Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams.
Adult
Aged
Algorithms
Artificial Intelligence
Breast
/ diagnostic imaging
Breast Neoplasms
/ diagnosis
Early Detection of Cancer
Female
Humans
Mammography
/ methods
Middle Aged
ROC Curve
Radiologists
/ statistics & numerical data
Reproducibility of Results
Retrospective Studies
Ultrasonography
/ methods
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
24 09 2021
24 09 2021
Historique:
received:
22
07
2021
accepted:
14
09
2021
entrez:
25
9
2021
pubmed:
26
9
2021
medline:
27
10
2021
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 34561440
doi: 10.1038/s41467-021-26023-2
pii: 10.1038/s41467-021-26023-2
pmc: PMC8463596
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
5645Subventions
Organisme : NIBIB NIH HHS
ID : P41 EB017183
Pays : United States
Organisme : NCI NIH HHS
ID : R21 CA225175
Pays : United States
Informations de copyright
© 2021. The Author(s).
Références
Sung, H. et al. Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 71, 209–249 (2021).
doi: 10.3322/caac.21660
pubmed: 33538338
Siegel, R. L., Miller, K. D., Fuchs, H. E. & Jemal, A. Cancer statistics, 2021. CA Cancer J. Clin. 71, 7–33 (2021).
pubmed: 33433946
doi: 10.3322/caac.21654
Arleo, E. K., Hendrick, R. E., Helvie, M. A. & Sickles, E. A. Comparison of recommendations for screening mammography using cisnet models. Cancer 123, 3673–3680 (2017).
pubmed: 28832983
doi: 10.1002/cncr.30842
Feig, S. Cost-effectiveness of mammography, MRI, and ultrasonography for breast cancer screening. Radiol. Clin. 48, 879–891 (2010).
doi: 10.1016/j.rcl.2010.06.002
Kolb, T. M., Lichy, J. & Newhouse, J. H. Comparison of the performance of screening mammography, physical examination, and breast us and evaluation of factors that influence them: an analysis of 27,825 patient evaluations. Radiology 225, 165–175 (2002).
pubmed: 12355001
doi: 10.1148/radiol.2251011667
Boyd, N. F. et al. Mammographic density and the risk and detection of breast cancer. N. Engl. J. Med. 356, 227–236 (2007).
pubmed: 17229950
doi: 10.1056/NEJMoa062790
Berg, W. A. et al. Ultrasound as the primary screening test for breast cancer: analysis from ACRIN 6666. J. Natl Cancer Inst. 108, djv367 (2016).
pubmed: 26712110
doi: 10.1093/jnci/djv367
Dempsey, P. J. The history of breast ultrasound. J. Ultrasound Med. 23, 887–894 (2004).
pubmed: 15292555
doi: 10.7863/jum.2004.23.7.887
Chung, M. et al. US as the primary imaging modality in the evaluation of palpable breast masses in breastfeeding women, including those of advanced maternal age. Radiology 297, 316–324 (2020).
pubmed: 32870133
doi: 10.1148/radiol.2020201036
Sood, R. et al. Ultrasound for breast cancer detection globally: a systematic review and meta-analysis. J. Global Oncol. 5, 1–17 (2019).
Berg, W. A. et al. Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer. JAMA 299, 2151–2163 (2008).
pubmed: 18477782
pmcid: 2718688
doi: 10.1001/jama.299.18.2151
Sickles, E. A. et al. ACR BI-RADS® atlas, breast imaging reporting and data system. Reston, VA: American College of Radiology 39–48 (2013).
