Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms

JAMA network open - Tập 3 Số 3 - Trang e200265
Thomas Schaffter1, Diana S. M. Buist2, Christoph I. Lee3, Yaroslav Nikulin4, Dezső Ribli5, Yuanfang Guan6, William Lotter7, Zequn Jie8, Hao Du9, Sijia Wang10, Jiashi Feng11, Mengling Feng12, Hyo-Eun Kim13, F. Albiol14, Alberto Albiol15, Stephen Morrell16, Zbigniew Wojna17, Mehmet Eren Ahsen18, Umar Asif19, Antonio Jimeno Yepes19, Shivanthan A.C. Yohanandan19, Simona Rabinovici‐Cohen20, Darvin Yi21, Bruce Hoff1, Thomas Yu1, Elias Chaibub Neto1, Daniel L. Rubin22, Peter Lindholm23, Laurie R. Margolies24, Russell B. McBride25, Joseph H. Rothstein26, Weiva Sieh27, Rami Ben‐Ari20, Stefan Harrer19, Andrew D. Trister28, Stephen Friend1, Thea Norman29, Berkman Sahiner30, Fredrik Strand31,32, Justin Guinney1, Gustavo Stolovitzky33, Lester Mackey34, Joyce Cahoon35, Li Shen36, Jae Ho Sohn37, Hari Trivedi38, Yiqiu Shen39, Ljubomir Buturović40, José Costa Pereira41, Jaime S. Cardoso41, Eduardo Castro41, Karl Trygve Kalleberg42, Obioma Pelka43,44, Imane Nedjar45, Krzysztof J. Geras46, Felix Nensa44, Ethan Goan47, Sven Koitka43,46, L. Caballero14, David Cox48, Pavitra Krishnaswamy49, Gaurav Pandey26,50, Christoph M. Friedrich43, Dimitri Perrin47, Clinton Fookes47, Bibo Shi51, Gerard Cardoso Negrie52, Michael Kawczynski53, Kyunghyun Cho39, Can Son Khoo54, Joseph Y. Lo55, A. Gregory Sorensen7, Hwejin Jung56
1Computational Oncology, Sage Bionetworks, Seattle, Washington
2Kaiser Permanente Washington Health Research Institute, Seattle, Washington
3University of Washington School of Medicine, Seattle
4Therapixel, Paris, France
5Department of Physics of Complex Systems, ELTE Eötvös Loránd University, Budapest, Hungary
6Department of Computational Medicine and Bioinformatics, Michigan Medicine, University of Michigan, Ann Arbor
7DeepHealth Inc, Cambridge, Massachusetts
8Tencent AI Lab, Shenzhen, China
9National University of Singapore, Singapore
10Integrated Health Information Systems Pte Ltd, Singapore
11Department of Electrical and Computer Engineering, National University of Singapore, Singapore
12National University Health System, Singapore
13Lunit Inc, Seoul, Korea
14Instituto de Física Corpuscular (IFIC), CSIC–Universitat de València, Valencia, Spain
15Universitat Politecnica de Valencia, Valencia, Valenciana, Spain
16Centre for Medical Image Computing, University College London, Bloomsbury, London, United Kingdom
17Tensorflight Inc, Mountain View, California
18University of Illinois at Urbana-Champaign, Urbana
19IBM Research Australia, Melbourne, Australia
20IBM Research Haifa, Haifa University Campus, Mount Carmel, Haifa, Israel
21Stanford University, Stanford, California
22Department of Biomedical Data Science, Radiology, and Medicine (Biomedical Informatics), Stanford University, Stanford, California
23Department of Physiology and Pharmacology, Karolinska Institutet, Stockholm, Sweden
24Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, New York
25Department of Pathology, Molecular and Cell-based Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
26Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
27Department of Population Health Science and Policy, Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
28Fred Hutchinson Cancer Research Center, Seattle, Washington
29Bill and Melinda Gates Foundation, Seattle, Washington
30Center for Devices and Radiological Health, Food and Drug Administration, Silver Spring, Maryland
31Breast Radiology, Karolinska University Hospital, Stockholm, Sweden
32Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden
33IBM Research, Translational Systems Biology and Nanobiotechnology, Thomas J. Watson Research Center, Yorktown Heights, New York
34Microsoft New England Research and Development Center, Cambridge, Massachusetts
35North Carolina State University, Raleigh
36Icahn School of Medicine at Mount Sinai, New York, New York
37Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco
38Emory University, Atlanta, Georgia
39New York University, New York
40Clinical Persona, East Palo Alto, California
41Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal
42KolibriFX, Oslo, Norway
43Department of Computer Science, University of Applied Sciences and Arts, Dortmund, Germany
44Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
45Biomedical Engineering Laboratory, Tlemcen University, Tlemcen, Algeria
46Department of Radiology, NYU School of Medicine, New York, New York
47Queensland University of Technology, Brisbane, Australia
48MIT-IBM Watson AI Lab, IBM Research, Cambridge, Massachusetts
49Institute for Infocomm Research, A*STAR, Singapore
50Icahn Institute for Data Science and Genomic Technology, New York, New York
51Carl E. Ravin Advanced Imaging Laboratories, Department of Radiology, Duke University School of Medicine, Durham, North Carolina
52Satalia, London, United Kingdom
53Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco
54University College London, London, United Kingdom
55Department of Radiology, Duke University School of Medicine, Durham, North Carolina
56Korea University, Seoul, Korea

