24 January 2019

Many pregnant women in developing countries do not receive an ultrasound examination. As a result, pregnancy risks often go unnoticed, which contributes to the high maternal mortality rates in these countries. To help solve this problem, Thomas van den Heuvel of Radboudumc has developed a low-cost ultrasound system that can automatically detect gestational age, breech presentation and twin pregnancies. During his recent defense of his PhD thesis on this research, he concluded: “We hope that this low-cost system will result in more women receiving ultrasound examinations, and if pregnancy risks are detected, that these women will be referred to a hospital.”

Worldwide, more than 800 women die every day in developing countries as a result of complications related to their pregnancy. Many of them do not receive an ultrasound examination during their pregnancy. As a result, risk factors for difficult deliveries are not detected in time. Ultrasound examinations are expensive and there is a severe shortage of specialists in developing countries who can make and interpret ultrasound images.

Low-cost and automated ultrasound system
Biomedical technologist Thomas van den Heuvel developed a low-cost ultrasound system that can automatically interpret ultrasound images. To do so, he used a device costing a few thousand euros, which can be connected to a laptop computer. In comparison, ultrasound devices used in the Netherlands cost between 20,000 and 200,000 euros. This new system can also help women in areas without electricity.

Deep learning
The protocol for making the ultrasound images can be taught to anyone within one day. Van den Heuvel: “In this protocol, the midwife makes three vertical and three horizontal sweeps with the ultrasound transducer across the abdomen of the pregnant woman. Each sweep yields approximately 100 images.” The system then interprets the ultrasound images. To achieve this, Van den Heuvel used ‘deep learning’. He showed the system many examples of ultrasound images with various cross-sections of the fetus. Based on these examples, the system learned to recognize these cross-sections by itself.

Algorithms
The system can determine the gestational age based on automatic measurements of the head circumference of the fetus on the ultrasound images. The system can also recognize twins or a breech presentation. Van den Heuvel compares the automatic analysis of ultrasound images to the image recognition system used by a self-driving car. “For example, the algorithms in the car need to distinguish people from trees. I use similar algorithms for the ultrasound system. The difference is then that it needs to be able to distinguish a single fetus from twins”

Prototype
In March, Van den Heuvel will return to Ethiopia to test the first prototype of his system. “We plan to give the prototype to midwives and see if they are able to use it. We will also determine whether the information provided by the system is used by the midwives to refer pregnant women with risk factors to a hospital” His goal is for women with pregnancy risks to receive appropriate care when they need it. “At present, many pregnant women in developing countries visit a hospital only when it is too late. With this system we hope to detect risk factors in a timely manner and, in combination with the determination of gestational age, we can advise women when they should to go to the hospital,” concludes Van den Heuvel. 

Thomas van den Heuvel is member of theme Rare cancers.

Related news items


More expertise needed for patients with prolonged Disorder of Consciousness

14 November 2019

Willemijn van Erp published in the Annals of Neurology that nearly 80% of people with Unresponsive Wakefulness Syndrome, formerly referred to as ‘vegetative state’, are not given a correct description of the diagnosis when they are discharged from the hospital.

read more

Martinus van Marum prize call for proposals

14 November 2019

The Martinus van Marum prize is given to young researchers (<5 years after PhD) for the original research they have conducted in science and technology.

read more

1.5 million for research into young people with mild intellectual disabilities

13 November 2019

Researchers from the Radboud University and Radboudumc will partner with social organisations to map how often young people with mild intellectual disabilities have psychological problems and how they can be treated. The project was recently awarded a subsidy of 1.5 million euro by ZonMw.

read more

Bart van de Warrenburg appointed visiting professor at the UKM Medical Centre in Kuala Lumpur

11 November 2019

Neurologist and Principal Investigator at the Donders Institute Bart van de Warrenburg has been appointed visiting professor at the UKM Medical Centre in Kuala Lumpur.

read more

KNAW Van Leersum beurs for Mohammad Alsady

7 November 2019

Mohammad Alsady, theme Disorders of movement, received the “KNAW Van Leersum beurs”.

read more

3D breast ultrasound elastography to improve breast cancer detection

5 November 2019

One out of seven women will be diagnosed with breast cancer during their life. Early detection of breast cancer is important to increase the survival rate. Gijs Hendriks graduated recently on a new technique, 3D elastography, to detect breast cancer better.

read more