Crystal, P., Strano, S. D., Shcharynski, S. & Koretz, M. J. Using sonography to screen women with mammographically dense breasts. Am. J. Roentgenol. 181, 177–182 (2003).
doi: 10.2214/ajr.181.1.1810177
Lazarus, E., Mainiero, M. B., Schepps, B., Koelliker, S. L. & Livingston, L. S. BI-RADS lexicon for us and mammography: interobserver variability and positive predictive value. Radiology 239, 385–391 (2006).
pubmed: 16569780
doi: 10.1148/radiol.2392042127
Yang, L. et al. Performance of ultrasonography screening for breast cancer: a systematic review and meta-analysis. BMC Cancer 20, 1–15 (2020).
doi: 10.1186/s12885-020-06992-1
Berg, W. A. et al. Detection of breast cancer with addition of annual screening ultrasound or a single screening MRI to mammography in women with elevated breast cancer risk. JAMA 307, 1394–1404 (2012).
pubmed: 22474203
pmcid: 3891886
doi: 10.1001/jama.2012.388
Corsetti, V. et al. Evidence of the effect of adjunct ultrasound screening in women with mammography-negative dense breasts: interval breast cancers at 1 year follow-up. Eur. J. Cancer 47, 1021–1026 (2011).
pubmed: 21211962
doi: 10.1016/j.ejca.2010.12.002
Chen, D.-R. & Hsiao, Y.-H. Computer-aided diagnosis in breast ultrasound. J. Med. Ultrasound 16, 46–56 (2008).
doi: 10.1016/S0929-6441(08)60005-3
Shen, W.-C., Chang, R.-F., Moon, W. K., Chou, Y.-H. & Huang, C.-S. Breast ultrasound computer-aided diagnosis using BI-RADS features. Acad. Radiol. 14, 928–939 (2007).
pubmed: 17659238
doi: 10.1016/j.acra.2007.04.016
Lee, J.-H. et al. Fourier-based shape feature extraction technique for computer-aided b-mode ultrasound diagnosis of breast tumor. In Proceedings of the 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 6551–6554 (IEEE, 2012).
Ding, J., Cheng, H.-D., Huang, J., Liu, J. & Zhang, Y. Breast ultrasound image classification based on multiple-instance learning. J. Digital Imaging 25, 620–627 (2012).
doi: 10.1007/s10278-012-9499-x
Bing, L. & Wang, W. Sparse representation based multi-instance learning for breast ultrasound image classification. Comput. Math. Methods Med. 2017, 7894705 https://doi.org/10.1155/2017/7894705 (2017).
pubmed: 28690670
pmcid: 5463197
doi: 10.1155/2017/7894705
Prabhakar, T. & Poonguzhali, S. Automatic detection and classification of benign and malignant lesions in breast ultrasound images using texture morphological and fractal features. In 2017 10th Biomedical Engineering International Conference (BMEiCON), 1–5 (IEEE, 2017).
Zhang, Q., Suo, J., Chang, W., Shi, J. & Chen, M. Dual-modal computer-assisted evaluation of axillary lymph node metastasis in breast cancer patients on both real-time elastography and b-mode ultrasound. Eur. J. Radiol. 95, 66–74 (2017).
pubmed: 28987700
doi: 10.1016/j.ejrad.2017.07.027
Gao, Y., Geras, K. J., Lewin, A. A. & Moy, L. New frontiers: an update on computer-aided diagnosis for breast imaging in the age of artificial intelligence. Am. J. Roentgenol. 212, 300–307 (2019).
doi: 10.2214/AJR.18.20392
Geras, K. J., Mann, R. M. & Moy, L. Artificial intelligence for mammography and digital breast tomosynthesis: current concepts and future perspectives. Radiology 293, 246–259 (2019).
pubmed: 31549948
doi: 10.1148/radiol.2019182627
Fujioka, T. et al. The utility of deep learning in breast ultrasonic imaging: a review. Diagnostics 10, 1055 (2020).
pmcid: 7762151
doi: 10.3390/diagnostics10121055
Cheng, J.-Z. et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in us images and pulmonary nodules in ct scans. Sci. Rep. 6, 1–13 (2016).
Yap, M. H. et al. Automated breast ultrasound lesions detection using convolutional neural networks. IEEE J. Biomed. Health Informatics 22, 1218–1226 (2017).
doi: 10.1109/JBHI.2017.2731873
Al-Dhabyani, W., Gomaa, M., Khaled, H. & Aly, F. Deep learning approaches for data augmentation and classification of breast masses using ultrasound images. Int. J. Adv. Computer Sci. Appl. 10, 1–11 (2019).
