RootPainter: deep learning segmentation of biological images with corrective annotation

Publikation: Bidrag til tidsskriftTidsskriftartikelfagfællebedømt

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 tidsskriftTidsskriftartikelfagfællebedømt

Harvard

Smith, AG, Han, E, Petersen, J, Olsen, NAF, Giese, C, Athmann, M, Dresbøll, DB & Thorup-Kristensen, K 2022, 'RootPainter: deep learning segmentation of biological images with corrective annotation', New Phytologist, bind 236, s. 774-791. https://doi.org/10.1111/nph.18387

APA

Smith, A. G., Han, E., Petersen, J., Olsen, N. A. F., Giese, C., Athmann, M., Dresbøll, D. B., & Thorup-Kristensen, K. (2022). RootPainter: deep learning segmentation of biological images with corrective annotation. New Phytologist, 236, 774-791. https://doi.org/10.1111/nph.18387

Vancouver

Smith AG, Han E, Petersen J, Olsen NAF, Giese C, Athmann M o.a. RootPainter: deep learning segmentation of biological images with corrective annotation. New Phytologist. 2022;236:774-791. https://doi.org/10.1111/nph.18387

Author

Smith, Abraham George ; Han, Eusun ; Petersen, Jens ; Olsen, Niels Alvin Faircloth ; Giese, Christian ; Athmann, Miriam ; Dresbøll, Dorte Bodin ; Thorup-Kristensen, Kristian. / RootPainter : deep learning segmentation of biological images with corrective annotation. I: New Phytologist. 2022 ; Bind 236. s. 774-791.

Bibtex

@article{3e041c68fc104a5cbedb2d5509971536,
title = "RootPainter: deep learning segmentation of biological images with corrective annotation",
abstract = "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.",
keywords = "biopore, deep learning, GUI, interactive machine learning, phenotyping, rhizotron, root nodule, segmentation",
author = "Smith, {Abraham George} and Eusun Han and Jens Petersen and Olsen, {Niels Alvin Faircloth} and Christian Giese and Miriam Athmann and Dresb{\o}ll, {Dorte Bodin} and Kristian Thorup-Kristensen",
note = "Publisher Copyright: {\textcopyright} 2022 The Authors. New Phytologist {\textcopyright} 2022 New Phytologist Foundation.",
year = "2022",
doi = "10.1111/nph.18387",
language = "English",
volume = "236",
pages = "774--791",
journal = "New Phytologist",
issn = "0028-646X",
publisher = "Academic Press",

}

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