THIS CONTENT IS BROUGHT TO YOU BY UiT The Arctic University of Norway - read more

AI can help detect heart diseases more quickly

Researchers have developed an artificial intelligence that can automatically measure the heart's structure – both quickly and accurately.

A newly developed AI system may help doctors detect and treat cardiovascular diseases more quickly.
Petter Bjørklund
Petter Bjørklund COMMUNICATIONS ADVISER
Presented by: Presented by: Presented by: UiT The Arctic University of Norway
Published

Artificial intelligence (AI) may become a helpful tool for detecting and treating cardiovascular diseases, according to Durgesh Kumar Singh's research.

He works at the AI centre SFI Visual Intelligence at UiT The Arctic University of Norway.

Singh examined how AI can be used to measure the heart's left ventricle – one of the four heart chambers – based on ultrasound images. The images are taken with an ultrasound probe placed on the patient’s chest.

Researcher Durgesh Kumar Singh believes the AI method could become a promising tool for healthcare services in and outside Norway.

Important for detecting heart diseases

The left ventricle is the heart's main pumping chamber and serves an important function – to pump out oxygen-rich blood to the aorta, which carries the blood to the rest of the body.

If not enough blood is pumped out, the organs won't receive enough oxygen to function properly. This may happen due to diseases or conditions that change the heart's size, thickness, or overall shape.

Examples include high blood pressure and heart-muscle diseases.

The measurements give doctors valuable information about the size and pumping capacity of the left ventricle. This is used to detect potential signs of heart disease.

Singh's results show that his AI method can measure the heart chamber more quickly and accurately. 

He believes it could become a promising tool for healthcare services in and outside Norway.

“We show how deep learning can be used to measure the left ventricle on ultrasound images more accurately and consistently by making the AI more aware of the heart's structure,” Singh says.

A helpful assistant

Deep learning involves getting machines to perform specific tasks without direct human instructions. 

Singh trained an AI model using thousands of ultrasound images of the heart chamber. The dataset contains images from hospitals around the world.

Through this process, the AI taught itself what the left ventricle looks like. It uses this knowledge to find the most important parts of the image for measuring the heart chamber.

“Think of it as an assistant which automatically lays the ruler at the correct place. The computer first finds the best measuring line by itself by outlining the heart's shape. The ruler is then used to read the size along that line,” Singh explains.

Saves valuable time and resources

These measurements are usually done manually by a cardiologist. This involves examining the ultrasound image, drawing a straight line across the left ventricle, and placing measurement points on that line. 

The problem is that it's a time-consuming and delicate process, even for experienced cardiologists.

“It's careful, repetitive work that takes a lot of time. The measurements may also vary depending on the patient's heart anatomy and the person doing the examination,” Singh says.

Singh's method can measure the heart chamber in a matter of seconds. This provides many potential benefits – from faster results for patients to less workload for doctors.

“Automating the most time-consuming parts means that results can be ready during the exam, speeding up diagnosis and treatment. Accurate measurements can also help track subtle heart changes more reliably over months and even years,” he explains.

Fewer unnecessary examinations

An ultrasound examination may cost hospitals and patients up to several thousand Norwegian kroner. Consistent measurements also mean fewer unnecessary exams.

“More accurate and repeatable measurements reduce do-over exams, saving patients' and the healthcare system's time and money,” says Singh.

He examined how well his method measures the heart chamber by comparing it with similar AI models.

The results show that it outperforms these models – both in placing measurement points accurately and overall agreement with human experts.

Works on different types of ultrasound images

Doctors measure the heart chamber using two types of ultrasound images: so-called B-mode and M-mode images. 

B-mode images present the ultrasound waves as a two-dimensional image, while M-mode images show the heart wall’s movements through a scanline.

Singh's method works on boththese image types, making it more useful in real clinical settings.

“Depending on the doctor's needs or preferences, the measurements can be displayed on either image type,” Singh says.

The left ventricle displayed via a B-mode (left) and M-mode ultrasound image (right). Singh's AI was trained on thousands of ultrasound images like these.

Close collaboration with the medical industry

The project was carried out in close collaboration with GE HealthCare, one of several industrial partners in SFI Visual Intelligence.

One goal of the project was to develop an AI-based algorithm that can be integrated into GE HealthCare's ultrasound scanners.

Erik Steen is a chief engineer at GE HealthCare, and he says there's a need to increase the productivity of these examinations. 

“This need is echoed by several clients and experts worldwide. Durgesh's work can contribute to increased productivity by automating measurements needed to uncover heart diseases like thickened heart wall,” he says.

Will be tested in controlled environments

Based on this potential, GE HealthCare plans to test the method in a controlled and safe environment. They hope his work may eventually be incorporated into their scanners.

But it will take several rounds of thorough testing before this happens, Steen says. This is to ensure that the method measures the heart chamber correctly.

“It's important for us to check that these methods are robust and work on a large number of patients with varying image quality. We also need to document that they are just as good as or better than human experts who measure by hand,” he explains.

Doctors still have full control

Singh's findings show how useful AI technology could be for detecting and treating heart diseases. 

But what will happen to the doctors? Will they eventually be replaced by artificially intelligent algorithms?

Singh assures us that this is not the case. AI is meant to assist doctors with their clinical work. The doctors will always be there to make sure that the AI does the job properly.

“It's designed to help, not replace. The technology's purpose is to remove the most tedious and time-consuming steps. The doctors are still keeping control,” Singh says.

Reference:

Singh, D.K. Towards more accurate and label-efficient Left Ventricle Automatic Measurements, Doctoral Dissertation at UiT The Arctic University of Norway, 2025. 

More content from UiT:

health partner medical methods technology uit-arctic-university diseases
Powered by Labrador CMS