Teaching Algorithms to Caption Ultrasound Images | Dr Mohammad Alsharid
Original Article Reference
This SciPod is a summary of the conference proceedings ‘Captioning Ultrasound Images Automatically’, from the International Conference on Medical Image Computing and Computer-Assisted Intervention. doi.org/10.1007/978-3-030-32251-9_37
About this episode
Medical professionals require years of training before they can describe ultrasound images of developing foetuses. Dr Mohammad Alsharid and colleagues from the Institute of Biomedical Engineering and Nuffield Department of Women’s and Reproductive Health at the University of Oxford suggest that this task could one day be carried out by machine learning algorithms. In their latest study, the team showed how neural networks, trained by the expert knowledge of real sonographers, could convert subtle features within the images into accurate, readable captions.
This work is licensed under a Creative Commons Attribution 4.0 International License. 
What does this mean?
Share: You can copy and redistribute the material in any medium or format
Adapt: You can change, and build upon the material for any purpose, even commercially.
Credit: You must give appropriate credit, provide a link to the license, and indicate if changes were made.
More episodes
Do Security and Regulation Failures Put Women’s Health Data, Their Privacy and Even Their Safety at Risk?
Recent research from Professor Maryam Mehrnezhad at the Information Security Department, Royal Holloway University of London and a team of researchers reveals widespread privacy, security and regulatory failings in female-oriented health technologies (also known as FemTech). The researchers’ comprehensive analysis demonstrates how current practices leave sensitive health information vulnerable, while highlighting an urgent need for reform across technical, legal and social dimensions of digital healthcare.
Dr. Beate Hoppe | Revealing the Secrets of Fish Health: Improving Research on Aging
The African turquoise killifish, also called Nothobranchius furzeri, is a small, vibrant freshwater species that is making a big splash in aging research. With our aging populations, research into aging and the mechanisms underlying age-related health issues is increasingly important. Scientists in this valuable field prize the killifish because it has a significantly short lifespan at just six to twelve months, making it an ideal model to study age-related diseases. However, as research on this species grows, so does the need for better care and monitoring of their health. In fact, distinguishing between the natural effects of aging and other health issues in these fish, such as pathogens or disease, is crucial in accurately researching age-related phenomena. Moreover, identifying health issues in laboratory fish could help researchers to better maintain health in their fish stocks, improving both experimental results and animal welfare. This is where Dr. Beate Hoppe and her colleagues at the Leibniz Institute on Aging at the Fritz Lipmann Institute, Jena, Germany, step in, pioneering a comprehensive approach to monitoring and managing killifish health that could revolutionize laboratory fish research.
Dr. Ndukaku Omelu | Sustaining Colorectal Cancer Screening in an Uncertain Funding Landscape
Colorectal cancer is a significant health challenge, and ranks as the second leading cause of cancer-related death and the third most common type of cancer in the United States, among men and women combined. Each year, over 52,000 people in the U.S. die from colorectal cancer, with more than 5,300 deaths occurring in California alone. While early detection of colorectal cancer through screening can significantly reduce both its incidence and mortality, ensuring that screening programs remain effective and sustainable is no small feat, particularly in the face of uncertain funding. This pressing issue is at the heart of recent research conducted by Dr. Ndukaku Omelu of the California Department of Public Health, and colleagues, who examined the sustainability of colorectal cancer screening strategies implemented through the California Colon Cancer Control Program (or C4P for short), with a particular focus on how these screening programs would fare in the absence of future C4P funding, a program funded by the Centers for Disease Control and Prevention (or CDC for short).
Dr. Luc Raijmakers | Comparing Simplified Physics-Based Models for Lithium-Ion Batteries
In order to operate safely and efficiently, lithium-ion batteries rely on battery management systems to monitor their state and to control their operation. An essential part of this process is modelling battery behaviour under different conditions to predict performance and prevent failures. To do this efficiently, it is crucial to simplify the underlying physical processes, while sacrificing as little accuracy as possible. Through their research, Dr. Luc Raijmakers and colleagues at the Jülich Research Centre, Germany, compare various different approaches to simplifying simulations. Their results could make it easier for battery operators to decide which approach is best suited to their requirements for accuracy and computational efficiency.
Increase the impact of your research
• Good science communication helps people make informed decisions and motivates them to take appropriate and affirmative action.
• Good science communication encourages everyday people to be scientifically literate so that they can analyse the integrity and legitimacy of information.
• Good science communication encourages people into STEM-related fields of study and employment.
• Good public science communication fosters a community around research that includes both members of the public, policymakers and scientists.
• In a recent survey, 75% of people suggested they would prefer to listen to an interesting story than read it.
Step 1 Upload your science paper
Step 2 SciPod script written
Step 3 Voice audio recorded
Step 4 SciPod published