National brain tumour research funding needs to increase to £30-35 million a year
Artificial intelligence can help to improve prognosis and treatment for glioblastoma
Latest news categories
Brain Tumour Research is a partner organisation of the National Cancer Research Institute (NCRI) and ahead of their Virtual Showcase taking place on 2-3 November 2020 – replacing the usual conference – we are pleased to bring news of how, in the first study of its kind in cancer, researchers have applied artificial intelligence to measure the amount of muscle in patients with brain tumours to help improve prognosis and treatment.
Dr Ella Mi, a clinical research fellow at Imperial College London (UK), will tell the NCRI Virtual Showcase that using deep learning to evaluate MRI brain scans of a muscle in the head was as accurate and reliable as a trained person, and was considerably quicker. Furthermore, her research showed that the amount of muscle measured in this way could be used to predict how long a patient might survive their disease as it was an indicator of a patient’s overall condition.
We asked report co-author Consultant Clinical Oncologist, specialising in neuro-oncology at Imperial College Healthcare NHS Trust, Dr Matt Williams to comment on this research and he told us:
“We are really pleased that the NCRI have chosen to highlight our work. The underlying idea is relatively simple, but this is the first time that anyone has used deep learning to look at muscle bulk in brain tumour patients.
“This approach lets us use images that are acquired as part of routine care, and uses a computer to process them. Once trained, it takes less than 10 seconds to process a scan.
“From a clinical perspective, we know that patients with this type of tumour generally have poor survival rates however some people obviously survive longer than others and the really important question is why? Our work uses a computer to assess patient-related factors (rather than tumour-based ones) to help us better understand prognosis in this group of patients.
“The next steps are to extend and refine this work. We want to test it in a wider group of patients, and also make it easier to use and more automated. We can then look at incorporating measures of muscle mass into clinical work, and ultimately understanding how that information can improve patient outcomes. It builds on research support and infrastructure provided by Brain Tumour Research, and is part of our wider program applying AI techniques to brain tumours.”
Another co-author of this research piece, Lillie Pakzad-Shahabi, is funded by Brain Tumour Research.
If you found this story interesting or helpful, sign up to our weekly e-news and keep up to date with all the latest from Brain Tumour Research.