This Research Associate (RA) position provides an exciting and unique opportunity to develop signal and image processing and machine learning algorithms for a breakthrough microendoscopy imaging system.
Real-time microendoscopy has been dominated and limited to intensity mode imaging due to existing detector technology. This limitation has been overcome using our new sensors that incorporate intensity and lifetime imaging. This technology enables multidimensional high content high-resolution real-time sensing and imaging of dynamic biological processes and is poised for disruptive healthcare impact.
The research associate will contribute signal and image processing and machine learning expertise to this project by developing, to near-clinical readiness, novel state of the art signal processing and machine learning algorithms to improve the quality of the data received from a sensing system called Kronoscan. There will be a strong emphasis on developing robust real-time algorithms.
We will use spatial, temporal, and spectral dependencies of the sensor data and video-compression techniques to develop real-time algorithms for coding data at the sensor head. This will require understanding of coding an FPGA for on-board calculations. We will develop novel and robust multimodal algorithms for fluorescence detection and quantification of bespoke chemical imaging agents using techniques ranging from multi-target tracking to saliency detection and morphological component analysis.
We will also investigate hexagonal sampled data techniques to approximate the irregular sampling across the fibre-cores and develop this physical model of the fibre-core intensity image, to inform other image enhancement techniques including super-resolution methods.
For more detailed information, and to apply, visit the University of Edinburgh’s vacancy pages – search for Reference No. 047911
For further information, please contact Dr James Hopgood: James.Hopgood@ed.ac.uk