Automated Training of Deep Convolutional Neural Networks for Cell Segmentation

Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created automati...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Scientific reports Ročník 7; číslo 1; s. 7860 - 7
Hlavní autoři: Sadanandan, Sajith Kecheril, Ranefall, Petter, Le Guyader, Sylvie, Wählby, Carolina
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Nature Publishing Group UK 10.08.2017
Nature Publishing Group
Nature Portfolio
Témata:
14
14/63
631/114/1564
631/80/2373
Computerized Image Processing
Datoriserad bildbehandling
Humanities and Social Sciences
Image processing
multidisciplinary
Neural networks
Science
Science (multidisciplinary)
Segmentation
Training
ISSN:2045-2322, 2045-2322
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created automatically using fluorescently labeled cells, perform similar to manual annotations.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-017-07599-6