News

‘Virtual biopsy’ uses AI to help doctors assess lung cancer 21 Feb 2024

Researchers have used artificial intelligence (AI) to extract information about the chemical makeup of lung tumours from medical scans, in a study funded by the National Institute for Health and Care Research (NIHR) Imperial Biomedical Research Centre (BRC).

For the first time, the team has demonstrated how combining medical imaging with AI can be used to provide a ‘virtual biopsy’ for cancer patients. Their non-invasive method can classify the type of lung cancer a patient has – which is crucial in selecting the right treatment – and can predict if the cancer is likely to progress. According to the researchers, the technique could be used by doctors when it’s not possible or suitable to obtain a physical tissue biopsy from a patient.

The study, published in the journal npj Precision Oncology, was led by Imperial College London and Imperial College Healthcare NHS Trust and funded by the NIHR Imperial BRC, alongside collaborators in Córdoba, Spain.

Early detection and diagnosis

Lung cancer is the most common cause of cancer death in the UK, with around 35,000 lives lost to the disease each year, according to Cancer Research UK. This is partly because symptoms don’t appear in the early stages and there is a pressing need for new ways to detect and treat the tumour before it spreads. Patients who present with symptoms of lung cancer are diagnosed using chest X-rays and computed tomography (CT) scans – which can also show if the cancer has spread beyond the lungs. If it’s safe to take a biopsy sample, clinical scientists look at the tumour cells under a microscope and classify the type of lung cancer to help doctors decide the right course of treatment.

The study’s senior author, Professor Eric Aboagye, from Imperial College London’s department of surgery and cancer, said: “At the moment, trying to find out in-depth information about tissues and tumours requires invasive biopsies, which can be uncomfortable for the patient, delay treatment decisions and be costly for health services. Although CT scans are commonly used in the clinic, they fall short of offering detailed insights into the cellular type or prognostic information of diseases.”

AI-powered imaging

In recent years, AI has been increasingly used to predict outcomes, analyse medical scans and look for signs of disease that can be missed by doctors or might not even be visible to the naked eye. For example, Professor Aboagye led a study in 2019, also funded by the NIHR Imperial BRC, that showed a machine learning software could forecast the survival rates and response to treatments of patients with ovarian cancer. The first-ever NHS study to evaluate an AI technology for point-of-care detection of heart failure was led by an Imperial consultant in 2022.

This research team used generative AI, a type of AI that can learn from data to create new content, to see if information about lung tumour chemistry might show up in CT scans. The AI model was first trained on existing medical scans alongside detailed medical histories. To do this, the researchers used data from 48 lung cancer patients who were treated at the University Hospital Reina Sofia (UHRS) in Córdoba, Spain. Based on this data, the Imperial team developed an AI-powered, deep learning assessment tool.

The researchers found a significant and powerful correlation between the chemistry of patients’ tumours and certain features of their CT scans. Using this method, the researchers believed they could avoid invasive physical tissue samples and understand tumours better from CT scans alone. To test this, they used the newly developed AI model in a separate group of 723 lung cancer patients who had a CT scan from Imperial College NHS Healthcare Trust, Royal Marsden Hospital or Guy’s and St Thomas’ Hospital. The researchers were able to classify lung cancers and give predictions about patient outcomes, surpassing the performance of traditional methods and clinical assessments.

A future clinical tool

The researchers hope to confirm their method in other groups of lung cancer patients and potentially people with brain, ovarian and endometrial cancers, which can also be difficult to get physical biopsies from. In the future, the technique could be incorporated as an algorithm as part of the software loaded onto commercial medical imaging scanners. 

Professor Aboagye concludes: “This research shows the potential of using CT scans to gain a deeper, more nuanced understanding of tissue and tumour chemical composition, that has until now only been accessible through direct tissue sampling. This method could prove particularly beneficial in countries like the UK, where lung cancer prevalence is high, and potentially transform diagnostic and treatment protocols.”