EFSUMB Newsletter
European Federation of Societies for Ultrasound in Medicine and Biology
Winners of the EFSUMB Young Investigators’ Award
Best technical abstract – Thomas LA van den Heuvel Thomas van den Heuvel is a postdoctoral fellow at the Radboud university medical center in the Netherlands. His research focuses on combining point-of-care ultrasound devices with deep learning solutions to facilitate diagnosis in resource limited countries. During his PhD, he developed a deep learning software that automatically detects twin pregnancies, estimates gestational age and determines fetal presentation. The system is so easy to operate that any health care worker can use the device after two hours of training. Currently, the methods are implemented in Android based smartphones to further facilitate widespread use of this technology.
Introducing prenatal ultrasound screening in resource-limited settings using artificial intelligence Thomas L. A. van den Heuvel; Bram van Ginneken; Chris L. de Korte Dept. Radiology and Nuclear Medicine, Radboud university medical center, Nijmegen, the Netherlands
making them suitable imaging devices for areas in the world that are difficult to reach and which lack stable power supply. Even though these devices have become more affordable and portable in recent years, they are still barely used in resource-limited settings while the World Health Organization recommends “one ultrasound scan before 24 weeks of gestation” [2]. The main reason that pregnant women in resource-limited settings have limited access to ultrasound imaging, is caused by the lack of well-trained medical personnel that is capable to both acquire and interpret prenatal ultrasound images. Training midwives to be able to perform prenatal ultrasound screening takes months till years, which impedes widespread application of ultrasound in these countries. In my work, I have focused on development of artificial intelligence software that can automatically interpret prenatal ultrasound images. By combining this software with a standardized acquisition protocol, it becomes possible to train a midwife in two hours to acquire the ultrasound images, which can be automatically interpreted by the software.
Methods
Abstract Introduction Each day, more than 820 women die as a consequence of their pregnancy. Worldwide, 99 % of these maternal deaths occur in resource-limited settings [1]. Ultrasound imaging is widely used for prenatal screening. These days, ultrasound devices only cost a few thousand dollars and they can be connected to tablets and smartphones,
Ultraschall in Med 2020; 41: 443–448
For the acquisition of the ultrasound data we used a standardized acquisition protocol that consists of six predefined sweeps with the ultrasound transducer over the abdomen of the pregnant woman (▶ Fig. 1A). This protocol was introduced by DeStigter et al. [3] and takes less than two hours to learn. My research focused on the development of deep learning software that could automatically interpret the ultrasound data acquired using these sweeps. First, a sys-
Thomas van den Heuvel
tem was developed for automated measurement of the fetal head circumference (HC), using 1334 acquired ultrasound images acquired with the high-end Voluson E8 and Voluson 730 (General Elecric, Austria) [4]. Secondly, a study was performed in Ethiopia, were the standardized acquisition protocol was acquired from 183 pregnant women using the mid-range SonoAce R3 (Samsung Medison, Korea) [5]. Thirdly, the standardized acquisition protocol was acquired from another 318 pregnant women in Ethiopia using the portable and low-cost MicrUs (Telemed, Lithuania) [6].
Results The system for automated measurement of the HC using the high-end ultrasound device showed state of the art results on the largest dataset described in literature [4]. The study showed that automated measurement of the HC in 2 D images was feasible with an accuracy similar to the measurement made by a trained sonographer. This dataset was made publicly available
443
EFSUMB Newsletter
focusing on the development of the first prototype that can be used in clinical practice and therefore hopefully improves prenatal care in resource-limited settings.
References [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
â–ś Fig.1A Visualization of the standardized acquisition protocol, consisting of six predefined free-hand sweeps with the ultrasound transducer over the abdomen of the pregnant woman. B Clipart showing a midwife using a hand-held ultrasound device for prenatal screening.
