Periodic Reporting for period 1 - REACT (Optimising Radiomics for MRI-based personalised cancer treatment)
Reporting period: 2017-11-17 to 2018-11-16
Although cancer survival rates have substantially improved in recent years, cancer is still among the leading causes of morbidity and mortality worldwide. The future of cancer treatment lies in early and better diagnosis and individually tailored treatments (‘personalised medicine). The REACT project developed a breakthrough AI solution, Radiomics is a quantitative image analysis technology that enables improved patient stratification through the use of routinely acquired images. This supports improved clinical decision making and leads to better patient outcomes.
Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far
Radiomics is based on the evolution of thousands of image-derived features over the course of treatment, Radiomics allows for more sensitive and robust identification of tumour types than currently possible. As MRI is recognised as one of the most promising techniques for the detection of cancer and spread of the disease, the REACT project aligned Radiomics with MRI, making analysis feasible across multiple centres and vendors while reducing variability by applying standardized protocols. This result delivers reliable high-quality quantifiable MRI feature analyses, for correlation with the underlying pathology, and for future decision support models. This is being exploited by the production of radiomics based clinical decision support systems for use in routine clinical care. Dissemination is achieved via our website promoting the REACT project.
Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)
The REACT project brought to bear advanced AI techniques such as Deep Learning to progress beyond the state of the art with respect to MRI use in oncology. This results in improved clinical decision making which leads to better individual patient outcomes and a more effective, efficient, and economic health service for the population.