Automated Detection of Maternal Risk Factors in Resource-Limited Settings

November 12, 2018 | Contributed By - Thomas van den Heuvel, Member IEEE and Chris de Korte, Senior Member IEEE

Mid-range ultrasound device used by a sonographer in a health-care clinic.

Researchers at the Radboud University Medical Center (Nijmegen, the Netherlands) in collaboration with Delft Imaging Systems (Veenendaal, the Netherlands) have developed  a method for automated detection of maternal risk factors using a low-cost ultrasound system that does not require a trained sonographer. The world health organization has reported that 99% of all maternal deaths worldwide occur in developing countries [1]. This corresponds to approximately 820 deaths each day. Ultrasound is commonly used to detect maternal risk factors during pregnancy. Unfortunately, it is hardly used in resource-limited settings because it requires a trained sonographer to acquire and interpret the images, and there is a severe shortage of well-trained medical personnel in these countries. Furthermore, when health care services are limited, it can require a substantial amount of travel time before a pregnant woman can receive medical care. Timely identification of maternal risk factors is, therefore, essential.

 

 

To address this important problem, a group of researchers including PhD candidate Thomas van den Heuvel, Prof. Chris de Korte and Prof. Bram van Ginneken, combined a low-cost ultrasound device with a simple acquisition protocol and automated image analysis software. The acquisition protocol can be taught to any healthcare worker, even those with no knowledge of ultrasound, within a single day. It is also feasible to train non-professionals to use the system. Data for this project was acquired by Dr. Hezkiel Petros at St. Luke’s Catholic Hospital in Wolisso, Ethiopia. The software is able to automatically determine gestational age and detect maternal risk factors such as twin pregnancies and breech presentation. The system that they have developed could, therefore, enable more effective use of ultrasound as a diagnostic tool for pregnant women in resource-limited countries. This should make it possible to better manage obstetric care and refer pregnant women to a health care clinic in time to receive necessary treatment when maternal risk factors are detected [2, 3, 4, 5, 6].

Left: Hezkiel Petros (gynecologist) and Right: Thomas van den Heuvel (PhD candidate) explaining the use of ultrasound imaging to midwives at St. Luke’s Catholic Hospital in Wolisso, Ethiopia.

Bibliography
  1. World Health Organization, UNICEF, UNFPA, The World Bank and the United Nations Population Division, “Trends in maternal mortality: 1990 to 2013: estimates by WHO, UNICEF, UNFPA, The World Bank and the United Nations Population Division,” 2014.
  2.  T. L. A. van den Heuvel, H. Petros, S. Santini, C. L. de Korte and B. van Ginneken, “A step towards measuring the fetal head circumference with the use of obstetric ultrasound in a low resource setting,” in SPIE Medical Imaging, 2017.
  3. T. L. A. van den Heuvel, H. Petros, S. Santini, C. L. de Korte and B. van Ginneken, “Combining Automated Image Analysis with Obstetric Sweeps for Prenatal Ultrasound Imaging in Developing Countries,” in MICCAI Workshop: Point-of-Care Ultrasound, 2017.
  4.  T. L. A. van den Heuvel, D. de Bruijn, D. Moens, A. Beverdam, B. van Ginneken and C. L. de Korte, “Comparison study of low-cost ultrasound devices for estimation of gestational age in resource-limited countries,” Ultrasound in Medicine & Biology, vol. 44, no. 11, pp. 2250-2260, 2018.
  5. T. L. A. van den Heuvel, D. de Bruijn, C. L. de Korte and B. van Ginneken, “Automated measurement of fetal head circumference using 2D ultrasound images,” PloS One, vol. 13, no. 8, p. e0200412, 2018.
  6. T. L. A. van den Heuvel, H. Petros, S. Santini, C. L. de Korte and B. van Ginneken, “Automated fetal head detection and circumference estimation from free-hand ultrasound sweeps using deep learning in resource-limited countries,” Accepted for publication in Ultrasound in Medicine & Biology, 2018.