The group develops and applies AI and machine learning methodologies for predictive modelling in biomedical applications, with a particular interest in precision medicine and cancer research.
Our mission is to drive the development and application of data-driven approaches in cancer precision medicine and to develop and validate novel patient stratification models, including prognostic and treatment predictive applications. To achieve this we develop methods and models that allow us to transform large biomedical data into clinically relevant predictions at the individual level. Our research also includes clinical translation and implementation of regulatory approved medical devices.
Common for our research projects is the use of large datasets (big-data) across multiple modalities including comprehensive molecular profiling (e.g. DNA- and RNA-sequencing), clinical information and medical imaging data (histopathology).
Main research areas
Computational pathology
AI (deep learning) driven research focusing on developing and validating models in the domain of cancer histopathology. We focus on precision pathology, i.e. applications where the focus is to predict patient outcomes. The research is based on large population representative studies (we have > 300,000 WSIs collected in-house). The main focus is on breast, prostate and colorectal cancer. We currently coordinate several national and international initiatives (www.chimestudy.se, www.abcap.org, www.swaipp.org/).
Cancer precision medicine
Development and validation of predictive models for improved patient stratification, based on comprehensive molecular phenotyping data (e.g. DNA- and RNA-sequencing)