RootPainter: deep learning segmentation of biological images with corrective annotation
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
RootPainter : deep learning segmentation of biological images with corrective annotation. / Smith, Abraham George; Han, Eusun; Petersen, Jens; Olsen, Niels Alvin Faircloth; Giese, Christian; Athmann, Miriam; Dresbøll, Dorte Bodin; Thorup-Kristensen, Kristian.
I: New Phytologist, Bind 236, 2022, s. 774-791.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - RootPainter
T2 - deep learning segmentation of biological images with corrective annotation
AU - Smith, Abraham George
AU - Han, Eusun
AU - Petersen, Jens
AU - Olsen, Niels Alvin Faircloth
AU - Giese, Christian
AU - Athmann, Miriam
AU - Dresbøll, Dorte Bodin
AU - Thorup-Kristensen, Kristian
N1 - Publisher Copyright: © 2022 The Authors. New Phytologist © 2022 New Phytologist Foundation.
PY - 2022
Y1 - 2022
N2 - Convolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machine-learning background. We present RootPainter, an open-source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis. We evaluate RootPainter by training models for root length extraction from chicory (Cichorium intybus L.) roots in soil, biopore counting, and root nodule counting. We also compare dense annotations with corrective ones that are added during the training process based on the weaknesses of the current model. Five out of six times the models trained using RootPainter with corrective annotations created within 2 h produced measurements strongly correlating with manual measurements. Model accuracy had a significant correlation with annotation duration, indicating further improvements could be obtained with extended annotation. Our results show that a deep-learning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with < 2 h of annotation time. They indicate that, when using RootPainter, for many datasets it is possible to annotate, train, and complete data processing within 1 d.
AB - Convolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machine-learning background. We present RootPainter, an open-source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis. We evaluate RootPainter by training models for root length extraction from chicory (Cichorium intybus L.) roots in soil, biopore counting, and root nodule counting. We also compare dense annotations with corrective ones that are added during the training process based on the weaknesses of the current model. Five out of six times the models trained using RootPainter with corrective annotations created within 2 h produced measurements strongly correlating with manual measurements. Model accuracy had a significant correlation with annotation duration, indicating further improvements could be obtained with extended annotation. Our results show that a deep-learning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with < 2 h of annotation time. They indicate that, when using RootPainter, for many datasets it is possible to annotate, train, and complete data processing within 1 d.
KW - biopore
KW - deep learning
KW - GUI
KW - interactive machine learning
KW - phenotyping
KW - rhizotron
KW - root nodule
KW - segmentation
U2 - 10.1111/nph.18387
DO - 10.1111/nph.18387
M3 - Journal article
C2 - 35851958
AN - SCOPUS:85135739109
VL - 236
SP - 774
EP - 791
JO - New Phytologist
JF - New Phytologist
SN - 0028-646X
ER -
ID: 318438881