Back to Projects

Computational extraction of semantic information from hyperspectral imaging for surgical guidance

Project ID: 2019_S02

1st supervisor: Tom Vercauteren, King’s College London
2nd supervisor: Christos Bergeles, King’s College London
3rd supervisor: Keyoumars Ashkan, King’s College Hospital NHS Foundation Trust

Each year, in the UK, approximately 11,500 patients are diagnosed with a primary central nervous system (CNS) tumour. Many others are diagnosed with secondary brain tumours. There is an acute need to improve outcomes for these neuro-oncology patients. For example, in primary malignant glioma, or high-grade glioma (HGG), which is the most common type of primary brain tumour, despite advanced treatment, half of the diagnosed patients live for only 12 months, and less than 5% live longer than five years. Clinical studies have demonstrated that patients who undergo surgery and have their CNS tumour radically removed have a significantly longer survival than those who are left with residual tumour tissue after surgery. Surgery is often the primary treatment and the aim of neuro-oncology surgery is to remove as much abnormal tissue as safely possible. Successful neurosurgery to remove brain tumours depends on achieving maximal safe tumour removal: avoiding damaging sensitive areas that undertake vital functions and preserving crucial nerves and blood vessels.  However, even with the most advanced current techniques, it may still not be possible to reliably identify critical structures during surgery. The identification of tumour and surrounding tissue is currently still based on surgeons’ subjective visual assessment.

During surgery, neuronavigation solutions can map preoperative information to the anatomy of the patient on the surgical table. However, navigation does not account for intraoperative changes. Interventional imaging and sensing, such as surgical microscopy, fluorescence imaging, point-based Raman spectroscopy, ultrasound and intra-operative MRI, may be used by the neurosurgeon, but partly due to stringent operative constraints, tissue differentiation remains challenging. Advanced optical imaging techniques provide a promising solution for intraoperative wide-field tissue characterisation, with the advantages of being non-contact, non-ionising and non-invasive.

Hyperspectral imaging (HSI) is a non-contact camera-based optical imaging technique that exploits the ability to split light into multiple narrow spectral bands far beyond the conventional red/green/blue channels. It enables the acquisition of much richer information than what can be seen with the naked eye. Using label-free HSI, it has been demonstrated that blood concentration, oxygenation and other aspects of tissue structure can be investigated with a wide-field of view. While the concept of HSI has been explored for biomedical applications for many years, compact sensors capable of acquiring HSI data in real-time have been made commercially available for the first time in 2018. While bearing rich information, the raw 2D+wavelength+time data that HSI produces is difficult to interpret for clinicians as it generates a temporal flow of three-dimensional information which cannot be simply displayed in an intuitive fashion on standard monitors (including “3D”/stereo displays). Combined with general increase in the use of imaging, with real-time HSI, the clinical team will face a data deluge that needs to be addressed.

Back to Projects