New AI tool can accurately detect cancer, researchers say

By Al Mayadeen English
Source: The Guardian
30 Apr 2023 20:02

The AI tool can determine if unusual growths noticed on CT scans are malignant.

The X-ray of an unidentified person shows both sides of the lungs with a growth on the left side, which could possibly be lung cancer (Reuters)

Doctors, scientists, and researchers have developed an artificial intelligence model that can precisely detect cancer, which they believe might speed up illness diagnosis and treatment, as reported by The Guardian.

According to the World Health Organization, cancer is the primary cause of death globally. The disease causes around 10 million deaths every year, or almost one in every six deaths. However, in a lot of instances, cancer can be cured if detected early and treated immediately.

Developed by the Royal Marsden NHS foundation trust, the Institute of Cancer Research, London, and Imperial College London, the AI tool can determine if unusual growths noticed on CT scans are malignant.

According to a study, the algorithm outperforms current approaches in terms of efficiency and effectiveness.

"In the future, we hope it will improve early detection and potentially make cancer treatment more successful by highlighting high-risk patients and fast-tracking them to earlier intervention," expressed Benjamin Hunter, a clinical oncology registrar at the Royal Marsden and a clinical research fellow at Imperial.

The researchers utilized CT images from 500 individuals with big lung nodules to create an AI system based on radiomics. The technology can extract critical information from medical photos that the human eye cannot see.

The model was then put to the test to see if it could precisely detect malignant nodules.

"According to these initial results, our model appears to identify cancerous large lung nodules accurately," Hunter pointed out.

"Next, we plan to test the technology on patients with large lung nodules in clinic to see if it can accurately predict their risk of lung cancer," he added.

The AI model may also assist physicians to reach more timely choices regarding patients with abnormal growths classified as medium-risk.

According to the researchers, the Libra study, which is supported by the Royal Marsden Cancer Charity, the National Institute for Health and Care Research, RM Partners, and Cancer Research UK, is still in its early stages. More testing must be done before the model can be implemented in healthcare systems.

"Through this work, we hope to push boundaries to speed up the detection of the disease using innovative technologies such as AI," said Richard Lee, the study’s chief investigator.

Lee cited lung cancer as an example of why fresh attempts to improve diagnosis were urgently required.

Lung cancer is the leading cause of cancer mortality globally, causing one-fifth (21%) of cancer deaths in the United Kingdom.

Early detection allows for more successful treatment, yet current data suggest that more than 60% of lung cancer cases in England are detected at stage three or four.

Lee indicated that "people diagnosed with lung cancer at the earliest stage are much more likely to survive for five years, when compared with those whose cancer is caught late."

"This means it is a priority we find ways to speed up the detection of the disease, and this study – which is the first to develop a radiomics model specifically focused on large lung nodules – could one day support clinicians in identifying high-risk patients," he explained.