Project description
A quicker way to diagnose heart attacks
Cardiovascular disease (CVD) is the biggest global cause of death. According to the World Health Organization, there will be 25 million deaths from CVD every year by 2020. An echocardiogram is the most common imaging tool to assess cardiac function. The problem is it takes over 30 minutes to perform and longer for results to be generated and reported. The EU-funded MARCIUS project aims to provide cardiologists a faster diagnostic tool. It will use machine learning to develop a neural network to map inputs to outputs, and intelligent algorithms to provide automatic interpretation of regional cardiac contraction patterns and myocardial image texture.
Objective
Cardiovascular diseases (CVD) are the number one cause of death in EU. Echocardiography is the most important imaging tool to assess cardiac function, since it is real time, cost effective and can be performed without discomfort and harmful radiation. A typical cardiac ultrasound examination takes 30-40 min, with image analysis and reporting doubling this time. Thus, cardiologists are now calling for a step change in diagnostic speed and accuracy to allow significant improvements for the care of CVD patients. We propose to develop intelligent algorithms to provide diagnostic support by automatic interpretation of regional cardiac contraction patterns and myocardial image texture. MARCIUS will leverage recent progress in machine learning to train a neural network to recognize unique disease states using a large database of patient data with known pathophysiology and outcome augmented with virtual patient data obtained using a well-validated mathematical model of the heart and circulatory system in combination with a beyond the state-of-the-art ultrasound simulation tool. The resulting diagnostic algorithm will be validated clinically. MARCIUS will take on research activities with high added value, both clinically for patients suffering from cardiac diseases, commercially for the industrial beneficiary and societally with reducing healthcare costs. The long-term and high-risk aspect of these activities makes them unsuited for execution within a normal product development context. Through training and knowledge development in a focused research project built on a unique combination of state-of-the-art technologies, MARCIUS will provide Europe with researchers trained with the cross-disciplinary understanding and skills necessary to develop enabling technologies in an industrial and clinical setting. The longer-term outcome of the project is new products, which will benefit patients across Europe directly by advancing the state of care within cardiology.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
- medical and health sciencesbasic medicinephysiologypathophysiology
- medical and health sciencesclinical medicinecardiologycardiovascular diseases
- natural sciencescomputer and information sciencessoftwaresoftware applicationssimulation software
- natural sciencesphysical sciencesacousticsultrasound
- natural sciencesmathematicsapplied mathematicsmathematical model
You need to log in or register to use this function
Programme(s)
Coordinator
3191 Horten
Norway