I teach the Geometric Modelling course where we build interesting 3D models.
I work in the general area of 3D geometric modelling, with a particular focus on the analysis of images sourced from medical scanners, across multiple modalities.
My group's OxMedIS software for Medical Image Segmentation is capable of processing MRI, CT, microCT, ultrasound and other medical and biological data. We have developed algorithms to partition each 3D image into regions with similar properties. These images are then analysed further so that particular features (such as bones, organs or blood vessels) can be identified within them and segmented out. Once labelled, the features can be reconstructed as 3D shapes and displayed or 3D printed on our Makerbot 2X. We specialise in automating some of the steps of the segmentation, whilst providing the clinicians with a manual override on the final results. Some of our algorithms work inparallel and have been implemented on a GPU.
The segmentation methods have been validated against hand-drawn ground truth contours, using a suite of conventional evaluation metrics. In addition we have also designed our own evaluation metrics which we have proved to rank segmentation results effectively.
Our most recent experiments have successfully used machine learning tehniques (specifically reinforcement learning) in order to segment features out of a pre-partitioned image. We thus reduce the need for vast amounts oftime consuming hand-drawn training contours.
All our research is carried out in very close collaboration with clinicians in a variety of fields, both in academia and in hospitals.
- Prof Sion Glyn-Jones, FRCS DPhil, Consultant Orthopaedic Surgeon, Oxford
- Dr Antony Palmer, MA BMBCh DPhil FRCS, NIHR Academic Clinical Lecturer, Oxford
- Dr Elise Pegg, Department of Mechanical Engineering, University of Bath
- Prof Hemant Pandit, FRCS DPhil, Orthopaedic Surgeon, Senior Clinical Lecturer, Chapel Allerton Hospital Leeds
- Prof David Murray, MA MD FRCS, Consultant Orthopaedic Surgeon, Oxford
- Dr Thomas Hamilton, MBChB, BSc (Hons), MSc, MRCS, Orthopaedic Registrar, Oxford
- Prof Dominic Furniss, FRCS DM, Plastic Surgeon, Oxford
- Prof Glyn Humphreys, Watts Professor of Experimental Psychology, Oxford
- Prof Nele Demeyere, Experimental Psychology, Oxford
- Dr Zoe Traill, MBBS, MA, MRCP, FRCR, Radiology consultant
- Prof David Cranston, MB ChB DPhil FRCS, Consultant Urological Surgeon
- Dr Andrew Protheroe, MBBS, FRCP, PhD, Renal oncologist
- Mr Mark Sullivan, MB BS, MD, FRCS, Clinical Directorate Lead, Urology
- 2013-2018 Varduhi Yeghiazaryan, DPhil, Parallel Front Propagation in Medical Image Segmentation
- 2006-2011 Stuart Golodetz, DPhil, Zipping and unzipping: the use of image partition forests in the analysis of abdominal CT scans
- 2005-2010 Gwyn Skone, DPhil, Stratagems for effective function evaluation in computational chemistry
- 2002-2012 Jian Chen, DPhil in collaboration with the Department of Structural Biology, Improving icosahedral virus reconstruction from cryo--electron micrographs
- 2017 Avraham Sherman, MSc, June Bug: Building and Analyzing Physical 3D Models from Medical Scans
- 2017 Jahangid Iqbal, MSc, Hand Gesture Recognition via LeapMotion Sensor
- 2017 Edoardo Pirovano, MCompSci, “Applications of Reinforcement Learning to MedicalImage Segmentation”
- 2017 John Burden, MCompSci, “Image Filtering For Medical Imaging”
- 2017 Dan-Andrei Gheorghe, MCompSci, “Exact Algorithm for Complex Root Clustering”, Microsoft Prize for best Computer Science project in Part C
- 2016 Christine Lind, MSc, Wearable sensors for post--op joint rehabilitation
- 2016 Samuel Littley, MCompSci, Improving 3D printing from medical data
- 2016 Tom McDonald, MCompSci, Knee joint visualisation and measurements of osteoarthritis
- 2016 Josiah Kane, MCompSci, Improving physiotherapy uptake through using a hand sensor
- 2016 Stephen Heap, MCompSci, Machine learning techniques for gesture classification using the Leap Motion sensor
- 2016 Benjamin Dawes, MCompSci, Reinforcement learning techniques for games
- 2015 Cihan Chen, MSc, Element--wise Analysis of Free--hand Line Drawings for Psychological Diagnosis
- 2015 Ioannis Zifos, MSc, Gesture Recognition using Leap Motion
- 2015 Xueying Jessica Liu, MSc, A System for Hand Physiotherapy Using Leap Motion
