Computer Vision News - May 2024

Computer Vision News 52 Congrats, Doctor Salma! Salma Dammak (right in the photo) has recently obtained her PhD at Western University in Ontario, Canada under the supervision of Aaron Ward (left) and David Palma. Her PhD research focused on developing AI models to address challenges in the diagnosis and treatment of lung cancer for both pathology and radiology applications. Salma is now a postdoctoral researcher at the Computational Pathology Group at RadboudUMC in the Netherlands. Congrats, Doctor Salma! The motivation for Salma’s thesis lies in the complexity of lung cancer treatment and the difficulty of achieving fully personalized care given the current tools available in the clinic. For personalized care, extensive patient information is necessary, which may sometimes be incomplete. In her thesis, Salma addresses two clinical challenges where this is the case by using artificial intelligence to build models that predict the missing information. The first challenge focuses on predicting tumour mutational burden (TMB), a biomarker that measures how mutated a cancer is. This biomarker is important for determining which lung cancer patients are most likely to benefit from immunotherapy, which can be highly effective but carries the risk of severe side effects. Unfortunately, TMB assessment is currently inaccessible in most clinics, as it requires invasive biopsy and costly genetic sequencing. However, this thesis shows that a model can predict TMB from existing lung tissue images based on the morphology of cancer cells on tissue samples taken during previous cancer surgeries, which are common for patients who are considered for immunotherapy. Tumours from surgery contain many non-cancer tissues, and these tissues were excluded manually when developing the model, but to improve clinical translatability, this thesis also presents a model to automate this by identifying cancer cells within surgically removed tumours. This would allow the TMB prediction model to be completely automated.