Scholar
Muhammad Asad
Google Scholar ID: SUS0SHIAAAAJ
Senior AI/Data Scientist, Medtronic | Honorary Research Fellow, DERI
Citations & Impact
Citations
776
H-index
10
i10-index
10
Publications
20
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- Holds 11 granted patents and has published 20+ papers in top-tier conferences and journals. Served as a reviewer for top-tier conferences and journals in the field. Recent publications and contributions include: Adaptive Multi-scale Online Likelihood Network for AI-assisted Interactive Segmentation (International Conference on Medical Image Computing and Computer Assisted Intervention 2023), FastGeodis: Fast Generalised Geodesic Distance Transform (Journal of Open Source Software 2022), ECONet: Efficient Convolutional Online Likelihood Network for Scribble-based Interactive Segmentation (MIDL 2022). Additionally, released multiple open-source code repositories such as MONet-MONAILabel, FastGeodis, numpymaxflow, torchmaxflow, MONAI Label v0.3.2, ECONet-MONAILabel, etc.
Research Experience
- Currently a Senior AI/Data Scientist at Medtronic Digital Surgery, UK, and an Honorary Research Fellow at Digital Environment Research Institute (DERI), Queen Mary University of London, UK. Previous roles include Senior Research Scientist at Motive (remote), Research Fellow at King's College London, UK, and Senior Research Engineer II at Imagination Technologies, UK. Worked primarily on designing, training, publishing, and optimising AI models, with projects in computer vision, machine learning, medical imaging, and neural network compression.
Education
- Completed a PhD in Machine Learning (Computer Science) from City, University of London in 2017 under the supervision of Greg Slabaugh. Contributed novel probabilistic regression methods to learn hand pose and orientation using uncalibrated colour images.
Background
- Research interests include machine learning, computer vision, medical imaging, neural networks, and probabilistic modelling. Current research focuses on developing AI methods for minimally invasive surgery (MIS), medical imaging, as well as AI-assisted annotation of imaging data.
