From entertainment to commerce, artificial intelligence (AI) is transforming many aspects of life and has the power to improve diagnostics. Next-generation healthcare technology has started implementing many AI-powered tools to improve efficacy, patient safety, and enhance the clinical experience.1
There are multiple image capture and analysis capabilities that can be augmented by an AI application for each task.2 These skills include:
• Classification – Identifying objects that are present in the scan
• Segmentation – finding organ boundaries
• Navigation – visualization of how best to get an optimal scan
• Quality Assessment – Determining whether the scan can be used to make a diagnosis
• Diagnostics – Check what is wrong with the imaged object
Almost every woman will need an ultrasound at some point during her treatment. There is tremendous potential for AI to support repetitive tasks and offer promising advances in transforming the workload through the use of ultrasound in obstetric and gynecological (OB/GYN) care.2
Can AI have an impact on obstetrics/gynaecology?
According to a study published in Ultrasound in obstetrics and gynecologyAI has had little impact on the OB/GYN field so far.2 However, it’s well on its way to making waves within the industry. Recently, there has been a push for collaboration between AI developers and ultrasound professionals.2 Medical device manufacturers have heeded this call to action and started innovating and implementing AI technology in ultrasound solutions for women’s health.
It is important to monitor and monitor the growth and development of the fetus throughout pregnancy. Ultrasonography is one way to track these changes.3 One of the conditions of concern to clinicians is congenital heart disease (CHD), one of the leading organ-specific birth defects and the leading cause of infant morbidity and mortality from congenital malformations. When it comes to prenatal diagnosis of CAD, two-dimensional ultrasonography has poor accuracy—only 15 to 39 percent—due to the complex anatomy and small size of the fetal heart.4
To address this, tools and solutions using AI have been developed to improve visualization and allow physicians to more accurately diagnose CAD.4 One tool, known as Fetal Intelligent Navigation Echocardiography (FINE), integrates spatial-temporal image correlation volume datasets using “intelligent navigation” technology to simplify fetal cardiac exams and reduce operator dependency.
Researchers have studied FINE for the last few years to determine its accuracy. In a 2020 publication, Yeo and Romero found that FINE:
• Helps healthcare providers evaluate both normal and abnormal fetal hearts.
• Can automatically provide nine standard fetal echocardiographic views in 96 to 100 percent of normal fetal heart cases.
• Can provide clinically useful information about cardiac structure and function in both normal and abnormal fetal hearts when color Doppler is enabled.
• Has high sensitivity (98 percent) and specificity (93 percent) for detecting CAD.4
FINE technology, known exclusively as 5D Heart™ on Samsung ultrasound systems, was developed to provide physicians and pregnant mothers with high-quality prenatal screening and CAD diagnosis.4
Because obstetric ultrasound is time-consuming, the use of AI can also reduce exam time and improve workflow.3 In very fast-paced environments, clinicians seek accuracy and speed in diagnostic tools. From administrative workflow to clinical documentation to patient admission, AI can help with all aspects of the diagnostic process.1
What the future holds for AI and ultrasound imaging
Experts and research trends continue to show how AI will revolutionize the field of medical imaging in the future. A recently published study in the National Library of Medicine estimates that AI applications have the potential to reduce annual US healthcare costs by $150 billion by 2026.1
Some fear AI algorithms will replace healthcare providers, but they will actually function as clinical support tools. By working together with AI algorithms, doctors can better ensure that tests are performed accurately and the correct diagnosis is made. In order to improve patient care and reduce costs, we must encourage and support providers to learn more about AI applications and to use them extensively in practice. We continue to anticipate new and updated AI tools to stay at the forefront of imaging and OB/GYN care.
references
1. Bohr A, Memarzadeh K. The rise of artificial intelligence in healthcare applications. National Library of Medicine. 2020;25-60. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7325854/ . Published June 26, 2020. Accessed September 20, 2022.
2. Drukker L, Noble JA, Papageorghiou AT. Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound obstetrics gynec. 2020;56(4):498-505.
3. Chen Z, Liu Z, Du M, Wang Z Artificial intelligence in obstetric ultrasound: an update and future applications. Front Med (Lausanne). Available at: https://www.frontiersin.org/articles/10.3389/fmed.2021.733468/full . Published August 27, 2021. Accessed September 20, 2022.
4. Yeo L, Romero R. New and advanced features of fetal intelligent navigation echocardiography (FINE) or 5D heart. J Matern Fetal Neonatal Med. 2022;35(8):1498-1516.
