The Centre has a long history of developing new techniques for medical imaging (particularly in magnetic resonance imaging), transforming them from a primarily diagnostic modality into an interventional and therapeutic platform. This is facilitated by the Centre's strong engineering background in practical imaging and image analysis platform development, as well as advances in minimal access and robotic assisted surgery. Hamlyn has a strong tradition in pursuing basic sciences and theoretical research, with a clear focus on clinical translation.

In response to the current paradigm shift and clinical demand in bringing cellular and molecular imaging modalities to an in vivo – in situ setting during surgical intervention, our recent research has also been focussed on novel biophotonics platforms that can be used for real-time tissue characterisation, functional assessment, and intraoperative guidance during minimally invasive surgery. This includes, for example, SMART confocal laser endomicroscopy, time-resolved fluorescence spectroscopy and flexible FLIM catheters.


BibTex format

author = {Feng, Y and Guo, Z and Dong, Z and Zhou, X and Kwok, K and Ernst, S and Lee, S},
doi = {10.1007/s11548-017-1587-4},
journal = {International Journal of Computer Assisted Radiology and Surgery},
pages = {199--1207},
title = {An efficient cardiac mapping strategy for radiofrequency catheter ablation with active learning},
url = {},
volume = {12},
year = {2017}

RIS format (EndNote, RefMan)

AB - ObjectiveA major challenge in radiofrequency catheter ablation procedure(RFCA) is the voltage and activation mapping of the endocardium, given a limitedmapping time. By learning from expert interventional electrophysiologists (operator),while also making use of an active-learning framework, guidance on performing car-diac voltage mapping can be provided to novice operators, or even directly to catheterrobots.MethodsA Learning from Demonstration (LfD) framework, based upon previous car-diac mapping procedures performed by an expert operator, in conjunction with Gaus-sian process (GP) model-based active learning, was developed to efficiently performvoltage mapping over right ventricles (RV). The GP model was used to output thenext best mapping point, while getting updated towards the underlying voltage datapattern, as more mapping points are taken. A regularized particle filter was used tokeep track of the kernel hyperparameter used by GP. The travel cost of the cathetertip was incorporated to produce time-efficient mapping sequences.ResultsThe proposed strategy was validated on a simulated 2D grid mapping task,with leave-one-out experiments on 25 retrospective datasets, in an RV phantom usingthe Stereotaxis NiobeR©remote magnetic navigation system, and on a tele-operatedcatheter robot. In comparison to an existing geometry-based method, regression errorwas reduced, and was minimized at a faster rate over retrospective procedure data.ConclusionA new method of catheter mapping guidance has been proposed based onLfD and active learning. The proposed method provides real-time guidance for theprocedure, as well as a live evaluation of mapping sufficiency.
AU - Feng,Y
AU - Guo,Z
AU - Dong,Z
AU - Zhou,X
AU - Kwok,K
AU - Ernst,S
AU - Lee,S
DO - 10.1007/s11548-017-1587-4
EP - 1207
PY - 2017///
SN - 1861-6410
SP - 199
TI - An efficient cardiac mapping strategy for radiofrequency catheter ablation with active learning
T2 - International Journal of Computer Assisted Radiology and Surgery
UR -
UR -
VL - 12
ER -