Optimising neuroimaging in the management of brain tumours using artificial intelligence

Glioblastoma is the most frequent and aggressive primary malignant brain tumour in adults. It carries an annual incidence in England of 4.64 per 100,000[1]. The current standard-of-care for newly diagnosed patients consists of surgery, followed by radiotherapy and chemotherapy[2]. Despite this, glioblastoma invariably recurs; and patients diagnosed with these tumours have an overall poor prognosis: the median overall survival is 14.6 months and fewer than 10% survive 5 years after diagnosis[3].

MRI likely plays an important role in the management of glioblastoma. Imaging is believed to be essential for the initial characterisation, surgical and radiotherapy planning and for the assessment of treatment response. Appropriate and timely neuroimaging in the follow-up period is believed to be crucial in making subsequent management decisions. However, on review of current UK, European and international guidelines[4-8] there is considerable variation and lack of evidence-based consensus on the exact frequency and timing of neuroimaging during the post-treatment follow-up period. There is also no evidence to support early post-operative MRI on patients after surgery. In summary, it is not known whether the imaging performed at each stage of the patient pathway after initial glioblastoma treatment changes outcomes (morbidity, mortality or health economics).

54% of caregivers had costs equivalent to over £205 a month, whilst 27% spent £1436 a month; transportation to hospitals was amongst the greatest non-medical costs.[9] Frequent imaging investigations can contribute to some of the financial difficulties that patients with glioblastoma face and can cause anxiety. However, it is not known whether the imaging performed at each stage of the patient pathway after initial glioblastoma treatment changes outcomes. Optimizing the pathway for post-treatment imaging in patients, and providing evidence-based reassurance of the imaging performed, will not only reduce anxiety surrounding imaging investigations, but may reduce some of the financial burden associated with this disease for patients and the healthcare system.

Project Description
RCTs give level 1 evidence[10], however performing one for each imaging time-point is challenging for multiple practical reasons including cost and poor recruitment – many patients believing that missing routine imaging follow-up would be disadvantageous. RCTs proving the value of any imaging are, unsurprisingly, rare but make a large impact[11,12].

Alternatively, using machine learning with Bayesian methodology, it is envisaged that the predicted contribution (with confidence intervals) of each co-variate, including each discrete imaging time-point, can be computed in terms of morbidity, mortality and health economic outcomes. Modelling would allow predictions as to whether imaging at any particular time-point is of value or not. It would also help to predict which key co-variates, including imaging time-points, should be targeted in non-CDT RCTs thereby optimizing research resources.

This study will also demonstrate a key priority of the James Lind Alliance Priority Setting Partnership (of patients, carers and clinicians) to determine the value of neuro-oncological interval scanning. This will help inform future clinical practice and ensure that all imaging performed is appropriately, timely and has an evidence base.

It is envisaged that the results, once disseminated, will inform standard practice in all the neuro-oncology centres throughout the UK. Furthermore, given that this is a value-based healthcare project, CE marking of models produced can be avoided with quicker implementation into hospitals. The expected timeline to achieve the initial results is within three years from the proposed start date.

Eligibility
Only home UK or EU/EEA candidates fulfilling the 3-year UK residency requirement are eligible for the EPSRC DTP studentships. EU/EEA applicants are only eligible for a full studentship if they have lived, worked or studied in the UK for 3 years prior to the funding commencing.

How to apply
Please submit an application for the Biomedical Engineering and Imaging Science Research MPhil/PhD (Full-time) programme using the King’s Apply system: https://apply.kcl.ac.uk/

Please include the following with your application:
A PDF copy of your CV should be uploaded to the Employment History section.
A PDF copy of your personal statement using this template should be uploaded to the Supporting statement section: https://www.kcl.ac.uk/health/study/studentships/docs/dtp-personal-statement-2019-20-final.docx
Funding information: Please choose Option 5 “I am applying for a funding award or scholarship administered by King’s College London” and under “Award Scheme Code or Name”enter BMEIS_DTP.Failing to include this code might result in you not being considered for this funding scheme.

Application closing date: Ongoing

Contact information
For enquiries, please contact Dr Thomas Booth at [Email Address Removed]