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.
Cemiplimab has shown substantial antitumour activity in patients with metastatic cutaneous squamous cell carcinoma. Patients with locally advanced cutaneous squamous cell carcinoma have poor ...prognosis with conventional systemic therapy. We present a primary analysis of the safety and antitumour activity of cemiplimab in patients with locally advanced cutaneous squamous cell carcinoma.
This pivotal open-label, phase 2, single-arm trial was done across 25 outpatient clinics, primarily at academic medical centres, in Australia, Germany, and the USA. Eligible patients (aged ≥18 years with histologically confirmed locally advanced cutaneous squamous cell carcinoma and an Eastern Cooperative Oncology Group performance status of 0–1) received cemiplimab 3 mg/kg intravenously over 30 min every 2 weeks for up to 96 weeks. Tumour measurements were done every 8 weeks. The primary endpoint was objective response, defined as the proportion of patients with complete or partial response, according to independent central review as per Response Evaluation Criteria in Solid Tumors version 1.1 for radiological scans and WHO criteria for medical photography. Data cutoff was Oct 10, 2018, when the fully enrolled cohort reached the prespecified timepoint for the primary analysis. Analyses were done as per the intention-to-treat principle. The safety analysis comprised all patients who received at least one dose of cemiplimab. This study is registered with ClinicalTrials.gov, number NCT02760498.
Between June 14, 2016, and April 25, 2018, 78 patients were enrolled and treated with cemiplimab. The median duration of study follow-up was 9·3 months (IQR 5·1–15·7) at the time of data cutoff. An objective response was observed in 34 (44%; 95% CI 32–55) of 78 patients. The best overall response was ten (13%) patients with a complete response and 24 (31%) with a partial response. Grade 3–4 treatment-emergent adverse events occurred in 34 (44%) of 78 patients; the most common were hypertension in six (8%) patients and pneumonia in four (5%). Serious treatment-emergent adverse events occurred in 23 (29%) of 78 patients. One treatment-related death was reported that occurred after onset of aspiration pneumonia.
Cemiplimab showed antitumour activity and an acceptable safety profile in patients with locally advanced cutaneous squamous cell carcinoma for whom there was no widely accepted standard of care.
Regeneron Pharmaceuticals and Sanofi.
Activating genomic alterations of the receptor tyrosine kinase KIT are found preferentially in certain melanoma subtypes such as acral and mucosal melanoma or melanoma arising in chronically ...sun-damaged skin. However, the therapeutic value of c-Kit inhibitors for these subtypes currently remains unclear.
The objective of this study was to summarise the efficacy and safety of c-Kit inhibitors for unresectable or metastatic mucosal, acral or chronically sun-damaged melanoma.
We performed a systematic literature research in MEDLINE, Embase and CENTRAL and hand searched pertinent trial registers and conference abstracts for eligible trials until 23rd June 2020. Results were pooled using a random-effects model to calculate pooled proportions of objective response rates (ORRs) and severe adverse events (sAEs) from unselected KIT mutant or amplified cohorts.
Nineteen single-arm studies with an overall sample size of 601 patients were included. The studies investigated imatinib (n = 8), nilotinib (n = 7), dasatinib (n = 3) and sunitinib (n = 1). The pooled ORR for all inhibitors was 15% (95% confidence interval CI: 12–18%). Subgroup analysis revealed the highest ORR (20%; 95% CI: 14–26%) for nilotinib. The ORR for mucosal melanoma was 14% (95% CI: 6–24%) and 22% for acral lentiginous melanoma (95% CI: 14–30%). At least one sAE was reported in 42% of patients (95% CI: 34–50%).
c-Kit inhibitors represent a valuable treatment option for patients with KIT-mutant melanoma, in particular for mutations of exons 11 and 13. Furthermore, high-quality trials are urgently needed to investigate putative combinations of specific targeted therapies with immunotherapy.
•The therapeutic value of c-Kit inhibitors in rare melanoma subtypes is unclear.•Twenty-one studies with n = 649 patients were identified in a systematic literature research.•Pooled objective response rate was 15% (95% confidence interval: 11–20%) for all c-Kit inhibitors.•Combination of c-Kit inhibitors with immunotherapy should be further investigated.
Internet-based guided self-help and face-to-face CBT have shown to be effective in the treatment of depression, but both approaches might not be an available treatment option for all patients. A ...treatment which blends internet-based guided self-help with video-based psychotherapy might reduce potential disadvantages of both approaches, while maintaining major advantages such as being location-independent. Additionally, it could provide a stronger focus on patient empowerment and lower resource use compared to traditional face-to-face treatment.
The aim of this study is to evaluate patient's experiences with blended internet- and video-based CBT (blended iCBT) treatment and to derive suggestions for the improvement of such services.
