ID:
publications-1853
Type:
Peer reviewed articles
Year:
2022
Authors:
Abraham George Smith, Eusun Han, Jens Petersen, Niels Alvin Faircloth Olsen, Christian Giese, Miriam Athmann, Dorte Bodin DresbĆøll, Kristian Thorup-Kristensen
Title:
RootPainter: deep learning segmentation of biological images with corrective annotation
Venue/Journal:
New Phytologist
DOI:
10.1111/nph.18387
Research type:
Uncategorized
Water System:
Precipitation & Ecological Systems
Technical Focus:
Abstract:
SummaryConvolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machineālearning background. We present RootPainter, an openāsource graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis.We evaluate RootPainterby training models for root length extraction from chicory (Cichorium intybusL.) 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 RootPainterwith corrective annotations created within 2āh 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 deepālearning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with <ā2āh of annotation time. They indicate that, when using RootPainter, for many datasets it is possible to annotate, train, and complete data processing within 1ād.
Link with Projects:
884364
Link with Tools:
Related policies:
ID:
