Medical deep learning-A systematic meta-review

被引：136

作者：

Egger, Jan ^{[1
,2
,3
,4
,5
]}

Gsaxner, Christina ^{[1
,2
,3
]}

Pepe, Antonio ^{[1
,3
]}

Pomykala, Kelsey L. ^{[4
]}

Jonske, Frederic ^{[3
,4
]}

Kurz, Manuel ^{[1
,3
]}

Li, Jianning ^{[1
,3
,4
]}

Kleesiek, Jens ^{[4
,5
,6
]}

机构：

[1] Graz Univ Technol, Inst Comp Graph & Vis, Fac Comp Sci & Biomed Engn, Inffeldgasse 16, A-8010 Graz, Styria, Austria

[2] Med Univ Graz, Dept Oral &Maxillofacial Surg, Auenbruggerpl 5-1, A-8036 Graz, Styria, Austria

[3] Comp Algorithms Med Lab, Graz, Styria, Austria

[4] Univ Med Essen, Inst Med IKIM, Girardetstr 2, D-45131 Essen, Germany

[5] Univ Med Essen, Canc Res Ctr Cologne Essen CCCE, Hufelandstr 55, D-45147 Essen, Germany

[6] German Canc Consortium DKTK, Partner Site Essen, Hufelandstr 55, D-45147 Essen, Germany

来源：

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE | 2022年 / 221卷

基金：

奥地利科学基金会;

关键词：

Deep learning; Artificial neural networks; Machine learning; Data analysis; Image analysis; Medical image analysis; Medical image processing; Medical imaging; Patient data; Pathology; Detection; Segmentation; Registration; Generative adversarial networks; PubMed; Systematic; Review; Survey; Meta-review; Meta-survey; NEURAL-NETWORKS; IMAGE; RECOGNITION;

D O I：

10.1016/j.cmpb.2022.106874

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Deep learning has remarkably impacted several different scientific disciplines over the last few years. For example, in image processing and analysis, deep learning algorithms were able to outperform other cutting-edge methods. Additionally, deep learning has delivered state-of-the-art results in tasks like autonomous driving, outclassing previous attempts. There are even instances where deep learning outperformed humans, for example with object recognition and gaming. Deep learning is also showing vast potential in the medical domain. With the collection of large quantities of patient records and data, and a trend towards personalized treatments, there is a great need for automated and reliable processing and analysis of health information. Patient data is not only collected in clinical centers, like hospitals and private practices, but also by mobile healthcare apps or online websites. The abundance of collected patient data and the recent growth in the deep learning field has resulted in a large increase in research effort s. In Q2/2020, the search engine PubMed returned already over 11,0 0 0 results for the search term 'deep learning', and around 90% of these publications are from the last three years. However, even though PubMed represents the largest search engine in the medical field, it does not cover all medical-related publications. Hence, a complete overview of the field of 'medical deep learning' is almost impossible to obtain and acquiring a full overview of medical sub-fields is becoming increasingly more difficult. Nevertheless, several review and survey articles about medical deep learning have been published within the last few years. They focus, in general, on specific medical scenarios, like the analysis of medical images containing specific pathologies. With these surveys as a foundation, the aim of this article is to provide the first high-level, systematic meta-review of medical deep learning surveys. (c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )

引用

页数：22

共 158 条

[1]

Abadi M, 2016, ACM SIGPLAN NOTICES, V51, P1, DOI [10.1145/2951913.2976746, 10.1145/3022670.2976746]

[2] A review of uncertainty quantification in deep learning: Techniques, applications and challenges [J].