Fleury, E. & Marcomini, K. Performance of machine learning software to classify breast lesions using BI-RADS radiomic features on ultrasound images. Eur. Radiol. Exp. 3, 34 (2019).
pubmed: 31385114
pmcid: 6682836
doi: 10.1186/s41747-019-0112-7
Tanaka, H., Chiu, S.-W., Watanabe, T., Kaoku, S. & Yamaguchi, T. Computer-aided diagnosis system for breast ultrasound images using deep learning. Phys. Med. Biol. 64, 235013 (2019).
pubmed: 31645021
doi: 10.1088/1361-6560/ab5093
Cao, Z., Duan, L., Yang, G., Yue, T. & Chen, Q. An experimental study on breast lesion detection and classification from ultrasound images using deep learning architectures. BMC Med. Imaging 19, 51 (2019).
pubmed: 31262255
pmcid: 6604293
doi: 10.1186/s12880-019-0349-x
Han, S. et al. A deep learning framework for supporting the classification of breast lesions in ultrasound images. Phys. Med. Biol. 62, 7714 (2017).
pubmed: 28753132
doi: 10.1088/1361-6560/aa82ec
Becker, A. S. et al. Classification of breast cancer in ultrasound imaging using a generic deep learning analysis software: a pilot study. Br. J. Radiol. 91, 20170576 (2018).
pubmed: 29215311
pmcid: 5965470
Xiao, T. et al. Comparison of transferred deep neural networks in ultrasonic breast masses discrimination. BioMed Res. Int. 2018, 4605191 https://doi.org/10.1155/2018/4605191 (2018).
pubmed: 30035122
pmcid: 6033250
doi: 10.1155/2018/4605191
Oquab, M., Bottou, L., Laptev, I. & Sivic, J. Is object localization for free?-weakly-supervised learning with convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 685–694 (2015).
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2921–2929 (2016).
Zhou, Z.-H. A brief introduction to weakly supervised learning. Natl Sci. Rev. 5, 44–53 (2018).
doi: 10.1093/nsr/nwx106
Al-Dhabyani, W., Gomaa, M., Khaled, H. & Fahmy, A. Dataset of breast ultrasound images. Data in Brief 28, 104863 (2020).
pubmed: 31867417
doi: 10.1016/j.dib.2019.104863
Shamout, F. et al. The NYU breast ultrasound dataset v1.0. Tech. Rep. (2021). Available at https://cs.nyu.edu/~kgeras/reports/ultrasound_datav1.0.pdf .
Du, H.-Y., Lin, B.-R. & Huang, D.-P. Ultrasonographic findings of triple-negative breast cancer. Int. J. Clin. Exp. Med. 8, 10040 (2015).
pubmed: 26309697
pmcid: 4538191
Ciritsis, A. et al. Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making. Eur. Radiol. 29, 5458–5468 (2019).
pubmed: 30927100
doi: 10.1007/s00330-019-06118-7
Houssami, N., Ciatto, S., Irwig, L., Simpson, J. & Macaskill, P. The comparative sensitivity of mammography and ultrasound in women with breast symptoms: an age-specific analysis. Breast 11, 125–130 (2002).
pubmed: 14965658
doi: 10.1054/brst.2001.0391
Baltrušaitis, T., Ahuja, C. & Morency, L.-P. Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intelligence 41, 423–443 (2018).
doi: 10.1109/TPAMI.2018.2798607
Zhou, T., Ruan, S. & Canu, S. A review: deep learning for medical image segmentation using multi-modality fusion. Array 3, 100004 (2019).
doi: 10.1016/j.array.2019.100004
Barinov, L. et al. Impact of data presentation on physician performance utilizing artificial intelligence-based computer-aided diagnosis and decision support systems. J. Digital Imaging 32, 408–416 (2019).
doi: 10.1007/s10278-018-0132-5
Dong, F. et al. One step further into the blackbox: a pilot study of how to build more confidence around an ai-based decision system of breast nodule assessment in 2d ultrasound. Eur. Radiol. 1–10 (2021).
