Refine
Has Fulltext
- yes (3) (remove)
Is part of the Bibliography
- yes (3)
Year of publication
- 2021 (3) (remove)
Document Type
- Journal article (3)
Language
- English (3) (remove)
Keywords
- PD-1 (2)
- melanoma (2)
- BRAF (1)
- CTLA-4 (1)
- adjuvant treatment (1)
- artificial intelligence (1)
- checkpoint blocker (1)
- deep learning (1)
- dermatology (1)
- immune checkpoint blockade (1)
- liver metastasis (1)
- machine learning (1)
- neural networks (1)
- nevus (1)
- skin neoplasms (1)
- targeted therapy (1)
- treatment resistance (1)
- uveal melanoma (1)
Background
A basic requirement for artificial intelligence (AI)–based image analysis systems, which are to be integrated into clinical practice, is a high robustness. Minor changes in how those images are acquired, for example, during routine skin cancer screening, should not change the diagnosis of such assistance systems.
Objective
To quantify to what extent minor image perturbations affect the convolutional neural network (CNN)–mediated skin lesion classification and to evaluate three possible solutions for this problem (additional data augmentation, test-time augmentation, anti-aliasing).
Methods
We trained three commonly used CNN architectures to differentiate between dermoscopic melanoma and nevus images. Subsequently, their performance and susceptibility to minor changes (‘brittleness’) was tested on two distinct test sets with multiple images per lesion. For the first set, image changes, such as rotations or zooms, were generated artificially. The second set contained natural changes that stemmed from multiple photographs taken of the same lesions.
Results
All architectures exhibited brittleness on the artificial and natural test set. The three reviewed methods were able to decrease brittleness to varying degrees while still maintaining performance. The observed improvement was greater for the artificial than for the natural test set, where enhancements were minor.
Conclusions
Minor image changes, relatively inconspicuous for humans, can have an effect on the robustness of CNNs differentiating skin lesions. By the methods tested here, this effect can be reduced, but not fully eliminated. Thus, further research to sustain the performance of AI classifiers is needed to facilitate the translation of such systems into the clinic.
Background: Since there is no standardized and effective treatment for advanced uveal melanoma (UM), the prognosis is dismal once metastases develop. Due to the availability of immune checkpoint blockade (ICB) in the real-world setting, the prognosis of metastatic UM has improved. However, it is unclear how the presence of hepatic and extrahepatic metastasis impacts the response and survival after ICB. Methods: A total of 178 patients with metastatic UM treated with ICB were included in this analysis. Patients were recruited from German skin cancer centers and the German national skin cancer registry (ADOReg). To investigate the impact of hepatic metastasis, two cohorts were compared: patients with liver metastasis only (cohort A, n = 55) versus those with both liver and extra-hepatic metastasis (cohort B, n = 123). Data were analyzed in both cohorts for response to treatment, progression-free survival (PFS), and overall survival (OS). The survival and progression probabilities were calculated with the Kaplan–Meier method. Log-rank tests, χ\(^2\) tests, and t-tests were performed to detect significant differences between both cohorts. Results: The median OS of the overall population was 16 months (95% CI 13.4–23.7) and the median PFS, 2.8 months (95% CI 2.5–3.0). The median OS was longer in cohort B than in cohort A (18.2 vs. 6.1 months; p = 0.071). The best objective response rate to dual ICB was 13.8% and to anti-PD-1 monotherapy 8.9% in the entire population. Patients with liver metastases only had a lower response to dual ICB, yet without significance (cohort A 8.7% vs. cohort B 16.7%; p = 0.45). Adverse events (AE) occurred in 41.6%. Severe AE were observed in 26.3% and evenly distributed between both cohorts. Conclusion: The survival of this large cohort of patients with advanced UM was more favorable than reported in previous benchmark studies. Patients with both hepatic and extrahepatic metastasis showed more favorable survival and higher response to dual ICB than those with hepatic metastasis only.
Adjuvant treatment of melanoma patients with immune-checkpoint inhibition (ICI) and targeted therapy (TT) significantly improved recurrence-free survival. This study investigates the real-world situation of 904 patients from 13 German skin cancer centers with an indication for adjuvant treatment since the approval of adjuvant ICI and TT. From adjusted log-binomial regression models, we estimated relative risks for associations between various influence factors and treatment decisions (adjuvant therapy yes/no, TT vs. ICI in BRAF mutant patients). Of these patients, 76.9% (95% CI 74–80) opted for a systemic adjuvant treatment. The probability of starting an adjuvant treatment was 26% lower in patients >65 years (RR 0.74, 95% CI 68–80). The most common reasons against adjuvant treatment given by patients were age (29.4%, 95% CI 24–38), and fear of adverse events (21.1%, 95% CI 16–28) and impaired quality of life (11.9%, 95% CI 7–16). Of all BRAF-mutated patients who opted for adjuvant treatment, 52.9% (95% CI 47–59) decided for ICI. Treatment decision for TT or ICI was barely associated with age, gender and tumor stage, but with comorbidities and affiliated center. Shortly after their approval, adjuvant treatments have been well accepted by physicians and patients. Age plays a decisive role in the decision for adjuvant treatment, while pre-existing autoimmune disease and regional differences influence the choice between TT or ICI.