[7] and I setup a challenge (https://hc18. grand-challenge.org/) which has currently more than one thousand submissions. Using the dataset acquired from 183 pregnant women using the mid-range ultrasound device in Ethiopia, I was able to show that a deep learning system could automatically estimate gestational age using the standardized acquisition protocol. The dataset of 318 pregnant women scanned with the low-cost ultrasound device was used to develop artificial intelligence algorithms that not only automatically estimates gestational age, but also determines fetal presentation and detects twin pregnancies. This makes it possible for midwives to know when to send a woman to a health
444
care facility for treatment, which is of great importance in resource-limited setting because this can take more than one day to reach. Both breech presentation and twin pregnancies are high risk deliveries that preferably should take place in close proximity of a health care facility.
Discussion and Conclusion I have developed artificial intelligence software that can be combined with a standardized ultrasound acquisition protocol to automatically detect prenatal risk factors. This makes it possible to train midwives within two hours in order to perform prenatal ultrasound screening in rural areas of resource-limited settings. Current efforts are
[2] World Health Organization. WHO recommendations on antenatal care for a positive pregnancy experience, World Health Organization 2016 [3] DeStigter KK, Morey GE, Garra BS et al. Lowcost teleradiology for rural ultrasound, in IEEE Glob Humanit Technol Conf 2011 [4] van den Heuvel TLA, de Bruijn D, de Korte CL et al. Automated measurement of fetal head circumference using 2D ultrasound images. PloS One 2018; 13 (8): e0200412 [5] van den Heuvel TLA, Petros H, Santini S et al. Automated fetal head detection and circumference estimation from free-hand ultrasound sweeps using deep learning in resource-limited countries. Ultrasound in Medicine & Biology 2018 [6] van den Heuvel TLA. Automated low-cost ultrasound: improving antenatal care in resource-limited settings. Universiteitsbibliotheek Nijmegen 2019 [7] van den Heuvel TLA, de Bruijn D, de Korte CL et al. Automated measurement of fetal head circumference using 2D ultrasound images [Data set]. Zenodo 2018
Ultraschall in Med 2020; 41: 443–448
Winners of the EFSUMB Young Investigators’ Award
Best Clinical Abstract – Tobias Todsen MD PhD I am a senior registrar in OtolaryngologyHead & Neck Surgery and clinical researcher in head and neck ultrasound and medical education. I teach ultrasound at a pre- and postgraduate level, and I am a part of a global health initiative to promote surgeonperformed ultrasound in resource-limited countries. Before my specialization, I received broad clinical training as a Foundation Doctor with 18-month rotation between the Dept. of Internal Medicine, Surgery, and General Medicine at Queen Ingrid’s Hospital in Greenland. I have been teaching clinical skills and conducted educational research for more than ten years and have skills within producing educational videos, virtual reality content and online apps with more than 50.000 views yearly: open-surgery.com – Vimeo – Youtube
A randomized multicenter clinical trial comparing transoral ultrasound versus standard of care in the management of patient suspected with peritonsillar abscess Tobias Todsen, MD, PhD Department of Otorhinolaryngology, Head and Neck Surgery & Audiology, Rigshospitalet, Denmark
Background Peritonsillar abscess is a common deep head and neck infection in younger adults primarily treated with needle aspiration and surgical drainage. However, it is difficult to distinguish between a peritonsillar phlegmon and abscess on the clinical ex-
Ultraschall in Med 2020; 41: 443–448
amination only, and many patients will have unsuccessful blind needle aspiration attempts performed. This trial aims to explore whether a new technique for transoral ultrasound-guided needle aspiration can decrease the number of unsuccessful needle aspiration and improve the management of patients with peritonsillar infection.
Material & Methods A randomized, controlled multicentre trial were conducted at the departments of Otolaryngology, Head and Neck Surgery at Rigshospitalet, and Odense University Hospital. The patients referred with peritonsillar abscess to the departments were randomized to either standard of care with a clinical examination (control group) or a clinical examination together with pointof-care transoral ultrasound (intervention group). The number of performed needle aspirations and the diagnostic accuracy were evaluated using binary logistic regression and a generalized estimating equation to compare the results between the two groups.
