International evaluation of an AI system for breast cancer screening

Autor: Demis Hassabis, Alan Karthikesalingam, Kenneth C. Young, Fiona J. Gilbert, Jonathan Godwin, Jeffrey De Fauw, Mark D. Halling-Brown, David S. Melnick, Daniel Tse, Mustafa Suleyman, Richard Sidebottom, Joshua J. Reicher, Marcin Sieniek, Hutan Ashrafian, Lily Peng, Sunny Jansen, Mary Chesus, Natasha Antropova, Dominic King, Hormuz Mostofi, Scott Mayer McKinney, Florencia Garcia-Vicente, Bernardino Romera-Paredes, Shravya Shetty, Varun Godbole, Christopher Kelly, Mozziyar Etemadi, Trevor Back, Greg C. Corrado, Ara Darzi, Joseph R. Ledsam
Přispěvatelé: Gilbert, Fiona [0000-0002-0124-9962], Apollo - University of Cambridge Repository, National Institute for Health Research, National Institute of Health Research
Rok vydání: 2020
Předmět:
Zdroj: Nature. 577:89-94
ISSN: 1476-4687
0028-0836
Popis: Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening. An artificial intelligence (AI) system performs as well as or better than radiologists at detecting breast cancer from mammograms, and using a combination of AI and human inputs could help to improve screening efficiency.
Databáze: OpenAIRE
Externí odkaz: