Artificial intelligence programme detects breast cancer better than experts, study finds Home Artificial intelligence programme detects breast cancer better than experts, study finds Previous Post Artificial intelligence programme detects breast cancer better than experts, study finds
An AI system developed by Google Health can identify cancer in breast screening mammograms with fewer false positives and fewer false negatives than radiologists
A new study has found that an AI system developed by Google Health can identify cancer in breast screening mammograms with fewer false positives, and fewer false negatives than radiologists.
The programme was developed in collaboration with DeepMind, Cancer Research UK Imperial Centre, Northwestern University, and Royal Surrey County Hospital.
Researchers said that the AI model was trained and tuned on anonymised mammograms from more than 76,000 women in the UK and more than 15,000 women in the US to see if it could learn to spot signs of breast cancer.
It was then tested on a separate data selection of more than 25,000 women in the UK and over 3,000 women in the US.
The study found that the AI system produced a 1.2% reduction in false positives, where a mammogram is reported as abnormal when no cancer is present, and 2.7% reduction of false negatives, when the scan is reported as normal even though breast cancer is present, in the UK.
This compared to a 5.7% reduction in false positives and 9.4% reduction of false negatives in the USA.
It said that while human experts had access to patient histories and prior mammograms when making screening decisions, the AI system only processed the most recent mammogram with no extra information and “compared favourably”.
The team said that the latest study, published in the journal Nature on Wednesday, “set the stage” for the model to potentially support radiologists performing breast cancer screenings.
Dominic King, UK Lead at Google Health, said: “Our team is really proud of these research findings, which suggest that we are on our way to developing a tool that can help clinicians spot breast cancer with greater accuracy.
“Further testing, clinical validation and regulatory approvals are required before this could start making a difference for patients, but we’re committed to working with our partners towards this goal.”
1 JANUARY 2020