BibTex format
@article{McKinney:2020:10.1038/s41586-019-1799-6,
author = {McKinney, SM and Sieniek, M and Godbole, V and Godwin, J and Antropova, N and Ashrafian, H and Back, T and Chesus, M and Corrado, GC and Darzi, A and Etemadi, M and Garcia-Vicente, F and Gilbert, FJ and Halling-Brown, M and Hassabis, D and Jansen, S and Karthikesalingam, A and Kelly, CJ and King, D and Ledsam, JR and Melnick, D and Mostofi, H and Peng, L and Reicher, JJ and Romera-Paredes, B and Sidebottom, R and Suleyman, M and Tse, D and Young, KC and De, Fauw J and Shetty, S},
doi = {10.1038/s41586-019-1799-6},
journal = {Nature},
pages = {89--94},
title = {International evaluation of an AI system for breast cancer screening},
url = {http://dx.doi.org/10.1038/s41586-019-1799-6},
volume = {577},
year = {2020}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - 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.
AU - McKinney,SM
AU - Sieniek,M
AU - Godbole,V
AU - Godwin,J
AU - Antropova,N
AU - Ashrafian,H
AU - Back,T
AU - Chesus,M
AU - Corrado,GC
AU - Darzi,A
AU - Etemadi,M
AU - Garcia-Vicente,F
AU - Gilbert,FJ
AU - Halling-Brown,M
AU - Hassabis,D
AU - Jansen,S
AU - Karthikesalingam,A
AU - Kelly,CJ
AU - King,D
AU - Ledsam,JR
AU - Melnick,D
AU - Mostofi,H
AU - Peng,L
AU - Reicher,JJ
AU - Romera-Paredes,B
AU - Sidebottom,R
AU - Suleyman,M
AU - Tse,D
AU - Young,KC
AU - De,Fauw J
AU - Shetty,S
DO - 10.1038/s41586-019-1799-6
EP - 94
PY - 2020///
SN - 0028-0836
SP - 89
TI - International evaluation of an AI system for breast cancer screening
T2 - Nature
UR - http://dx.doi.org/10.1038/s41586-019-1799-6
UR - https://www.ncbi.nlm.nih.gov/pubmed/31894144
UR - http://hdl.handle.net/10044/1/76203
VL - 577
ER -
