当前位置: X-MOL 学术Nat. Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams
Nature Communications ( IF 14.7 ) Pub Date : 2021-09-24 , DOI: 10.1038/s41467-021-26023-2
Yiqiu Shen 1 , Farah E Shamout 2 , Jamie R Oliver 3 , Jan Witowski 3 , Kawshik Kannan 4 , Jungkyu Park 5 , Nan Wu 1 , Connor Huddleston 3 , Stacey Wolfson 3 , Alexandra Millet 3 , Robin Ehrenpreis 3 , Divya Awal 3 , Cathy Tyma 3 , Naziya Samreen 3 , Yiming Gao 3 , Chloe Chhor 3 , Stacey Gandhi 3 , Cindy Lee 3 , Sheila Kumari-Subaiya 3 , Cindy Leonard 3 , Reyhan Mohammed 3 , Christopher Moczulski 3 , Jaime Altabet 3 , James Babb 3 , Alana Lewin 3 , Beatriu Reig 3 , Linda Moy 3, 5 , Laura Heacock 3 , Krzysztof J Geras 1, 3, 5
Affiliation  

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.



中文翻译:

人工智能系统减少了乳腺超声检查解释中的假阳性结果

尽管一直被证明可以检测出乳房 X 线照相术中隐匿的癌症,但乳房超声已被注意到具有很高的假阳性率。在这项工作中,我们提出了一个 AI 系统,可以在超声图像中识别乳腺癌方面达到放射科医师级别的准确性。该 AI 基于 288,767 次检查开发,包括 5,442,907 张 B 模式和彩色多普勒图像,在包含 44,755 次检查的测试集上实现了 0.976 的接受者操作特征曲线下面积 (AUROC)。在一项回顾性读者研究中,AI 获得的 AUROC 高于十名获得委员会认证的乳腺放射科医生的平均值(AUROC:0.962 AI,0.924 ± 0.02 放射科医生)。在 AI 的帮助下,放射科医生将他们的假阳性率降低了 37.3%,并将要求的活检减少了 27.8%,同时保持了相同的灵敏度水平。

更新日期:2021-09-24
down
wechat
bug