Computational Analysis

The collaboration between clinician scientists and computer scientists is paramount to the projects within the MFICM.

Strength lies in partnership and sharing of expertise

Data integration is the central element of the MFICM approach. It brings together the themes of genomics (somatic, germline, ctDNA), imaging (radiomics, quantitative imaging, digital pathology) and clinical data and focuses on innovative approaches to analysis in a near real-time and longitudinal fashion. It uses prospectively collected data from clinical trials to explore these analyses. The overarching goal is to deliver a new paradigm in personalised cancer treatment which integrates multi-modality analyses in real-time that improves treatment selection and ultimately prognosis.

The last 30 years have witnessed a revolution in our understanding of cancer. For example, the invention of next generation sequencing by Cambridge scientist Professor Sir Shankar Balasubramanian. Cambridge researchers are also developing novel imaging technology that provides the ability to assess the response of tumour treatment more rapidly to name but two important advances. These new approaches could dramatically improve cancer diagnosis and management; however, at present they are performed as parallel, “siloed” research disciplines with little integration. We believe that the power of these disciplines to revolutionise cancer treatment could be fully realised as we learn how to integrate their rich datasets, both within and among different cancer types.

The continual, iterative and integrated analysis of these complementary and complex data streams – made possible by advanced machine learning and other computational approaches – will enable an unprecedented decision matrix for optimal treatment selection and improved chance of cure.  Data Stream Integration within the MFICM brings together a small, focused team of bioinformaticians, statisticians and computational scientists to demonstrate that our integrated cancer medicine approach can generate both scientific validity and clinical value.

 

Artificial Intelligence/Machine Learning

The resources below highlight how AI/ML are applied to Integrated Cancer Medicine in order to drive our research forward.

Spotlight on MFICM research

The METABRIC study

The METABRIC study

The techniques undertaken in the 2012 METABRIC study underpin the AI/ML Integrated Cancer Medicine data analysis techniques.

IMAX-T Grand Challenge Project: Creating virtual reality maps of tumours

IMAX-T Grand Challenge Project: Creating virtual reality maps of tumours

Combining established techniques with new technology, Professor Hannon’s team builds 3D tumours containing every cell in them, which can be studied using virtual reality. This new way of studying breast cancer could change how the disease is diagnosed, treated and managed. The IMAX-T project is distinct from the MFICM but it has been generously agreed, where appropriate, to collaborate with the Integrated Cancer Medicine effort.

Professor Mateja Jamnik TedX talk on AI

Professor Mateja Jamnik TedX talk on AI

In her TedX Talk in September 2016, Professor Mateja Jamnik discusses whether one day AI will outsmart humans. Mateja is developing AI techniques for human-like thinking and applies this AI technology to medical data to advance Integrated Cancer Medicine.

Connect

Connect with us

The Mark Foundation Institute for Integrated Cancer Medicine (MFICM) at the University of Cambridge aims to revolutionise cancer care by affecting patients along their treatment pathway.

Find out more

Connect