Researchers at New York University (NYU) Langone Health in the US have developed an artificial intelligence (AI) tool that was shown to improve the accuracy of breast cancer imaging in a study.
The tool is trained to check patterns among thousands of breast ultrasound images and can help doctors precisely detect breast cancer.
When separately tested on 44,755 previously completed ultrasound exams, the AI tool enhanced radiologists’ ability to precisely detect the disease by 37%.
Furthermore, the tool lowered the number of tissue samples or biopsies required to establish suspect tumours by 27%.
Potentially the largest study of its kind, the latest AI analysis was led by scientists from the Department of Radiology at NYU Langone Health and its Laura and Isaac Perlmutter Cancer Center.
It used 288,767 separate ultrasound exams obtained from 143,203 women who were treated at NYU Langone hospitals in New York City between 2012 and 2018.
NYU Grossman School of Medicine radiology professor Dr Linda Moy said: “If our efforts to use machine learning as a triaging tool for ultrasound studies prove successful, ultrasound could become a more effective tool in breast cancer screening, especially as an alternative to mammography, and for those with dense breast tissue.
“Its future impact on improving women’s breast health could be profound.”
The preliminary data is promising, but clinical trials of the tool in present patients and real-world conditions are required before routinely deploying the tool, the team noted.
The AI software could also be refined by incorporating further patient data, such as a woman’s increased risk from having a family history or genetic mutation tied to breast cancer, which was not present in the most recent assessment.
Ultrasound exams leverage high-frequency sound waves passing through the tissue to create real-time images of the breast or other tissues.
The researchers added that ultrasound is low-cost, broadly available and does not involve radiation exposure, but it has been shown to cause too many false diagnoses of breast cancer.