The early detection of melanoma is the most efficient way to reduce its mortality rate. Dermatologists achieve this task with the help of dermoscopy, a non-invasive tool allowing the visualization of patterns of skin lesions. Computer-aided diagnosis (CAD) systems developed on dermoscopic images are needed to assist dermatologists. These systems rely mainly on multiclass classification approaches. However, the multiclass classification of skin lesions by an automated system remains a challenging task. Decomposing a multiclass problem into a binary problem can reduce the complexity of the initial problem and increase the overall performance. This paper proposes a CAD system to classify dermoscopic images into three diagnosis classes: melanoma, nevi, and seborrheic keratosis. We introduce a novel ensemble scheme of convolutional neural networks (CNNs), inspired by decomposition and ensemble methods, to improve the performance of the CAD system. Unlike conventional ensemble methods, we use a directed acyclic graph to aggregate binary CNNs for the melanoma detection task. On the ISIC 2018 public dataset, our method achieves the best balanced accuracy (76.6%) among multiclass CNNs, an ensemble of multiclass CNNs with classical aggregation methods, and other related works. Our results reveal that the directed acyclic graph is a meaningful approach to develop a reliable and robust automated diagnosis system for the multiclass classification of dermoscopic images.

Early detection of melanoma remains a daily challenge due to the increasing number of cases and the lack of dermatologists. Thus, AI-assisted diagnosis is considered as a possible solution for this issue. Despite the great advances brought by deep learning and especially convolutional neural networks (CNNs), computer-aided diagnosis (CAD) systems are still not used in clinical practice. This may be explained by the dermatologist’s fear of being misled by a false negative and the assimilation of CNNs to a “black box”, making their decision process difficult to understand by a non-expert. Decision theory, especially game theory, is a potential solution as it focuses on identifying the best decision option that maximizes the decision-maker’s expected utility. This study presents a new framework for automated melanoma diagnosis. Pursuing the goal of improving the performance of existing systems, our approach also attempts to bring more transparency in the decision process. The proposed framework includes a multi-class CNN and six binary CNNs assimilated to players. The players’ strategies is to first cluster the pigmented lesions (melanoma, nevus, and benign keratosis), using the introduced method of evaluating the confidence of the predictions, into confidence level (confident, medium, uncertain). Then, a subset of players has the strategy to refine the diagnosis for difficult lesions with medium and uncertain prediction. We used EfficientNetB5 as the backbone of our networks and evaluated our approach on the public ISIC dataset consisting of 8917 lesions: melanoma (1113), nevi (6705) and benign keratosis (1099). The proposed framework achieved an area under the receiver operating curve (AUROC) of 0.93 for melanoma, 0.96 for nevus and 0.97 for benign keratosis. Furthermore, our approach outperformed existing methods in this task, improving the balanced accuracy (BACC) of the best compared method from 77% to 86%. These results suggest that our framework provides an effective and explainable decision-making strategy. This approach could help dermatologists in their clinical practice for patients with atypical and difficult-to-diagnose pigmented lesions. We also believe that our system could serve as a didactic tool for less experienced dermatologists.

PMN-MDSCs support tumor progression and resistance to ICI therapy through their suppressive functions but their heterogeneity limits their use as biomarkers in cancer. Our aim was to investigate the phenotypic and functional subsets of PMN-MDSCs to identify biomarkers of response to ICI therapy. We isolated low-density CD15⁺ PMNs from patients with metastatic melanoma and assessed their immune-suppressive capacities. Expression of CD10 and CD16 was used to identify mature and immature subsets and correlate them to inhibition of T cell proliferation or direct cytotoxicity. Frequencies of the PMN-MDSCs subsets were next correlated to the radiological response of 36 patients receiving ICI therapy. Mature activated cells constituted the major population of PMN-MDSCs. They were found in a higher proportion in the pre-treatment blood of patients non responders to ICI. A subset of immature cells characterized by intermediate levels of CD10 and CD16, the absence of expression of SIRPα and a strong direct cytotoxicity to T cells was increased in patients responding to ICI. The paradoxical expansion of such cells during ICI therapy suggests a role of PMNs in the inflammatory events associated to efficient ICI therapy and the usefulness of their monitoring in patients care.

Melanoma is still a major health problem worldwide. The early diagnosis is the first step toward reducing its mortality, but it remains a challenge even for experienced dermatologists. While computer-aided systems have been developed to help the diagnosis, the lack of insight of their predictions is still a significant limitation towards acceptance by the medical community. To tackle this issue, we designed handcrafted expert features representing color asymmetry within the lesions, which are parts of the approach used by dermatologists in their daily practice. These features are given to an artificial neural network (ANN) classifying between nevi and melanoma. We compare our results with an ensemble of seven state-of-the-art CNNs and merge the two approaches by computing the average prediction. Our experiments are done on a subset of the International Skin Imaging Collaboration (ISIC) 2019 dataset (6296 nevi, 1361 melanomas). The ANN based on asymmetry achieved an AUC of 0.873, Sensitivity 90%, Specificity 67%, the CNN approach achieved an AUC of 0.938, Sensitivity 91%, Specificity 82%, and the fusion of both approaches was 0.942, Sensitivity 92%, Specificity 82%. Merging the knowledge of dermatologists with CNNs showed high performances for melanoma detection, encouraging collaboration between computer science and medical fields.