Semi-structured interviews were conducted with 15 participants of the blended iCBT treatment as part of the European MasterMind trial. Participants included adults suffering from Major Depressive Disorder. The interview guide assessed patient's experiences regarding the four treatment components program, 1. face-to-face diagnostic interviews, 2. video-based synchronous therapy sessions (VTS), 3. online self-help treatment modules (OTM) as well as 4. behaviour diaries and symptom monitoring. Interviews were analyzed using the framework method and outcomes regarding connections within and between participants and categories were generated by counting the statements within relevant themes.
Overall, patients indicated to have been satisfied with all components of the treatment, highlighting the option to independently work from home in their own pace. While the OTMs allowed for a deeper reflection of the content, the VTS with the therapist were mentioned to provide the personal character of the service. The working alliance with the therapist was experienced as fostering the individual fit of the treatment. Patients reported a high self-perceived treatment effectiveness. Negative effects included that some patients felt overwhelmed by the service, e.g. by working with the content of the OTM as they forced them to address their problems. Within the combination of OTM and VTS, both components were rated as equally important and patients felt that the combination depicted a treatment at least equal to regular face-to-face treatment regarding the perceived effectiveness. Other identified themes included patient's individual factors, reactions in their social environment and suggestions for improvement of the service.
Predominantly, patients reported positive experiences with the blended iCBT service and rate the treatment as adequate and effective to treat their condition. The importance of the VTS is highlighted. Following this approach might be an option to make affordable and effective evidence-based CBT available independent from regional barriers.
•The combination of video-based synchronous therapy sessions and online self-help treatment modules is evaluated as a blended CBT treatment•A blended CBT treatment might be an option to overcome traditional barriers for the provision of evidence-based CBT•Patients experienced the service as a useful alternative to traditional face-to-face-treatment•Patients experienced the working alliance as intense and sufficiently stable to create an emotional bond with the therapist
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.
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.
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).
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).
•A convolutional neural network (CNN) received enhanced training with 11,444 dermoscopic images of >90% of lesions faced in a skin cancer screening setting.•The performance of 112 dermatologists from 13 university hospitals was then compared with the CNN on a test set of 300 biopsy-verified images.•The CNN achieved systematic outperformance of the dermatologists (p < 0.001) regardless of their clinical experience.
Cutaneous squamous cell carcinoma is a common type of skin cancer that may progress to locally advanced or metastatic disease. Both disease stages are managed by a variety of treatment options, ...including immune checkpoint blockade (ICB), targeted therapy to epidermal growth factor, chemotherapy or treatment combinations. However, the comparative efficacy of such treatments is unclear.
We performed a systematic literature search of Medline, Embase and Central to identify eligible studies reporting Kaplan–Meier curves or individual patient data for overall survival (OS) or progression-free survival (PFS). Kaplan–Meier curves were digitised using the “‘WebPlotDigitizer” program. Individual patient data was subsequently remodelled and pooled for distinct treatment groups.
Overall, 22 independent studies were included of which n = 927 patients were evaluable for PFS and n = 1054 for OS. ICB showed the highest median PFS (mPFS 9.9 months (95% CI: 8.1–19.9)) and median OS (mOS not reached (95% CI: 31.5 months-not reached)) compared to chemotherapy (mPFS 3.0 months (95% CI: 2.2–4.8), mOS 12.6 months (95% CI: 9.6–15.8)), targeted therapy to epidermal growth factor (mPFS 4.9 months (95% CI: 4.4–5.6), mOS 12.7 months (95% CI: 11.9–14.9)) and combination therapies without ICB (mPFS 9.1 months (95% CI: 8.0–12.1), mOS 18.1 months (95% CI: 16.3–22.8)). The survival benchmark with ICB after 26 months for metastatic squamous cell carcinoma was 70.8% (95% CI: 61.5%–81.5%) versus 37.9% (95% CI: 29.5%–48.8%) for the combination group and 17.1% (95% CI: 9.5%–30.8%) for chemotherapy.
ICB is superior to other systemic treatments and sets a novel survival benchmark for advanced cutaneous squamous cell carcinoma.
•The relative efficacy of treatments for cutaneous squamous cell carcinoma is unclear.•Immune checkpoint blockade is superior to other systemic treatments.•Immune checkpoint blockade sets a new survival benchmark.
This study aimed to identify prognostic factors in patients with metastatic uveal melanoma (UM) that were associated with long-term survival in a real-world setting. A total of 94 patients with ...metastatic UM were included from German skin cancer centers and the German national skin cancer registry (ADOReg). Data were analyzed for the response to treatment, progression-free survival, and overall survival (OS). Prognostic factors were explored with univariate Cox regression, log-rank, and
χ
2-tests. Identified factors were subsequently validated after the population was divided into two cohorts of short-term survival (< 2 years OS, cohort A,
n
= 50) and long-term survival (> 2 years OS, cohort B,
n
= 44). A poor ECOG performance status (hazard ratio HR 2.0, 95% confidence interval CI 1.0–3.9) and elevated serum LDH (HR 2.0, 95% CI 1.0–3.8) were associated with a poor OS, whereas a good response to immune checkpoint blockade (ICB,
p
< 0.001), radiation therapy (
p
< 0.001), or liver-directed treatments (
p
= 0.01) were associated with a prolonged OS. Long-term survivors (cohort B) showed a higher median number of organs affected by metastasis (
p
< 0.001), while patients with liver metastases only were more common in cohort A (40% vs. 9%;
p
= 0.002). A partial response to ICB was observed in 16% (12/73), being 21% (8/38) for combined ICB, 17% (1/6) for single CTLA4 inhibition, and 10% (3/29) for single PD1 inhibition. One complete response occurred in cohort B with combined ICB. We conclude that the response to ICB and the presence of extrahepatic disease were favorable prognostic factors for long-term survival.
