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
Prof. Abdullah Alrasheed | How Light, Air, and Time Shape the Future of Two-Dimensional Materials
Over the past two decades, materials science has been quietly transforming the technological foundations of everyday life. While consumers notice faster phones and more capable computers, the deeper story unfolds at the scale of atoms. Scientists are learning how to isolate and control materials that are only a few atoms thick, revealing forms of matter whose behavior differs profoundly from their bulk counterparts. These so-called two-dimensional materials promise a new generation of electronics, sensors, and photonic devices. At the same time, they challenge long held assumptions about stability, reliability, and control at the smallest scales. Researchers such as Prof. Abdullah Alrasheed of the King Abdulaziz City for Science and Technology are helping to expand our knowledge and push the boundaries of what is possible in this sphere.
Prof. Debra Zoran | After the Storm: Protecting Companion Animals in Crisis
When disaster strikes, the images that dominate news coverage are almost always human centered. We see flooded neighborhoods, collapsed buildings, families waiting in shelters, and exhausted first responders. Yet woven into nearly every one of those scenes is another presence, often trembling at the end of a leash or peering out from a carrier. Companion animals are not an afterthought in modern life. They are family members, sources of emotional stability, and in some cases essential partners such as service dogs. As natural and human-made disasters grow in frequency and severity, the question of how to protect people inevitably includes the question of how to protect their animals.
Dr. Jeddah Marie Vasquez | Blending Biology and Engineering to Repair Damaged Nerves
When a peripheral nerve is badly damaged due to injury, the consequences can be life-changing. Hands that no longer feel heat or cold, muscles that will not respond to the brain’s commands, and pain that lingers for years are all common outcomes. Surgeons can sometimes stitch nerves back together, but when there is a section of nerve missing entirely, repair becomes far more complex. For decades, researchers have been trying to build better bridges for injured nerve axons to cross. A new interdisciplinary research effort led by Dr. Jeddah Marie Vasquez and Dr. Vijay Kumar Kuna of Research Institutes of Sweden, and their collaborators from Umeå University (Associate Professor Paul Kingham) and University College London (Professor James Phillips), bring together polymer chemistry, materials science, and cell biology to rethink what such a bridge could be made of – and how it might one day be tailored to individual patients.
Dr. Huda Makhluf | The Long Shadow: The Science Behind Long COVID
Four years after the first lockdowns and daily case counts faded from headlines, COVID 19 continues to shape lives in quieter but deeply disruptive ways. For millions of people around the world, the virus did not simply end with a negative test. Instead, it left behind a complex and often invisible condition known as long COVID. This lingering illness challenges how medicine understands recovery, chronic disease, and the long reach of viral infections. In a comprehensive review, Dr. Huda Makhluf of the National University in San Diego, and her colleagues, synthesize what scientists currently know about long COVID and what remains frustratingly uncertain.
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