Results Ninety-five patients were included in the study (58 at Rigshospitalet and 37 at Odense University Hospital) by 28 different physicians treating the patients. Forty-seven patients were allocated to the intervention group and 48 patients to the control group. The results demonstrated that 31.9 % fewer patients in the intervention group were initially treated with needle aspirations compared to the control group
Tobias Todsen MD PhD
(P < 0.01), and the total number of needle aspirations decreased from 2.4 to 1.7 mean per patient with the use of transoral ultrasound (P < 0.01). The diagnostic accuracy (self-reported) was 80.9 % in the intervention group versus 72.9 % in the control group (P = 0.51). Though ultrasound was available in the intervention group, still 40 % of the needle aspiration attempts were performed blind.
Conclusion Transoral ultrasound can improve patient management and successfully decrease the number of needle aspiration attempts in patients suspected with peritonsillar abscess.
445
EFSUMB Newsletter
EFSUMB Fellow – Boris Brkljacic, Croatia Prof Boris Brkljacic was born in 1963, in Zagreb, Croatia, and is currently full professor of radiology at University of Zagreb School of Medicine, vice-dean for science of University of Zagreb School of Medicine and chairman of the Board of Directors of European Society of Radiology, member of the Executive Council of International Society of Radiology and member of the Executive Board of International Society for Strategic Studies in Radiology. Since 2008 he is president of the Croatian Society of Ultrasound in Medicine and Biology of Croatian Medical Association. Prof Brkljacic was a member of the Education and Professional Standards committee of EFSUMB (2008–2011) gave the “EUROSON lecture” in vascular ultrasound in Madrid in 2012. From 2011–2017 he was member of the Executive council of European Society of Radiology, and in the period of 2017–2022 is member of the Board of ESR where he strongly promotes cooperation between the ESR and EFSUMB. He is president of European Congress of Radiology 2020 and president of ESR 2019–2020.
He is the best-known expert for ultrasound in Croatia and neighbouring countries, especially in the field of vascular ultrasound, breast ultrasound and interventional ultrasound. Together with colleagues from Slovenian Society of Ultrasound he organises for several years joint national ultrasound congresses of Croatia and Slovenia. One of his major achievements in the field of ultrasound in Croatia and neighbouring country was the establishment of the educational programme in vascular ultrasound, that runs since 1998, that is very well known and highly esteemed. In 43 courses, under the auspices of University of Zagreb School of Medicine, Professor Brkljacic and his team trained between 1998 and 2020 more than 550 physicians (radiologists, angiologists, vascular surgeons and others) from Croatia, Slovenia, Bosnia-Herzegovina, Macedonia, Montenegro, Serbia and Kosovo in vascular ultrasound. Professor Brkljacic is editor in chief of the Journal of Ultrasound (SIUMB), and is a member of the international editorial board
Boris Brkljacic
of Ultraschall in der Medizin, Magyar Radiologia, Polish Journal of Ultrasonography, lJltrasonographia Romana (Romania), Radiology and Oncology (Slovenia).
EFSUMB Upcoming webinars
▪ clinical value of CEUS in ggllbladder disease Xiang Fei ▪ CEUS diagnosis of new hepatic nodules in patients with colorectal cancer during chemotherapy Guang-Jian Liu ▪ Combined application of navigation and contrast-enhanced ultrasound in liver tumor Kai Li
▪ value of CEUS applications in thyroid diseases Wen Luo ▪ Significance and value of CEUS in thyroid disease diagnosis and treatment Hong Yang ▪ Application of contrast-enhanced ultrasound in differential diagnosis of complex gynaecology masses Xinling Zhang
EFSUMB Euroson Schools
446
Ultraschall in Med 2020; 41: 443–448
Ultraschall in Med 2020; 41: 443â&#x20AC;&#x201C;448
447
EFSUMB Newsletter
448
Ultraschall in Med 2020; 41: 443â&#x20AC;&#x201C;448