MIAdx: Molecular diagnostics for Melanoma
Accurately distinguishing melanoma from benign melanocytic lesions is one of the most challenging areas in pathology, with significant implications for treatment and patient outcomes. Our research is focused on creating advanced molecular diagnostics, such as MIAdx, a genomic test that integrates mutational patterns from both coding and non-coding regions, to provide pathologists with highly specific and objective tools to aid diagnosis. These efforts are part of a broader program developing innovative assays and platforms that reduce diagnostic uncertainty, support clinical decision-making, and improve outcomes for patients.
Artificial Intelligence in Histopathology
Accurate diagnosis of melanoma is critical, yet histopathology can be subjective and prone to misinterpretation. This project leverages artificial intelligence (AI) image analysis to support pathologists in distinguishing melanoma from benign moles on tissue slides. Working with a multidisciplinary team, we have developed an AI classifier trained on unequivocal pathology cases, demonstrating strong discriminatory performance. Current efforts focus on testing the model in more challenging scenarios, across diverse melanoma subtypes, and on external datasets to assess generalisability. By building trust in AI-assisted pathology, this research aims to reduce diagnostic uncertainty, improve accuracy, and ultimately enhance patient care