Continuous Learning AI in Radiology: Implementation Principles and Early Applications

被引：127

作者：

Pianykh, Oleg S. ^{[1
]}

Langs, Georg ^{[3
,4
]}

Dewey, Marc ^{[2
,5
]}

Enzmann, Dieter R. ^{[2
,6
]}

Herold, Christian J. ^{[2
,3
]}

Schoenberg, Stefan O. ^{[2
,7
]}

Brink, James A. ^{[1
,2
]}

机构：

[1] Harvard Med Sch, Massachusetts Gen Hosp, Dept Radiol, 55 Fruit St,FND 210, Boston, MA 02114 USA

[2] Int Soc Strateg Studies Radiol IS3R, Vienna, Austria

[3] Med Univ Vienna, Dept Biomed Imaging & Image Guided Therapy, Vienna, Austria

[4] MIT, Comp Sci & Artificial Intelligence Lab, Boston, MA USA

[5] Charite, Dept Radiol, Berlin, Germany

[6] Univ Calif Los Angeles, David Geffen Sch Med, Dept Radiol Sci, Los Angeles, CA USA

[7] Heidelberg Univ, Univ Med Ctr Mannheim, Med Fac Mannheim, Inst Clin Radiol & Nucl Med, Mannheim, Germany

来源：

RADIOLOGY | 2020年 / 297卷 / 01期

关键词：

ARTIFICIAL-INTELLIGENCE; NEURAL-NETWORKS; CANCER; COMPUTER;

D O I：

10.1148/radiol.2020200038

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

Artificial intelligence (AI) is becoming increasingly present in radiology and health care. This expansion is driven by the principal AI strengths: automation, accuracy, and objectivity. However, as radiology AI matures to become fully integrated into the daily radiology routine, it needs to go beyond replicating static models, toward discovering new knowledge from the data and environments around it. Continuous learning AI presents the next substantial step in this direction and brings a new set of opportunities and challenges. Herein, the authors discuss the main concepts and requirements for implementing continuous AI in radiology and illustrate them with examples from emerging applications. (C) RSNA, 2020

引用

页码：6 / 14

页数：9

共 54 条

[1] Data Science in Radiology: A Path Forward
Aerts, Hugo J. W. L.
[J]. CLINICAL CANCER RESEARCH, 2018, 24 (03) : 532 - 534
[2] Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
Aerts, Hugo J. W. L.
Velazquez, Emmanuel Rios
Leijenaar, Ralph T. H.
Parmar, Chintan
Grossmann, Patrick
Cavalho, Sara
Bussink, Johan
Monshouwer, Rene
Haibe-Kains, Benjamin
Rietveld, Derek
Hoebers, Frank
Rietbergen, Michelle M.
Leemans, C. Rene
Dekker, Andre
Quackenbush, John
Gillies, Robert J.
Lambin, Philippe
[J]. NATURE COMMUNICATIONS, 2014, 5
[3] Ali H. A., 2007, International Journal of Computers & Applications, V29, P259, DOI 10.2316/Journal.202.2007.3.202-1961
[4] Learning Cross-Protocol Radiomics and Deep Feature Standardization from CT Images of Texture Phantoms
Andrearczyk, Vincent
Depeursinge, Adrien
Mueller, Henning
[J]. MEDICAL IMAGING 2019: IMAGING INFORMATICS FOR HEALTHCARE, RESEARCH, AND APPLICATIONS, 2019, 10954
[5] [Anonymous], How transferable are features in deep neural networks?
[6] [Anonymous], Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD)
[7] Probabilistic Modeling of Imaging, Genetics and Diagnosis
Batmanghelich, Nematollah K.
Dalca, Adrian
Quon, Gerald
Sabuncu, Mert
Golland, Polina
[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (07) : 1765 - 1779
[8] Bengio Y., 2009, PROC ICML, V41, P41, DOI DOI 10.1145/1553374.15533802,5
[9] REAL-TIME CONTINUOUS AI SYSTEMS
BENNETT, ME
[J]. IEE PROCEEDINGS-D CONTROL THEORY AND APPLICATIONS, 1987, 134 (04): : 272 - 277
[10] Bloom J, BECKERS HOSP REV

← 1 2 3 4 5 6 →