2019
DOI: 10.1055/a-1008-9400
|View full text |Cite
|
Sign up to set email alerts
|

Digitale Bildverarbeitung und Tiefe Neuronale Netze in der Augenheilkunde – aktuelle Trends

Abstract: ZusammenfassungDer Einsatz von Tiefen Neuronalen Netzen (Deep Learning) eröffnet neue Möglichkeiten in der digitalen Bildverarbeitung. Auch für die Auswertung von Bilddaten in der Ophthalmologie wird diese Methode erfolgreich eingesetzt und findet weite Verbreitung. In diesem Artikel wird die methodische Vorgehensweise beim Deep Learning betrachtet und der klassischen Vorgehensweise für die Entwicklung von Methoden für die digitale Bildverarbeitung gegenübergestellt. Dabei wird auf Unterschiede eingegangen und… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 37 publications
0
3
0
Order By: Relevance
“…Even in those areas in which artificial intelligence has high potential, this is tied in particular to the availability of data. A challenge that remains is therefore the existence and selection of training data (Bartschat et al 2019(Bartschat et al : 1401. Whether the training data represent a comprehensive problem domain for the posed problem depends on whether later results are also correctly classified or processed.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Even in those areas in which artificial intelligence has high potential, this is tied in particular to the availability of data. A challenge that remains is therefore the existence and selection of training data (Bartschat et al 2019(Bartschat et al : 1401. Whether the training data represent a comprehensive problem domain for the posed problem depends on whether later results are also correctly classified or processed.…”
Section: Discussionmentioning
confidence: 99%
“…Whether the training data represent a comprehensive problem domain for the posed problem depends on whether later results are also correctly classified or processed. Precisely this comprehensiveness is usually hard to ensure for rare or complex events (Bartschat et al 2019(Bartschat et al : 1401, whereas what is rare and complex for AI can also be a simple manual task from a human perspective.…”
Section: Discussionmentioning
confidence: 99%
“…Machine learning, a form of AI that uses computerized algorithms that learn and improve with experience, will find increasing application in medicine in the coming years [7]. The AI concepts of deep learning and artificial neural networks have become the cornerstones of significant achievements in image processing [8][9][10]. Several studies have demonstrated the effectiveness of deep learning algorithms for the interpretation of radiologic images compared to human experts [11][12][13].…”
Section: Introductionmentioning
confidence: 99%