2022
DOI: 10.3389/fmed.2022.959068
|View full text |Cite
|
Sign up to set email alerts
|

How to learn with intentional mistakes: NoisyEnsembles to overcome poor tissue quality for deep learning in computational pathology

Abstract: There is a lot of recent interest in the field of computational pathology, as many algorithms are introduced to detect, for example, cancer lesions or molecular features. However, there is a large gap between artificial intelligence (AI) technology and practice, since only a small fraction of the applications is used in routine diagnostics. The main problems are the transferability of convolutional neural network (CNN) models to data from other sources and the identification of uncertain predictions. The role … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
2
0
4

Year Published

2023
2023
2024
2024

Publication Types

Select...
3

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(6 citation statements)
references
References 38 publications
0
2
0
4
Order By: Relevance
“…Für Ensembles wurden je 15 Modelle durch Bagging trainiert und aggregiert. Bei NoisyEnsembles wurden zusätzlich 15 % der Labels im Training verfälscht [ 13 ].…”
Section: Materials Und Methodenunclassified
See 3 more Smart Citations
“…Für Ensembles wurden je 15 Modelle durch Bagging trainiert und aggregiert. Bei NoisyEnsembles wurden zusätzlich 15 % der Labels im Training verfälscht [ 13 ].…”
Section: Materials Und Methodenunclassified
“…Sollen Daten genutzt werden, welche vom Trainingsdatensatz abweichen, verlieren Modelle häufig Genauigkeit [ 13 ]. Dies kann von vielen Faktoren beeinflusst werden (Abb.…”
Section: Einflussfaktoren Auf Transferierbarkeitunclassified
See 2 more Smart Citations
“…Quality issues are also recognised to impact on the development and performance of AI tools for histopathology [4][5][6][7][8], and without assurance of performance reproducibility of such tools, their approval by regulatory bodies and their integration into the clinical setting will remain limited.…”
Section: Introductionmentioning
confidence: 99%