Constant scientific innovation and new technologies improve cancer detection and treatment worldwide. Imperial College London will lead, for at least 12 months, a consortium of clinicians and academics, which will collaborate with DeepMind Health and the Google AI health research team to develop more accurate breast cancer diagnosis thanks to artificial intelligence. Based at the Cancer Research UK Imperial Centre, the project will explore whether machine learning could make breast screening technologies more efficient than they are nowadays – mammograms, which are X-rays images of the breasts, miss thousands of cases every year, including an estimated 30% of interval cancers. The consortium will use machine learning technology on about 7,500 depersonalised mammography images from the OPTIMAM mammography database to train computer algorithms to better analyse screenings and identify cancerous tissue more accurately. This would lead to earlier detection and treatment. If successful, the technology could benefit millions of women: according to the last available data from the World Cancer Research Fund International, breast cancer is the most common cancer among women in the world, and the second most frequent cancer overall.
By Marie-Eléonore Noiré