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. Dr. Dietmar Thurnher | Von der Stille zum Überleben: 150 Jahre Laryngektomie und die Zukunft der Stimme
Im späten neunzehnten Jahrhundert stand die Medizin an der Schwelle zwischen Verzweiflung und Entdeckung. Krebs des Kehlkopfes, jener Struktur, die uns die Stimme verleiht und unsere Atemwege schützt, verlief fast immer tödlich. Chirurgen verfügten nur über wenige Werkzeuge und noch weniger Erfolge. Dann veränderte im Jahr 1873 eine mutige und kontroverse Operation alles. Theodor Billroth führte die erste totale Laryngektomie durch und entfernte einem menschlichen Patienten den gesamten Kehlkopf. Es war ein radikaler Eingriff, der ein Leben rettete – allerdings um den Preis des Sprachvermögens und der natürlichen Atmung. Dieser Moment markierte den Beginn einer langen und sich stetig weiterentwickelnden Reise in der Behandlung von Kopf-Hals-Karzinomen.
Prof. Peter Littrup | The Future of Cancer Care May Already Be Here, and May Hold Faster Promise for Neurologic Diseases
For decades, cancer treatment has followed a familiar path. A tumor is found, surgery removes it, radiation burns what remains, and chemotherapy or immunotherapy attempts to destroy cells that may have spread elsewhere. These treatments have saved countless lives, yet they often come with immense physical, emotional, and financial costs. Many patients endure fatigue, pain, scarring, organ damage, mounting bills and lifelong side effects. However, the extraordinary advances of modern medicine have often included the commercial viability of a proven medical product, regardless of its cost and accessibility. The dream of a gentler, more precise, and more effective cancer treatment has remained elusive.
Prof. Vibeke Vågenes – Cecilie Grevstad | When a Monthly Cycle Becomes a Barrier: Why Menstrual Health Matters for Girls’ Education in Tanzania
For millions of girls around the world, education represents hope. It offers the possibility of independence, financial security, improved health, and the chance to shape a different future from previous generations. Yet for many girls, the path to education is filled with obstacles that receive little attention. Some are obvious, such as poverty or long journeys to school. Others are far less visible, hidden behind silence, embarrassment and social expectations. One of the most overlooked is menstruation.
Dr. Gary Blau – Dr. Kyle Stephens | The Hidden Costs of the Digital Workplace: Why Employee Deviant Work Behaviour Needs an Additional Lens
The work of Dr. Gary Blau and Dr. Kyle Stephens of Temple University, Philadelphia, Pennsylvania, USA asks an important question that is becoming increasingly relevant around the world. If the workplace has fundamentally changed, shouldn’t the way we measure employee deviant work behaviour change too? Their research argues the answer is yes because the consequences reach far beyond academic debate. Traditional work behaviour deviance examples include: someone deliberately arrives late, spending long coffee breaks chatting with colleagues, or working more slowly than usual. Others are spreading rumours, bullying coworkers, or damaging company property. These are the kinds of in-person, on-site deviant behaviours researchers have investigated, that is, why employees sometimes act against the interests of employing organisations.
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