Elizaveta Savochkina (Elizabeth) is a DPhil Candidate in Biomedical Engineering at the University of Oxford. Her research is focused on the advancement of medical imaging through deep learning under the supervision of Prof. Alison Noble.
She completed her MSc in Robotics and Autonomous Systems at Sussex University. Elizabeth graduated from Royal Holloway, University of London with BSc in Economics and Mathematics.
- Machine Learning & Deep Learning
- Computer Vision
- Medical Imaging (Ultrasound)
Elizabeth primarily focuses on gaze estimation and automation of guidance techniques for the first trimester US scanning where the saliency predictions direct novice and experienced sonographers’ gaze to important anatomy.
Her research project titles are:
1. "First trimester gaze pattern estimation using stochastic augmentation policy search for single frame saliency prediction". Manuscript accepted to MIUA2021 which mainly focused on data augmentation techniques to help reduce data imbalance and over-fitting whilst improving the segmentation performance.
2. "First trimester video saliency prediction using cLSTMU-Net with stochastic augmentation". Manuscript accepted to ISBI2022 where spatio-temporal connectivity was explored to differentiate between the static and fast-moving US frames, improving saliency predictions.
1. First Trimester Video Saliency Prediction using cLSTMU-Net with Stochastic Augmentation. ISBI 2022. (accepted yet to be published)