Richard Droste

PhD Student in Medical Imaging

University of Oxford


I am a final-year PhD student at the University of Oxford, striving to advance medical imaging through artificial intelligence. I work under the supervision of Prof. Alison Noble at the Institute of Biomedical Engineering and my research is part of the interdisciplinary PULSE (Perception Ultrasound by Learning Sonographic Experience) project, which aims to build machine learning systems that capture the expertise of sonographers in order to enable the widespread deployment of fetal ultrasound screenings.

I completed my B.Sc and M.Sc. degrees in mechanical engineering at ETH Zurich (Swiss Federal Institute of Technology), where I graduated with distinction in 2017. Before commencing my PhD, I worked as an intern at Siemens Healthcare (2015) and McKinsey & Company (2016), and as a research assistant at the Institute for Biomedical Engineering, ETH Zurich (2017). During my studies and internships I worked on research and engineering projects ranging from life support systems for space flight to magnetic resonance imaging (MRI) for cardiac and neuro applications.


  • Machine Learning & Deep Learning
  • Computer Vision
  • Medical Imaging (Ultrasound & MRI)


  • Currently: PhD in Engineering Science, (graduating 2021)

    University of Oxford

  • MSc in Mechanical Engineering, 2017

    ETH Zurich

  • BSc in Mechanical Engineering, 2014

    ETH Zurich


Unified Image and Video Saliency Modeling

16th European Conference on Computer Vision (ECCV 2020). *RD and JJ contributed equally to this work. Spotlight Presentation.

Automatic Probe Movement Guidance for Freehand Obstetric Ultrasound

23rd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2020).

Safety Indices of Ultrasound: Adherence to Recommendations and Awareness During Routine Obstetric Ultrasound Scanning

European Journal of Ultrasound. *LD and RD contributed equally to this work. Selected as Editor's Choice.

Discovering Salient Anatomical Landmarks by Predicting Human Gaze

IEEE International Symposium on Biomedical Imaging (ISBI) 2020. Oral presentation. Runner up for Best Paper Award.

Self-supervised Representation Learning for Ultrasound Video

IEEE International Symposium on Biomedical Imaging (ISBI) 2020.

Expected‐value bias in routine third‐trimester growth scans

Ultrasound in Obstetrics & Gynecology. *LD and RD contributed equally to this work.

OC10.02: Bioeffects safety indices of ultrasound: quantifying adherence to recommendations on routine obstetric scan

ISUOG World Congress 2019. Oral presentation. *LD and RD contributed equally to this work.

OC19.02: A novel eye tracking study: how common is expected value bias in fetal growth scan assessment?

ISUOG World Congress 2019. Oral presentation. *LD and RD contributed equally to this work.

Towards Capturing Sonographic Experience: Cognition-Inspired Ultrasound Video Saliency Prediction

23rd Conference on Medical Image Understanding and Analysis (MIUA) 2019. Oral presentation. Best paper award.

Spatio-temporal Partitioning and Description of Full-length Routine Fetal Anomaly Ultrasound Scans

IEEE International Symposium on Biomedical Imaging (ISBI) 2019. Oral presentation.

Ultrasound Image Representation Learning by Modeling Sonographer Visual Attention

26th International conference on Information Processing in Medical Imaging (IPMI) 2019.