In addition to Circulating Tumour Cells (CTCs), cell-free DNA (cfDNA) and Extracellular Vesicles (EVs), the notion of "Tumour-Educated Platelets" (TEP) has recently emerged as a potential source of ...tumour-derived biomarkers accessible through blood liquid biopsies. Here we sought to confirm the suitability of the platelet blood fraction for biomarker detection in comparison to their corresponding EV fraction. As publications have claimed that tumour RNA and other tumour-derived material are transferred from tumour cells to the platelets and that tumour-derived transcripts can be detected in platelets, we chose to focus on RNA carrying a mutation as being of bona fide tumour origin. After informed consent, we collected prospective blood samples from a cohort of 12 melanoma patients with tissue-confirmed BRAF V600E mutation. Each blood specimen was processed immediately post collection applying two published standard protocols in parallel selecting for EVs and platelets, respectively. The RNA of each fraction was analysed by a highly sensitive ARMS RT-qPCR enabling the quantification of the mutant allele fraction (%MAF) of BRAF V600E down to 0.01%. In a direct comparative analysis, the EV fraction contained detectable BRAF V600E in 10 out of 12 patients, whereas none of the patient platelet fractions resulted in a mutant allele signal. The platelet fraction of all 12 patients contained high amounts of wild-type BRAF signal, but no mutation signal above background was detectable in any of the samples. Our observations suggest that the phenomenon of tumour RNA transfer to platelets occurs below detection limit since even a very sensitive qPCR assay did not allow for a reliable detection of BRAF V600E in the platelet fraction. In contrast, EV fractions derived from the same patients allowed for detection of BRAF V600E in 10 of 12 blood specimens.
IMPORTANCE: Multiple interventions are available for the treatment of actinic keratosis (AK). However, most randomized clinical trials and meta-analyses focus on short-term efficacy outcomes. ...OBJECTIVE: To investigate and synthesize the long-term efficacy (≥12 months) of interventions for AK from parallel-arm randomized clinical trials. DATA SOURCES: Searches in MEDLINE, Embase, and Central were conducted from inception until April 6, 2020. The reference lists of the included studies and pertinent trial registers were hand searched. The study was completed February 27, 2021. STUDY SELECTION: Two reviewers screened the titles and abstracts of 2741 records. Finally, 17 published reports (original studies and follow-up reports) referring to 15 independent randomized clinical trials with an overall sample size of 4252 patients were included. DATA EXTRACTION AND SYNTHESIS: Two reviewers independently extracted data on study, patient, and intervention characteristics. Network meta-analysis (NMA) of each outcome was conducted with a frequentist approach. The Grading of Recommendations Assessment, Development, and Evaluation (GRADE) guidance for NMA was used to assess the certainty of evidence. The revised Cochrane risk-of-bias tool for randomized clinical trials was used to evaluate the methodologic quality. MAIN OUTCOMES AND MEASURES: Participant complete clearance, participant partial clearance, and lesion-specific clearance were the outcomes, with each assessed at least 12 months after the end of treatment. RESULTS: Data from 15 independent randomized clinical trials including 4252 patients were extracted and synthesized. Ten studies were included in an NMA for the outcome of participant complete clearance, with photodynamic therapy with aminolevulinate (ALA-PDT) showing the most favorable risk ratio (RR) compared with placebo (RR, 8.06; 95% CI, 2.07-31.37; GRADE, moderate), followed by imiquimod, 5% (RR, 5.98; 95% CI, 2.26-15.84; GRADE, very low), photodynamic therapy with methyl aminolevulinate (MAL-PDT) (RR, 5.95; 95% CI, 1.21-29.41; GRADE, low), and cryosurgery (RR, 4.67; 95% CI, 1.36-16.66; GRADE, very low). Similarly, ALA-PDT had the highest RR in the NMA for lesion-specific clearance (RR, 5.08; 95% CI, 2.49-10.33; GRADE, moderate). No NMA was possible for participant partial clearance owing to poor reporting of this outcome. CONCLUSIONS AND RELEVANCE: This systematic review and network meta-analysis found that therapy including ALA-PDT, imiquimod, 5%, MAL-PDT, and cryosurgery was associated with significant long-term efficacy in the NMA. This study provides data for a possible use in an evidence-based framework for selecting interventions with sustained lesion clearance.