Tóm tắt

Từ khóa


Tài liệu tham khảo

Nelson, 2009, Screening for breast cancer: an update for the U.S. Preventive Services Task Force., Ann Intern Med, 151, 727, 10.7326/0003-4819-151-10-200911170-00009

Lehman, 2017, National performance benchmarks for modern screening digital mammography: update from the Breast Cancer Surveillance Consortium., Radiology, 283, 49, 10.1148/radiol.2016161174

Nelson, 2016, Harms of breast cancer screening: systematic review to update the 2009 US Preventive Services Task Force recommendation., Ann Intern Med, 164, 256, 10.7326/M15-0970

O’Donoghue, 2014, Aggregate cost of mammography screening in the United States: comparison of current practice and advocated guidelines., Ann Intern Med, 160, 145, 10.7326/M13-1217

Houssami, 2017, Artificial intelligence for breast cancer screening: opportunity or hype?, Breast, 36, 31, 10.1016/j.breast.2017.09.003

Trister, 2017, Will machine learning tip the balance in breast cancer screening?, JAMA Oncol, 3, 1463, 10.1001/jamaoncol.2017.0473

Fenton, 2007, Influence of computer-aided detection on performance of screening mammography., N Engl J Med, 356, 1399, 10.1056/NEJMoa066099

Lehman, 2015, Diagnostic accuracy of digital screening mammography with and without computer-aided detection., JAMA Intern Med, 175, 1828, 10.1001/jamainternmed.2015.5231

Obermeyer, 2016, Predicting the future: big data, machine learning, and clinical medicine., N Engl J Med, 375, 1216, 10.1056/NEJMp1606181

Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks., Nature, 542, 115, 10.1038/nature21056

Poplin, 2018, Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning., Nat Biomed Eng, 2, 158, 10.1038/s41551-018-0195-0

Bender, 2016, Challenges: crowdsourced solutions., Nature, 533, S62, 10.1038/533S62a

Mayo, 2019, Reduction of false-positive markings on mammograms: a retrospective comparison study using an artificial intelligence-based CAD., J Digit Imaging, 32, 618, 10.1007/s10278-018-0168-6

Rodríguez-Ruiz, 2019, Detection of breast cancer with mammography: effect of an artificial intelligence support system., Radiology, 290, 305, 10.1148/radiol.2018181371

Rodriguez-Ruiz, 2019, Stand-alone artificial intelligence for breast cancer detection in mammography: comparison with 101 radiologists., J Natl Cancer Inst, 111, 916, 10.1093/jnci/djy222

Conant, 2019, Improving accuracy and efficiency with concurrent use of artificial intelligence for digital breast tomosynthesis., Radiol Artif Intell, 1, 10.1148/ryai.2019180096

Wu, Deep neural networks improve radiologists’ performance in breast cancer screening, IEEE Trans Med Imaging

Krizhevsky, 2017, ImageNet classification with deep convolutional neural networks., Commun ACM, 60, 84, 10.1145/3098997

Saez-Rodriguez, 2016, Crowdsourcing biomedical research: leveraging communities as innovation engines., Nat Rev Genet, 17, 470, 10.1038/nrg.2016.69

Bossuyt, 2015, STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies., Radiology, 277, 826, 10.1148/radiol.2015151516

Guinney, 2018, Alternative models for sharing confidential biomedical data., Nat Biotechnol, 36, 391, 10.1038/nbt.4128

Wolpert, 1992, Stacked generalization., Neural Netw, 5, 241, 10.1016/S0893-6080(05)80023-1

Whalen, 2016, Predicting protein function and other biomedical characteristics with heterogeneous ensembles., Methods, 93, 92, 10.1016/j.ymeth.2015.08.016

Friedman, 2010, Regularization paths for generalized linear models via coordinate descent., J Stat Softw, 33, 1, 10.18637/jss.v033.i01

Ribli, 2018, Detecting and classifying lesions in mammograms with deep learning., Sci Rep, 8, 4165, 10.1038/s41598-018-22437-z

Akselrod-Ballin, 2019, Predicting breast cancer by applying deep learning to linked health records and mammograms., Radiology, 292, 331, 10.1148/radiol.2019182622

Lee, 2019, Artificial intelligence for breast cancer imaging: the new frontier?, J Natl Cancer Inst, 111, 875, 10.1093/jnci/djy223

Kuhn, A Short Introduction to the Caret Package

Lotter, 2017, Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 169, 10.1007/978-3-319-67558-9_20

SAGE Bionetworks. Digital mammography DREAM challenge. https://sagebionetworks.org/research-projects/digital-mammography-dream-challenge/. Accessed January 22, 2020.

Breast Cancer Surveillance Consortium. https://www.bcsc-research.org/. Accessed August 30, 2019.

SAGE Bionetworks. Synapse. https://www.synapse.org/. Accessed January 22, 2020.

Docker. https://www.docker.com/. Accessed January 22, 2020.

NIPS Proceedings. Faster R-CNN: towards real-time object detection with region proposal networks. https://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks. Accessed January 22, 2020.

GitHub. Code for classifying mammograms using an ensemble of models from the DREAM D.M. Challenge. https://github.com/Sage-Bionetworks/DigitalMammographyEnsemble. Accessed January 22, 2020.

Thông tin
Thông tin xuất bản

JAMA network open

Tập 3 Số 3

e200265

Thông tin tác giả