Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201701662> ?p ?o ?g. }
- W3201701662 abstract "Abstract Though consistently shown to detect mammographically occult cancers, breast ultrasound has been noted to have high false-positive rates. In this work, we present an AI system that achieves radiologist-level accuracy in identifying breast cancer in ultrasound images. Developed on 288,767 exams, consisting of 5,442,907 B-mode and Color Doppler images, the AI achieves an area under the receiver operating characteristic curve (AUROC) of 0.976 on a test set consisting of 44,755 exams. In a retrospective reader study, the AI achieves a higher AUROC than the average of ten board-certified breast radiologists (AUROC: 0.962 AI, 0.924 ± 0.02 radiologists). With the help of the AI, radiologists decrease their false positive rates by 37.3% and reduce requested biopsies by 27.8%, while maintaining the same level of sensitivity. This highlights the potential of AI in improving the accuracy, consistency, and efficiency of breast ultrasound diagnosis." @default.
- W3201701662 created "2021-10-11" @default.
- W3201701662 creator A5003554728 @default.
- W3201701662 creator A5003735451 @default.
- W3201701662 creator A5006551978 @default.
- W3201701662 creator A5007346529 @default.
- W3201701662 creator A5010954824 @default.
- W3201701662 creator A5013882013 @default.
- W3201701662 creator A5015601146 @default.
- W3201701662 creator A5015696229 @default.
- W3201701662 creator A5021579153 @default.
- W3201701662 creator A5022340038 @default.
- W3201701662 creator A5023066145 @default.
- W3201701662 creator A5023660328 @default.
- W3201701662 creator A5026754321 @default.
- W3201701662 creator A5028606188 @default.
- W3201701662 creator A5035602695 @default.
- W3201701662 creator A5036756598 @default.
- W3201701662 creator A5047540039 @default.
- W3201701662 creator A5049693451 @default.
- W3201701662 creator A5053088612 @default.
- W3201701662 creator A5054022463 @default.
- W3201701662 creator A5054427605 @default.
- W3201701662 creator A5067875697 @default.
- W3201701662 creator A5070556265 @default.
- W3201701662 creator A5075080165 @default.
- W3201701662 creator A5080296152 @default.
- W3201701662 creator A5084679466 @default.
- W3201701662 creator A5088825333 @default.
- W3201701662 creator A5089245216 @default.
- W3201701662 creator A5089302664 @default.
- W3201701662 date "2021-09-24" @default.
- W3201701662 modified "2023-10-11" @default.
- W3201701662 title "Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams" @default.
- W3201701662 cites W1534477342 @default.
- W3201701662 cites W1909268051 @default.
- W3201701662 cites W1972489770 @default.
- W3201701662 cites W1980527762 @default.
- W3201701662 cites W1993584845 @default.
- W3201701662 cites W1994488211 @default.
- W3201701662 cites W2009629689 @default.
- W3201701662 cites W2074811485 @default.
- W3201701662 cites W2086543716 @default.
- W3201701662 cites W2092128146 @default.
- W3201701662 cites W2097036415 @default.
- W3201701662 cites W2106671991 @default.
- W3201701662 cites W2124653673 @default.
- W3201701662 cites W2135118182 @default.
- W3201701662 cites W2141014056 @default.
- W3201701662 cites W2145205109 @default.
- W3201701662 cites W2149988868 @default.
- W3201701662 cites W2160408484 @default.
- W3201701662 cites W2253584488 @default.
- W3201701662 cites W2295107390 @default.
- W3201701662 cites W2302255633 @default.
- W3201701662 cites W2469066941 @default.
- W3201701662 cites W2549976854 @default.
- W3201701662 cites W2619383789 @default.
- W3201701662 cites W2619880275 @default.
- W3201701662 cites W2740028789 @default.
- W3201701662 cites W2741140850 @default.
- W3201701662 cites W2744692634 @default.
- W3201701662 cites W2745926851 @default.
- W3201701662 cites W2746791238 @default.
- W3201701662 cites W2772603135 @default.
- W3201701662 cites W2776140409 @default.
- W3201701662 cites W2809348156 @default.
- W3201701662 cites W2895793770 @default.
- W3201701662 cites W2913774342 @default.
- W3201701662 cites W2929215516 @default.
- W3201701662 cites W2939142770 @default.
- W3201701662 cites W2955429674 @default.
- W3201701662 cites W2966875446 @default.
- W3201701662 cites W2970546341 @default.
- W3201701662 cites W2975029521 @default.
- W3201701662 cites W2977497532 @default.
- W3201701662 cites W2979634944 @default.
- W3201701662 cites W2982092517 @default.
- W3201701662 cites W2991372685 @default.
- W3201701662 cites W3003086109 @default.
- W3201701662 cites W3016608747 @default.
- W3201701662 cites W3033158784 @default.
- W3201701662 cites W3110722024 @default.
- W3201701662 cites W3112635222 @default.
- W3201701662 cites W3119005666 @default.
- W3201701662 cites W3119612737 @default.
- W3201701662 cites W3128646645 @default.
- W3201701662 cites W3154126551 @default.
- W3201701662 cites W3161550517 @default.
- W3201701662 cites W3209042722 @default.
- W3201701662 cites W4242614154 @default.
- W3201701662 cites W3082740960 @default.
- W3201701662 doi "https://doi.org/10.1038/s41467-021-26023-2" @default.
- W3201701662 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8463596" @default.
- W3201701662 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34561440" @default.
- W3201701662 hasPublicationYear "2021" @default.
- W3201701662 type Work @default.
- W3201701662 sameAs 3201701662 @default.
- W3201701662 citedByCount "69" @default.
- W3201701662 countsByYear W32017016622021 @default.