ectopically expressed in primary melanocytes and fibroblasts, anchorage-independent growth was increased. In tumourigenic melanocytes and fibroblasts, Brn3a accelerated tumour growth in vivo. Furthermore, Brn3a cooperated with proliferation pathways such as oncogenic BRAF, by reducing oncogene-induced senescence in non-malignant melanocytes. Together, these results identify Brn3a as a new factor in melanoma that is essential for melanoma cell survival and that promotes melanocytic transformation and tumourigenesis.
Background: Inactivation of the p53 pathway that controls cell cycle progression, apoptosis and senescence, has been proposed to occur in virtually all human tumors and p53 is the protein most frequently mutated in human cancer. However, the mutational status of p53 in melanoma is still controversial; to clarify this notion we analysed the largest series of melanoma samples reported to date. Methodology/Principal Findings: Immunohistochemical analysis of more than 180 melanoma specimens demonstrated that high levels of p53 are expressed in the vast majority of cases. Subsequent sequencing of the p53 exons 5–8, however, revealed only in one case the presence of a mutation. Nevertheless, by means of two different p53 reporter constructs we demonstrate transcriptional inactivity of wild type p53 in 6 out of 10 melanoma cell lines; the 4 other p53 wild type melanoma cell lines exhibit p53 reporter gene activity, which can be blocked by shRNA knock down of p53. Conclusions/Significance: In melanomas expressing high levels of wild type p53 this tumor suppressor is frequently inactivated at transcriptional level.