Plasma-derived Extracellular Vesicles (EVs) have been suggested as novel biomarkers in melanoma, due to their ability to reflect the cell of origin and ease of collection. This study aimed to identify novel EV biomarkers that can discriminate between disease stages. This was achieved by characterising the plasma-derived EVs of patients with melanoma, and comparing their proteomic and metabolomic profile to those from healthy controls. EVs were isolated from the plasma of 36 patients with melanoma and 13 healthy controls using Size Exclusion Chromatography. Proteomic and Metabolomic Analyses were performed, and machine learning algorithms were used to identify potential proteins and metabolites to differentiate the plasma-derived EVs from melanoma patients of different disease stages. The concentration and size of the EV population isolated was similar between groups. Proteins (APOC4, PRG4, PLG, TNC, VWF and SERPIND1) and metabolites (lyso PC a C18:2, PC ae C44:3) previously associated with melanoma pathogenesis were identified as relevant in differentiating between disease stages. The results further support the continued investigation of circulating plasma-derived EVs as biomarkers in melanoma. Furthermore, the potential of combined proteo-metabolomic signatures for differentiation between disease stages may provide valuable insights into early detection, prognosis, and personalised treatment strategies.

Malignant melanoma, one of the most aggressive human malignancies, is responsible for 80% of skin cancer deaths. Whilst early detection of disease progression or metastasis can improve patient survival, this remains a challenge due to the lack of reliable biomarkers. Importantly, these clinical challenges are not unique to humans, as melanoma affects many other species, including companion animals, such as the dog and horse. Extracellular vesicles (EVs) are tiny nanoparticles involved in cell-to-cell communication. Several protein and genomic EV markers have been described in the literature, as well as a wide variety of methods for isolating EVs from body fluids. As such, they may be valuable biomarkers in cancer and may address some clinical challenges in the management melanoma. This review aimed to explore the translational applications of EVs as biomarkers in melanoma, as well as their role in the clinical setting in humans and animals. A summary of melanoma-specific protein and genomic EV markers is presented, followed by a discussion of the role EVs in monitoring disease progression and treatment response. Finally, herein, we reviewed the advantages and disadvantages of methods utilised to isolate EVs from bodily fluids in melanoma patients (human and animals) and describe some of the challenges that will need to be addressed before EVs can be introduced in the clinical setting.

Introduction: There has been a recent explosion of research into the field of artificial intelligence as applied to clinical radiology with the advent of highly accurate computer vision technology. These studies, however, vary significantly in design and quality. While recent guidelines have been established to advise on ethics, data management and the potential directions of future research, systematic reviews of the entire field are lacking. We aim to investigate the use of artificial intelligence as applied to radiology, to identify the clinical questions being asked, which methodological approaches are applied to these questions and trends in use over time. Methods and analysis: We will follow the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines and by the Cochrane Collaboration Handbook. We will perform a literature search through MEDLINE (Pubmed), and EMBASE, a detailed data extraction of trial characteristics and a narrative synthesis of the data. There will be no language restrictions. We will take a task-centred approach rather than focusing on modality or clinical subspecialty. Sub-group analysis will be performed by segmentation tasks, identification tasks, classification tasks, pegression/prediction tasks as well as a sub-analysis for paediatric patients. Ethics and dissemination: Ethical approval will not be required for this study, as data will be obtained from publicly available clinical trials. We will disseminate our results in a peer-reviewed publication. Registration number PROSPERO: CRD42020154790

The treatment of Melanoma, one of the most aggressive human malignancies, has been revolutionised by the advent of novel targeted and immuno-therapies. However, methods utilised to detect early presentations, and to stratify risk for patients diagnosed with invasive melanoma in the clinical setting are lagging. The primary prognostic indicator is restricted to Breslow Thickness, or depth the tumour invades into the dermis. Gene Expression Profiling (GEP), the analysis of molecular gene signatures of an individual tumour, has been implemented with great success in other malignancies, such as breast and prostate cancer. In the setting of melanoma, commercial GEP panels are becoming available, offering patients a personalised approach, though yet to enter widespread clinical use. This short perspective seeks to describe how GEP is currently employed in practice, and its current clinical impact. We also suggest the potential roles for GEP in meeting the key clinical challenges faced by clinicians in melanoma treatment, such as decisions around adjuvant therapy, sentinel lymph node biopsy (SLNB) and surgical resection , thus highlighting areas for future potential research.