Zhao, C. et al. Reducing the number of unnecessary biopsies of US-BI-RADS 4a lesions through a deep learning method for residents-in-training: a cross-sectional study. BMJ Open 10, e035757 (2020).
pubmed: 32513885
pmcid: 7282415
doi: 10.1136/bmjopen-2019-035757
Fujioka, T. et al. Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network. Jpn. J. Radiol. 37, 466–472 (2019).
pubmed: 30888570
doi: 10.1007/s11604-019-00831-5
Mango, V. L., Sun, M., Wynn, R. T. & Ha, R. Should we ignore, follow, or biopsy? impact of artificial intelligence decision support on breast ultrasound lesion assessment. Am. J. Roentgenol. 214, 1445–1452 (2020).
doi: 10.2214/AJR.19.21872
Qian, X. et al. Prospective assessment of breast cancer risk from multimodal multiview ultrasound images via clinically applicable deep learning. Nat. Biomed. Eng. 5, 522–532 (2021).
pubmed: 33875840
doi: 10.1038/s41551-021-00711-2
Collins, G. S., Reitsma, J. B., Altman, D. G. & Moons, K. G. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (tripod) the tripod statement. Circulation 131, 211–219 (2015).
pubmed: 25561516
pmcid: 4297220
doi: 10.1161/CIRCULATIONAHA.114.014508
LeCun, Y. & Bengio, Y. et al. Convolutional networks for images, speech, and time series. Handbook of Brain Theory and Neural Networks 3361, 1995 (1995).
He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. In European Conference on Computer Vision, 630–645 (Springer, 2016).
Ilse, M., Tomczak, J. M. & Welling, M. Attention-based deep multiple instance learning. Proceedings of the 35th International Conference on Machine Learning, In Proceedings of Machine Learning Research (eds Dy, J. & Krause, A.) 80, 2127–2136 (PMLR, 2018).
Shen, Y. et al. Globally-aware multiple instance classifier for breast cancer screening. In International Workshop on Machine Learning in Medical Imaging, 18–26 (Springer, 2019).
Shen, Y. et al. An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization. Med. Image Anal. 68, 101908 (2021).
pubmed: 33383334
doi: 10.1016/j.media.2020.101908
Shamout, F. E. et al. An artificial intelligence system for predicting the deterioration of covid-19 patients in the emergency department. NPJ Digital Med. 4, 1–11 (2021).
doi: 10.1038/s41746-021-00453-0
Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2014).
Caruana, R. Multitask learning: a knowledge-based source of inductive bias. In Proceedings of the Tenth International Conference on Machine Learning 41–48 (1993).
Bergstra, J. & Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learning Res. 13, 2 (2012).
Dietterich, T. G. Ensemble methods in machine learning. In International Workshop on Multiple Classifier Systems, 1–15 (Springer, 2000).
Shanmugam, D., Blalock, D., Balakrishnan, G. & Guttag, J. When and why test-time augmentation works. Preprint at https://arxiv.org/abs/2011.11156 (2020).
Lobo, J. M., Jiménez-Valverde, A. & Real, R. Auc: a misleading measure of the performance of predictive distribution models. Global Ecol. Biogeography 17, 145–151 (2008).
doi: 10.1111/j.1466-8238.2007.00358.x
Pedregosa, F. et al. Scikit-learn: Machine learning in python. J. Mach. Learning Res. 12, 2825–2830 (2011).
Johnson, R. W. An introduction to the bootstrap. Teaching Stat. 23, 49–54 (2001).
doi: 10.1111/1467-9639.00050
Chihara, L. & Hesterberg, T. Mathematical Statistics with Resampling and R (Wiley Online Library, 2011).
Liberman, L. & Menell, J. H. Breast imaging reporting and data system (BI-RADS). Radiol. Clin. 40, 409–430 (2002).
doi: 10.1016/S0033-8389(01)00017-3