Cancer is a complex disease and although overall mortality rates have decreased over the past decade, the total number of new diagnoses per year continues to rise. This highlights the urgent need for improved methods to identify individuals who would benefit from effective cancer treatments while minimizing treatment-related side effects. Moreover, with advancements in surgical techniques, radiotherapy, and various systemic therapies such as chemotherapy, targeted therapy, and immunotherapy, there is a growing opportunity and necessity for personalized cancer treatment based on biomarker-driven approaches, also known as precision oncology.

Precision oncology is a targeted approach to diagnosing and treating cancer based on an individual’s specific profile. In personalised cancer therapy, biomarkers (measurable and quantifiable biological molecules that indicate a specific biological state or condition) are used to predict the course of the disease (prognostic biomarkers) and which patients will have the highest probability (predictive biomarkers) of responding or having adverse side effects to particular therapies.

Our team focuses on developing Computational Pathology approaches to find and validate biomarkers to be implemented in daily clinical practice to empower precision oncology. Ultimately, we want to help the right person, to get the right treatment, at the right time!

Combining clinical, pathology and genomics data with image analysis of the tumour, we aim to find the balance between over- and under-treatment of women's ovarian and breast cancer. We develop models to recognise the tumour and its microenvironment using pathology samples from the clinic. We analyse different regions within tumour samples from the time of diagnosis, relapse and metastasis and combine it with data describing RNA, DNA and protein sequences of single cells to study the impact of intra-tumour heterogeneity upon cancer immunity and progression. These image-based quantitative results, together with genomic analysis of the cancer-immune interactions, can be complementary to identity biomarkers for prediction of treatment response to empower precision oncology.