- 2015 Thomas Lear, MCompSci, Static Target Finding with the Parrot ARDrone 2.0
- 2014 Emil Culic, MCompSci, Objective Hand Gesture Scoring for Apraxia Patients using Leap Motion
- 2014 Pernille Hanehoj, MCompSci, Assessment of Simple Geometric Drawings on a Tablet
- 2013 Piotr Kozlowski, MCompSci, Measuring Gesture Mimicking Accuracy with Microsoft Kinect
- 2013 Kamil Chmurzynski, MCompSci, Assessment of Static Hand Gestures
- 2013 Varduhi Yeghiazaryan, MSc, Feature Identification on CT Images Using the Fast Marching Method'' Richard Bird Prize "for the dissertation that best presents a piece of software, an algorithm, or a mathematical theory pertaining to program construction"
- 2013 Shaun Rudge, MSc, Virtual Milling Machine
- 2012 Jan Paul Posma, MSc, jsdares: a New Approach to Learning Programming
- 2010 Narayan Kamath, MSc, Subdivision Algorithms for Complex Root Isolation: Empirical Comparisons, Hoare prize for best overall MSc in CS performance
- 2010 Stuart Bowyer, MSc, Segmentation and Classification of Magnetic Resonance Images, project continued by the student in a doctoral programme at Imperial College London
- 2009 Chris Arthurs, DTC, Generating Non--Self--Intersecting Molecular Conformations
- 2009 Xingyan Jin, MSc, Map Reconstruction Based On Hand-drawn Images
- 2009 Ruijian Zhang, MSc, Segmentation of Medical Images
- 2009 David Batey, MSc, Generating Computer Animations Based on Real World Objects Using Stereopsis
- 2008 Qingnan Zhang, MSc, A Point Pattern Matching Algorithm for the Registration of Medical Images
- 2007 Ruo Yin, MSc, 3D Reconstruction of Fossils From Registered Binary Images
- 2005 Luis Agudelo, MSc, A Byzantine Music Editor and Translator
- 2005 Celia Cheung, MSc, 3D Fossil Reconstruction using Splines
- 2003 Patichan Kamolvisit, MSc, Simplified Byzantine Music Editor
- 2003 Alistair Thorpe, MSc, Surface Detection in Colour Image Processing
- 2002 Eran Socher, MSc, A Three-dimensional Chat Room System
I am always looking for motivated DPhil/PhD or Masters students to join my group. Please get in touch if you have an interest in
- Image Analysis
- GPU programming
- Machine Learning (specifically Reinforcement Learning)
- Global Health Challenges
Here is a 3D reconstruction of an abdominal CT scan. It features the rib cage, liver, kidneys, spleen, blood vessels and a renal tumour.
My other interests include
- 3D printing
- Mathematics of curves and surfaces
- Finding roots of polynomials
- Constructive Solid Geometry (CSG)
- Molecular modelling
I have been a Lecturer in the Department of Computer Science at Oxford since 1999. I obtained my PhD at the University of Bath, for research in Constructive Solid Geometry (CSG). I contributed to the development of the geometric modelling software svLis through the application of polynomial root finding methods.
As part of the Spatial Reasoning research group at Oxford I have been conducting research in the areas of molecular modelling (protein docking), medical imaging (CT and MRI scan analysis) and polynomial root finding (interval arithmetic). I am interested in other aspects of geometric modelling such as as applications of multivariate polynomial forms in geometry, Bernstein-form polynomials and generalized Newton-like methods.
I am actively involved in public engagement activities, such as the Oxford RobotGames, a programme where children of high school age design and build their own robot in half a day. Another on-going project of the Spatial Reasoning group has been to build a robot sheepdog which automatically herds either live or robotic animals. The Oxford robotic flock was shown in 2001 at the Royal Society Summer Science Exhibition.
Simplifying TugGraph using Zipping Algorithms
Stuart Golodetz‚ Anurag Arnab‚ Irina Voiculescu and Stephen Cameron
In Pattern Recognition. Vol. 103. Pages 107257. 2020.
OXENDONET: A Dilated Convolutional Neural Networks For Endoscopic Artefact Segmentation
Mourad Gridach and Irina Voiculescu
Vol. 2595 of CEUR Workshop Proceedings. Pages 26–29. CEUR−WS.org. 2020.
Segmentation of Hip Cartilage in Compositional Magnetic Resonance Imaging: A Fast‚ Accurate‚ Reproducible‚ and Clinically Viable Semi−Automated Methodology
Scott Fernquest‚ Daniel Park‚ Marija Marcan‚ Antony Palmer‚ Irina Voiculescu and Sion Glyn−Jones
In Journal of Orthopaedic Research. 2018.