Mattias Johan Rantalainen

Breast cancer (BC) remains a global health challenge, with 7.8 million new cases annually. Despite treatment and screening advances that have gradually improved outcomes since the 1970s, many patients still do not survive their dissease, creating an urgent need for precision diagnostics to identify high-risk individuals and predict therapeutic responses. The Consortium for AI in Registry-Based Image Epidemiology Research in Breast Cancer (CARE-B) addresses this by combining registry data, histopathology images, and AI to improve BC characterization.CARE-B will establish an internationally unique large (up to 30,000 patients), multimodal multi-site database integrating clinical data, whole slide images (WSIs), and molecular profiles from breast cancer cohorts in Sweden, Denmark, and Scotland. The consortium will develop scalable AI models for cost-effective precision diagnostics, focusing on deep phenotyping of BC subtypes based on routine H&E stained histopathology slides, characterise intra-tumor heterogeneity (ITH), predicting treatment responses and for prognostic stratification.CARE-B will foster collaboration, support junior researchers, and advance epidemiological research and clinical translation. By leveraging AI and registry data, CARE-B aims to significantly impact BC research and clinical diagnostics, creating a foundation for future advances in precision medicine, while also building a research environment that take health-registry research to the next level.

Cancer is a leading cause of death globally. Precision medicine, which offers new (targeted) therapies, has the potential to improve cancer care. However, precision diagnostic solutions are required to be able to provide the right treatment to the right patient, and to be able to do it quickly, reliably and cost-effectively. Molecular diagnostics offer improved diagnostics, but at a high cost, which limits patient access and also places a high financial burden on healthcare systems. AI technology has the potential to offer new precision diagnostics that can reach broad patient groups. In this project, we develop and validate AI-based image analysis solutions for cancer diagnostics in breast and prostate cancer. Clinical pathology is undergoing a digital transition that enables the introduction of AI-based decision support tools for precision diagnostics at a fraction of the cost of molecular diagnostics. The project uses large and unique study materials consisting of histopathology images and clinical pathology data for the development and clinical validation of new AI-based precision diagnostic solutions. The project has the potential to contribute to improving diagnostics and cancer care and increased access to precision diagnostics. The goals of the projects are partly to build large studies that are the basis for studies in AI-based precision diagnostics, partly to develop solutions that improve prognostic and treatment predictive models for breast and prostate cancer.

Microscopic examination of stained tissue samples is the primary approach to cancer detection and diagnosis. However, there is a lack of pathology expertise at the same time as the manual review carried out in today's cancer care has a built-in degree of uncertainty and error because the assessments are difficult for the human eye. The uncertainty in the assessments leads to both over- and under-treatment, with potentially large consequences for individual patients. Access to expertise in pathology also varies across locations and over time, which can contribute to a degree of inequality in care. Rapid progress has been made in recent years in an area of artificial intelligence (AI) and machine learning referred to as “deep learning”. Deep learning models can now be trained to perform difficult prediction problems with reliability comparable to, or better than, humans in a variety of applications, including medical image analysis. These models may transform cancer care for the better in several areas. This project uses large-scale epidemiological studies for the development and validation of AI-based cancer diagnostics for breast cancer, prostate cancer and colorectal cancer. The goal is that the research should be able to lead to AI-based decision support that can be used to improve the precision of today's routine diagnostics based on tissue samples, but also to the development of new diagnostic and prognostic models. The results will lead to safer diagnoses and increased access to high-quality cancer diagnostics. This will lead to reduced over- and under-treatment, and better patient outcomes.