Imaging

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.

2 column colour block - Research areas

Cardiovascular Imaging

Cardiovascular Imaging

At the Hamlyn Centre, we work on a broad range of imaging modalities, particularly in cardiovascular magnetic resonance imaging. These include the development of accurate cardiac function measurement including phase contrast velocity mapping, myocardial perfusion and coronary imaging.

Image-guided Navigation

The use of minimally invasive and flexible access surgery has imposed significant challenges on surgical navigation. Our work focuses on combining prior knowledge of the anatomical model with subject specific information derived from pre- and intra-operative imaging for image-guided surgery.

2 column colour block - Research areas 2

Surgical Imaging and Vision

Surgical Imaging and Vision

At the Hamlyn Centre, we are working towards the development of lightweight, cost-effective, flexible manipulators with minimum footprint in the operative theatre that enhance current surgical workflow as well as new techniques for providing synergistic control between the surgeon and the robot.
Biophotonics

Surgical Imaging and Biophotonics

Our work in biophotonics focuses on in situ, in vivo tissue characterisation and surgical guidance. Our key research interests include the development and application of photonics technology to surgical imaging and surgical robotics.

Citation

BibTex format

@inproceedings{Han:2021:10.1109/BSN51625.2021.9507038,
author = {Han, J and Gu, X and Lo, B},
doi = {10.1109/BSN51625.2021.9507038},
publisher = {IEEE},
title = {Semi-supervised contrastive learning for generalizable motor imagery eeg classification},
url = {http://dx.doi.org/10.1109/BSN51625.2021.9507038},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Electroencephalography (EEG) is one of the most widely used brain-activity recording methods in non-invasive brain-machine interfaces (BCIs). However, EEG data is highly nonlinear, and its datasets often suffer from issues such as data heterogeneity, label uncertainty and data/label scarcity. To address these, we propose a domain independent, end-to-end semi-supervised learning framework with contrastive learning and adversarial training strategies. Our method was evaluated in experiments with different amounts of labels and an ablation study in a motor imagery EEG dataset. The experiments demonstrate that the proposed framework with two different backbone deep neural networks show improved performance over their supervised counterparts under the same condition.
AU  - Han,J
AU  - Gu,X
AU  - Lo,B
DO  - 10.1109/BSN51625.2021.9507038
PB  - IEEE
PY  - 2021///
TI  - Semi-supervised contrastive learning for generalizable motor imagery eeg classification
UR  - http://dx.doi.org/10.1109/BSN51625.2021.9507038
UR  - http://hdl.handle.net/10044/1/90332
ER  -
Download