Diagnosis of such problems before the baby is born, allowing for prompt treatment within a week after birth, is known to markedly improve the prognosis, so there have been many attempts to develop technology to enables accurate and rapid diagnosis. However, today, fetal diagnosis depends heavily on observations by experienced examiners using ultrasound imaging, so it is unfortunately not uncommon for children to be born without having been properly diagnosed. In recent years, machine learning techniques such as deep learning have been developing rapidly, and there is great interest in the adoption of machine learning for medical applications. Machine learning can allow diagnostic systems to detect diseases more rapidly and accurately than human beings, but this requires the availability of adequate datasets on normal and abnormal subjects for a certain disease. Unfortunately, however, since congenital heart problems in children are relatively rare, there are no complete datasets, and up until now, prediction based on machine learning was not accurate enough for practical use in the clinic.
A research group led by scientists from the RIKEN Center for Advanced Intelligence Project (AIP), collaborating with Fujitsu Ltd. and Showa University, decided to take on the challenge. They have successfully developed a new machine learning technology that can accurately predict disease using relatively small and incomplete collections of data. Typically, fetal heart experts determine if parts of the heart, such as valves or blood vessels, are in the correct positions by comparing normal and abnormal fetal heart images and relying on their professional experience. The RIKEN researchers found a computer process that was similar to how humans worked called "object detection." This allowed the AI to both distinguish position and classify multiple objects appearing in fetal heart images.
The announcement was one of several at the Fujitsu Forum in Munich to feature AI developments. Fujitsu Intelligence Technology brings together the company's AI work in Japan and around the world to run it from Vancouver, Canada. The area has many research institutions such as the University of Toronto engaged in AI and quantum computing research, as well as startup technology companies. The government there is pushing the country towards AI. "In Vancouver and across British Columbia, Fujitsu will have the opportunity to collaborate with our state-of-the-art universities and research facilities to discover new ways that artificial intelligence can help solve local and global challenges," said John Horgan, Premier of the Province of British Columbia.
Cardiology Both children and adults can have cardiac problems. Congenital problems predominate in childhood, whereas adults are more likely to suffer from conditions associated with age. In both cases, however, accurate diagnosis depends on access to health care and the availability of trained specialists. In two recent studies, Arnaout et al. and Yao et al. showed how machine learning can supplement specialist care in both pediatric and adult cardiology settings. Arnaout et al. analyzed fetal ultrasound images to detect congenital heart disease. Yao et al. used machine learning in conjunction with electrocardiogram imaging to detect adults with low ejection fraction (a measure of the amount of blood that the heart succeeds in pumping), which is a risk factor for subsequent heart failure. In each case, the technology should help to improve diagnostic accuracy and access to appropriate treatment. Nat. Med. 27 , 815, 882 (2021).
Samsung's efforts to make a difference in the medical field are once again being recognized. The company's 5D Heart Color ultrasound technology is currently on the cover of a leading academic journal that focuses on women's healthcare. This is the second medical invention by the South Korea-headquartered company that is gracing the cover of an academic journal since last year. On Sunday, Samsung proudly shared on its online Newsroom the appearance of its invention on the cover of Ultrasound in Obstetrics & Gynecology (UOG), the official journal of the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG). The 5D Heart Color technology is the creation of Samsung Medison, an affiliate of Samsung Electronics that has been manufacturing diagnostic ultrasound systems since 1985.