A groundbreaking artificial intelligence (AI) tool has been developed by researchers at University College London (UCL) and University College London Hospitals (UCLH) to enhance the analysis of brain scans. This innovative technology promises not only to outperform experienced neuroradiologists in terms of speed but also offers a more personalised approach to patient treatment. The findings were detailed in a study published in "NeuroImage: Clinical."
The newly created AI tool is capable of analysing brain scans in merely three seconds, a significant reduction from the typical five minutes required by seasoned neuroradiologists. This expedited analysis does not come at the cost of accuracy or detail. Rather, the tool provides enhancements in the personalisation of patient data, potentially leading to better predictions of treatment outcomes. The potential financial impact is notable as well, with forecasts suggesting that a national implementation across the UK could save the National Health Service (NHS) an estimated £1.5 million over a three-year period.
In the UK, around 100,000 individuals live with brain tumours, a condition that necessitates regular monitoring through brain imaging. The differences in tumour imaging from patient to patient pose a considerable challenge in medical assessments. Traditionally, specialist radiologists evaluate these images to determine the tumour's location, approximate size, and proximity to essential brain structures. The adoption of this AI tool could represent a significant shift in how these assessments are conducted.
The development team at the UCL Queen Square Institute of Neurology and UCLH demonstrated the AI's effectiveness in a substantial study involving 1,172 patients. The tool showed consistent accuracy across a diverse patient demographic, spanning various ages and sexes.
Dr James Ruffle from the UCL Queen Square Institute of Neurology, the study's lead author, highlighted the importance of this development. He remarked, "Given that the imaging appearances of an individual's brain tumour vary greatly from one patient to another, artificial intelligence technologies provide an innovative solution to enhance health care workers' data-driven decision making, improving and personalising care for each individual affected, and at near-zero additional cost to the NHS—and with savings to the NHS over the medium term."
Adding to this, Dr Harpreet Hyare, Senior Neuroradiologist at UCLH, said, "This work shows real promise in enabling neuroradiologists to provide accurate and quantified descriptors of brain tumours. By providing objective quantitative assessments of different brain tumour components that can be monitored over time, we can enable clinicians to plan treatment more effectively at critical time points."
This AI tool represents just one of several technological advancements the research team is pursuing for neuro-oncology applications. They are actively working towards introducing these tools into clinical settings to potentially revolutionise how brain tumours are managed and treated in the near future.
Source: Noah Wire Services