New AI ‘can accurately detect cancer’: Algorithm outperforms existing methods in identifying cancerous nodules, study claims
- This tool can identify whether abnormal growths found on CT scans are cancerous.
- Algorithms perform more efficiently and effectively than current methods
New artificial intelligence tools can accurately identify developing cancers, doctors and scientists say, speeding up diagnosis of the disease.
Research shows that this algorithm works better than current methods.
Abnormal growths found on CT scans can be identified as cancerous.
An AI tool designed by experts from the Royal Marsden NHS Foundation Trust, the Cancer Institute of London and Imperial College London can quickly track patients to treatment.
According to the World Health Organization, cancer causes approximately 10 million deaths annually.
![New artificial intelligence tools can accurately identify developing cancers, doctors and scientists say, speeding up diagnosis of the disease. [File image]](https://i.dailymail.co.uk/1s/2023/04/30/19/70409013-12031361-image-m-10_1682878955822.jpg)
New artificial intelligence tools can accurately identify developing cancers, doctors and scientists say, speeding up diagnosis of the disease. [File image]
Dr Benjamin Hunter, Clinical Oncology Registrar, Royal Marsden, said:
The team used CT scans of about 500 patients with large lung nodules to develop an AI algorithm using radiomics, according to a report by. Guardian.
This technology can extract important information from medical images that is not easily spotted by the human eye.
We then tested the model to determine whether it could accurately identify cancerous nodules.
This study used a measure called area under the curve (AUC) to see how effective the model was in predicting cancer.
![Studies show that the algorithm performs more efficiently and effectively than current methods. [File image]](https://i.dailymail.co.uk/1s/2023/04/30/19/68794779-12031361-The_algorithm_performs_more_efficiently_and_effectively_than_cur-m-25_1682879414803.jpg)
Studies show that the algorithm performs more efficiently and effectively than current methods. [File image]
According to The Guardian, an AUC of 1 indicates a perfect model, but 0.5 is expected if the model is guessing randomly.
The results showed that the AI model could identify the cancer risk of each nodule with an AUC of 0.87. Performance improved on the Brock score, a test used in the clinic, with a score of 0.67.
“Through this research, we hope to push the boundaries to speed up disease detection using innovative technologies such as AI,” said Dr. Richard Li, principal investigator of the Libra study.
This is after AI developed a cure for aggressive cancer in just 30 days and demonstrated that doctors’ notes could be used to predict patient survival.
Breakthroughs were made by separate systems, but they demonstrate the use of powerful technology far beyond generating images and text.
Researchers at the University of Toronto, in collaboration with Insilico Medicine, have developed a potential treatment for hepatocellular carcinoma (HCC) using an AI drug discovery platform called Pharma.
HCC is a type of liver cancer, and AI has discovered a previously unknown therapeutic pathway and designed a “novel hit molecule” that can bind to its target.
