top of page
Writer's pictureAhmed Toure

Artificial intelligence tool revolutionizes cancer detection


Global Goals & Global Society
Artificial intelligence tool revolutionizes cancer detection

In a groundbreaking development, doctors, scientists, and researchers have successfully developed an artificial intelligence (AI) model capable of accurately identifying cancer. This breakthrough has the potential to expedite cancer diagnosis and accelerate patients' access to vital treatments. The AI tool, designed collaboratively by experts at the Royal Marsden NHS Foundation Trust, the Institute of Cancer Research (London), and Imperial College London, has demonstrated superior efficiency and effectiveness compared to current methods, as detailed in a study published in the Lancet's eBioMedicine journal.


Cancer remains a leading cause of death worldwide, accounting for approximately 10 million deaths annually, or nearly one in six deaths, according to the World Health Organization. However, early detection and prompt treatment significantly increase the chances of successful outcomes. The newly developed AI algorithm, leveraging radiomics, can accurately determine the cancerous nature of abnormal growths detected in CT scans.


Dr. Benjamin Hunter, a clinical oncology registrar at the Royal Marsden and a clinical research fellow at Imperial, expressed optimism about the future implications of this technology. He stated, "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."

To develop the AI model, the research team utilized CT scans from approximately 500 patients with large lung nodules. By employing radiomics, a technique that extracts crucial information from medical images that may elude human perception, the model was trained and subsequently tested for its ability to accurately identify cancerous nodules.


The performance of the AI model was evaluated using the area under the curve (AUC) measure, which indicates the model's predictive efficacy. The results demonstrated that the AI model achieved an impressive AUC of 0.87 in determining each nodule's cancer risk. This performance surpassed the currently employed Brock score, which scored 0.67, and was comparable to the Herder score with an AUC of 0.83.


Dr. Hunter emphasized the model's accuracy in identifying cancerous large lung nodules and outlined the team's next steps. "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 explained.


Moreover, the AI model could aid doctors in making expedited decisions regarding patients with medium-risk abnormal growths. When combined with the Herder score, the AI model successfully identified high-risk patients within this group. Notably, it recommended early intervention for 18 out of 22 nodules (82%) later confirmed as cancerous, as outlined in the study.


While the Libra study, 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, the potential benefits of the AI tool are evident. Researchers envision its implementation to accelerate cancer detection, streamline CT scan analysis, and facilitate the prompt delivery of treatment. Dr. Richard Lee, the chief investigator of the Libra study, highlighted the importance of pushing boundaries through innovative technologies like AI to expedite disease detection.


The significance of this AI tool becomes even more apparent when considering its potential contribution to the Sustainable Development Goals (SDGs) and the vision of a global society. By enabling faster and more accurate cancer detection, the AI model aligns with SDG 3 (Good Health and Well-being) and supports efforts to combat non-communicable diseases. Moreover, it emphasizes the importance of research, innovation, and technological advancements in healthcare, in line with SDG 9 (Industry, Innovation, and Infrastructure).


The involvement of civil society organizations and sustainable healthcare systems is paramount to fully leverage the benefits of this AI tool. Collaboration between research institutions, healthcare providers, and governments is necessary to ensure equitable access and affordability of this cutting-edge technology. By working together, global society can strive towards SDG 17 (Partnerships for the Goals) to achieve sustainable development and address critical healthcare challenges.


The AI tool's potential to revolutionize cancer detection and expedite treatment highlights the urgent need to address the issue of late-stage diagnoses, particularly in lung cancer. As the leading cause of cancer mortality worldwide, lung cancer accounts for a significant proportion of cancer deaths, including 21% in the UK. Early detection is crucial, as patients diagnosed at the earliest stages have significantly higher survival rates. Dr. Lee emphasized the importance of finding ways to speed up disease detection, underscoring the study's contribution to identifying high-risk patients and supporting clinicians in their efforts.


As the Libra study continues to progress and undergo further testing, the AI model holds promise for transforming cancer diagnosis and treatment. With its potential to improve global health outcomes, this innovative approach to cancer detection reflects the aspirations of a global society striving for a healthier, more sustainable future.


More information:


bottom of page