AI accelerates blood flow MRI

Imaging technology helps to detect cardiovascular diseases much earlier; however, precise examinations are still very time-​consuming. Researchers from ETH and the University of Zurich have now presented a method that could greatly accelerate dynamic magnetic resonance imaging of blood flow.

Photo
The new MRI method makes it possible to obtain precise MRI images of blood flow in less than five minutes instead of 30 minutes as it is currently the case.
Source: Visualization: CMR Zurich

“Thanks to this innovation, quantitative magnetic resonance imaging could make tremendous progress,” says Sebastian Kozerke, Professor of Biomedical Imaging at ETH and the University of Zurich. He worked with Valery Vishnevskiy and Jonas Walheim to develop a method that greatly accelerates so-called 4D flow MRIs. “At the moment, the recording and subsequent processing of a 4D flow MRI takes up to 30 minutes. Our results show that this could be possible within five minutes in the future.”

Magnetic resonance tomography (MRT or MRI) is a key modality in clinical diagnosis. It poses no health risks and provides precise images of the interior of the body. This method can be used to display soft body parts such as tissue and organs in 3D and with high contrast. Furthermore, special recording techniques deliver information on the dynamics of the cardiovascular system.

In particular, 4D flow MRI measurements enable the quantification of dynamic changes of blood flow. Such dynamic images are highly useful, particularly when it comes to detecting cardiovascular diseases.

However, conventional 4D flow MRI has a significant drawback: the method is very time-consuming. Nowadays, the data recording can be completed in the MRI scanner within four minutes. However, the required compressed sensing approach comes at a cost: the subsequent image reconstruction is iterative and thus takes a very long time. Doctors have to wait 25 minutes or longer for the images to appear on their computers.

Thus, the results of the measurement only become available long after the doctor has completed the examination. This is why 4D flow MRI is not yet established in everyday medical practice. Changes to blood flow are currently diagnosed primarily via ultrasound – a method that’s quicker but less precise in comparison with MRI.

Elegant and efficient algorithms

In the recently published article, the researchers from ETH and the University of Zurich illustrate a way in which image reconstruction for 4D flow MRI could be made quicker and thus more practical. “The solution consists of elegant and efficient algorithms based on neural networks,” explains Kozerke.

Vishnevskiy, Kozerke and Walheim call their new approach FlowVN. It is based on machine learning, more specifically on what is known as deep learning; the software learns through data presented during a training stage. What makes FlowVN so special is the efficiency – the method combines training with prior knowledge of the measurement.

This means that generalisations can be made on the basis of little data instead of requiring thousands of training examples. “As a result, the network needs very little training to deliver reliable results,” explains Vishnevskiy.

The researchers were able to demonstrate that this method works as described in thier recently published paper. They trained the software using 11 MRI scans of healthy test subjects. This data was sufficient to accurately reproduce pathological blood flow in a patient’s aorta on an ordinary computer within just 21 seconds. The method is thus many times faster than conventional methods – and, on top, delivers better results.

Advancing clinical diagnosis

“We hope that FlowVN will drive forward the use of 4D flow MRI in clinical diagnostics,” says Kozerke. The data was reconstructed offline for this study. The next step for the Zurich research team will be to install the software on clinical MRI machines. “We then envisage larger clinical patient studies,” says Kozerke. The researchers benefit from the long-term partnership with the radiology and cardiology departments at the University Hospital Zurich.

If the follow-up tests confirm the results obtained by Kozerke’s team, the method could one day make its way into everyday medical practice. “However, it will take at least another four or five years until this happens,” estimates Kozerke. In order to accelerate the scientific research process, his team made the executable codes and data examples available as open source, enabling other scientists to test and reproduce the method.

Subscribe to our newsletter

Related articles

Microfluidics and AI microscopy measure hemoglobin

Microfluidics and AI microscopy measure hemoglobin

Researchers at the Indian Institute of Science and SigTuple Technologies have developed a method to measure hemoglobin levels in small-volume blood samples.

Deep learning platform accurately diagnoses dystonia

Deep learning platform accurately diagnoses dystonia

Researchers have developed a unique diagnostic tool that can detect dystonia from MRI scans, the first technology of its kind to provide an objective diagnosis of the disorder.

AI could serve as backup to radiologists' eyes

AI could serve as backup to radiologists' eyes

A study showed that an AI algorithm provides results comparable with lung function tests, which measure how forcefully a person can exhale.

Robot uses AI and imaging to draw blood

Robot uses AI and imaging to draw blood

Engineers have created a tabletop device that combines a robot, AI and near-infrared and ultrasound imaging to draw blood or insert catheters to deliver fluids and drugs.

AI measures fat around heart to predict diabetes

AI measures fat around heart to predict diabetes

Researchers have developed a new artificial intelligence tool that is able to automatically measure the amount of fat around the heart from MRI scan images.

COVID-19: AIs shortcuts lead to misdiagnosis

COVID-19: AIs shortcuts lead to misdiagnosis

Researchers discovered that AI models have a tendency to look for shortcuts. In the case of AI-assisted disease detection, these shortcuts could lead to diagnostic errors if deployed in clinical settings.

Image fusion method uses AI to improve outcomes

Image fusion method uses AI to improve outcomes

Researchers have developed a new "multi-modal" image fusion method based on supervised deep learning that enhances image clarity, reduces redundant image features and supports batch processing.

Portable hybrid gamma camera should improve cancer diagnosis

Portable hybrid gamma camera should improve cancer diagnosis

Scientists have designed a portable 3D imaging device which will improve the treatment and diagnosis of cancer.

Device rapidly creates 3D images of skin

Device rapidly creates 3D images of skin

A portable 3D printed device produces high-resolution 3D images of human skin within 10 minutes. It could be used to assess the severity of skin conditions.

Popular articles

Subscribe to Newsletter