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
Professor Mamta Jain | Improving Hepatitis C Screening and Care: Approaches for Reaching Underserved Populations
Research from Professor Mamta Jain at UT Southwestern Medical Center and her colleagues reveals how electronic alerts, patient navigation, and mailed outreach can significantly increase hepatitis C screening and treatment in traditionally difficult-to-reach populations. Their work demonstrates that while electronic reminders are effective, combining multiple approaches with adequate clinical staffing and resources leads to the greatest improvements in patient care across all stages of the hepatitis C care continuum.
Dr. Jon Reinders | A genetic breakthrough for farming: editing corn inside the plant, not the lab
Corn is a cornerstone of modern agricultural food production, particularly in North America. Humans have selectively bred such crops over generations to create better yields, improved appearance and flavor and enhanced disease resistance. However, what if we could skip these arduous rounds of selective breeding and improve a crop’s stability and reliability regardless? Deep within the genetic blueprint of every maize kernel, scientists are aiming to achieve just this. In a recent groundbreaking study, Dr. Jon Reinders of Corteva Agriscience and his colleagues have unveiled a powerful new way to create genetically improved corn, not in a lab dish, but inside the plant itself. This new method is faster, cleaner, safer, and could transform how we grow our most essential crops.
Dr. Hanieh Razzaghi | Behind the Screens: Improving Health Outcomes with Better Data
We can imagine our health as a jigsaw, with each individual piece representing a different aspect of our medical history. These pieces might include blood test results, X-ray images or the notes taken by a doctor as we describe our symptoms. These jigsaw pieces are ultimately recorded and stored in electronic health records (or EHRs). EHRs are a valuable resource, providing an overview of someone’s health and they could have the potential to allow clinicians and researchers to unlock new medical insights. However, there’s a fly in the ointment – not all the pieces in such records always fit together correctly, and they may not completely capture the required information. Some clinical event documentation may not be complete, others do not align with related pieces, and some events are even missing entirely. This data quality problem was tackled by Dr. Hanieh Razzaghi of the Children’s Hospital of Philadelphia, and her colleagues, in their innovative work on the PRESERVE study, a research project exploring chronic kidney disease in children (the PRESERVE study itself was led by Drs. Michelle Denburg and Christopher Forrest). Using EHRs from 15 different hospitals across the United States, the team aimed to understand how various treatments could potentially slow down chronic kidney disease progression. However, initially, they had to make sure that the data they were relying on were accurate, reliable, and suitable for the required complex analyses.
Dr. Yassir Mahgoub | New Insights into Severe Depression Towards a Breakthrough in Treatment
Associate Professor Yassir Mahgoub and his team at Penn State University have uncovered an important link between melancholia – a severe form of depression that often doesn’t respond to treatment – and catatonia – a condition characterized by abnormal movements and associated with schizophrenia. The researchers analyzed case studies involving six patients who had been hospitalized for severe depression. All six patients experienced significant relief from their depressive symptoms by taking lorazepam – a drug typically used to treat catatonia. This discovery reveals a potential new avenue for treating severe, treatment-resistant depression.
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