The researchers at Imperial College in London have combined medical imaging with AI in order to provide the first “virtual Biopsy” for lung cancer patients, making them the world’s pioneers in this method.
Their non-invasive method can classify the type of lung cancer a patient has (which is important in selecting the right treatment), and can predict if the cancer is likely to progress.
For the first time, #OurImperial researchers have demonstrated how combining medical imaging with AI can be used to provide a 'virtual biopsy' for cancer patients ⚕️🖥️
Read more ⬇️https://t.co/fkTeKm9NJt
— Imperial College London (@imperialcollege) February 22, 2024
Usually, patients who have symptoms of lung cancer tend to be diagnosed using a chest X-ray and computed tomography (CT) scan, followed by a biopsy.
This technique involve taking a small sample of body tissue so it can be examined under a microscope.
Professor Eric Aboagye, from Imperial’s Department of Surgery and Cancer, believes that these methods are “uncomfortable for the patient, delay treatment decisions and can be costly for health services.”
According to the researchers, this new technique could be used by doctors when it’s not possible, or suitable, to take a physical tissue biopsy from a patient.
How did the study work?
The Imperial team collected data from 48 lung cancer patients from the University Hospital Reina Sofia in Córdoba, Spain.
Each patient had a CT scan as well as a new cancer test called metabolic profiling, which provides detailed information about the chemistry of tumour cells and how the cancer is likely to evolve.
Researchers at Imperial College used the data to develop an AI-powered tool called tissue-metabolomic-radiomic-CT (TMR-CT).
This was tested on 723 lung cancer patients who were treated in London Hospitals.
The results showed that the AI method was efficient, surpassing the performance of a traditional CT scan.
Marc Boubnovski Martell, Imperial PhD candidate, added that the system “allows us to classify lung cancer types and provides reliable predictions about patient outcomes”.
