Artificial intelligence and big data in medical imaging will dramatically change the landscape of healthcare

882
Wiro Niessen

The analysis of big data with artificial intelligence (AI) techniques will have an enormous impact on disease prevention, cure and care. By 2030, it will have dramatically changed the landscape of the healthcare system, said Wiro Niessen, Rotterdam, The Netherlands, speaking at the press conference of European Congress of Radiology (ECR; 28 February–4 March, Vienna, Austria).

Niessen, professor in Biomedical Image Analysis, Erasmus MC, Rotterdam, The Netherlands and at the University of Technology in Delft, spoke on the topic “AI and big data in medical imaging” on 3 March at the ECR. He started off by referencing The Economist’s 2016 article “Anything you can do, AI can do better” and asked the question: “should AI be embraced or feared?”

Niessen then went on to provide examples in healthcare where artificial intelligence and big data should be “embraced” as they have the capacity to realise the potential of precision medicine and precision health.

Niessen explained that precision medicine involved taking individual variability into account to optimise diagnosis, prognosis and treatment. In cardiovascular disease, this can involve      knowing which patients to treat; in cancer treatment, this can involve predicting which treatment is likely to be successful; and in dementia, this can involve prognosis to support preventive strategies.

“With an ageing society, there is an urgent need to develop new preventive and therapeutic strategies for common, age-related, diseases, such as Alzheimer’s disease, the most common form of dementia,” said Niessen.

“Largescale data analytics in longitudinal population neuroimaging studies, especially when combining imaging with other clinical, biomedical and genetic data, provide a unique angle to study the brain, both in normal ageing and disease,” he said while also discussing the promise and challenges of using state-of-the-art artificial intelligence techniques as deep learning in this domain, to improve diagnostics and prognostics.

“As a second example, radiomics approaches can be used to improve tumour characterisation and therapy selection and guidance in oncology, and here the enormous potential and pitfalls of using artificial intelligence in the interpretation of these data were discussed,” stated Niessen.

(Visited 382 times, 1 visits today)

LEAVE A REPLY

Please enter your comment!
Please enter your name here