Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy

The recent developments in artificial intelligence have the potential to facilitate new research methods in ecology. Especially Deep Convolutional Neural Networks (DCNNs) have been shown to outperform other approaches in automatic image analyses. Here we apply a DCNN to facilitate quantitative wood...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Giulia Resente, Alexander Gillert, Mario Trouillier, Alba Anadon-Rosell, Richard L. Peters, Georg von Arx, Uwe von Lukas, Martin Wilmking
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/5dc098263318426dbb165835eb7a1342
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5dc098263318426dbb165835eb7a1342
record_format dspace
spelling oai:doaj.org-article:5dc098263318426dbb165835eb7a13422021-11-04T08:36:12ZMask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy1664-462X10.3389/fpls.2021.767400https://doaj.org/article/5dc098263318426dbb165835eb7a13422021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fpls.2021.767400/fullhttps://doaj.org/toc/1664-462XThe recent developments in artificial intelligence have the potential to facilitate new research methods in ecology. Especially Deep Convolutional Neural Networks (DCNNs) have been shown to outperform other approaches in automatic image analyses. Here we apply a DCNN to facilitate quantitative wood anatomical (QWA) analyses, where the main challenges reside in the detection of a high number of cells, in the intrinsic variability of wood anatomical features, and in the sample quality. To properly classify and interpret features within the images, DCNNs need to undergo a training stage. We performed the training with images from transversal wood anatomical sections, together with manually created optimal outputs of the target cell areas. The target species included an example for the most common wood anatomical structures: four conifer species; a diffuse-porous species, black alder (Alnus glutinosa L.); a diffuse to semi-diffuse-porous species, European beech (Fagus sylvatica L.); and a ring-porous species, sessile oak (Quercus petraea Liebl.). The DCNN was created in Python with Pytorch, and relies on a Mask-RCNN architecture. The developed algorithm detects and segments cells, and provides information on the measurement accuracy. To evaluate the performance of this tool we compared our Mask-RCNN outputs with U-Net, a model architecture employed in a similar study, and with ROXAS, a program based on traditional image analysis techniques. First, we evaluated how many target cells were correctly recognized. Next, we assessed the cell measurement accuracy by evaluating the number of pixels that were correctly assigned to each target cell. Overall, the “learning process” defining artificial intelligence plays a key role in overcoming the issues that are usually manually solved in QWA analyses. Mask-RCNN is the model that better detects which are the features characterizing a target cell when these issues occur. In general, U-Net did not attain the other algorithms’ performance, while ROXAS performed best for conifers, and Mask-RCNN showed the highest accuracy in detecting target cells and segmenting lumen areas of angiosperms. Our research demonstrates that future software tools for QWA analyses would greatly benefit from using DCNNs, saving time during the analysis phase, and providing a flexible approach that allows model retraining.Giulia ResenteAlexander GillertMario TrouillierAlba Anadon-RosellAlba Anadon-RosellRichard L. PetersRichard L. PetersGeorg von ArxGeorg von ArxUwe von LukasUwe von LukasMartin WilmkingFrontiers Media S.A.articleartificial intelligencewood anatomydeep learninglumen areaF1 scoreROXASPlant cultureSB1-1110ENFrontiers in Plant Science, Vol 12 (2021)
institution DOAJ
collection DOAJ
language EN
topic artificial intelligence
wood anatomy
deep learning
lumen area
F1 score
ROXAS
Plant culture
SB1-1110
spellingShingle artificial intelligence
wood anatomy
deep learning
lumen area
F1 score
ROXAS
Plant culture
SB1-1110
Giulia Resente
Alexander Gillert
Mario Trouillier
Alba Anadon-Rosell
Alba Anadon-Rosell
Richard L. Peters
Richard L. Peters
Georg von Arx
Georg von Arx
Uwe von Lukas
Uwe von Lukas
Martin Wilmking
Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy
description The recent developments in artificial intelligence have the potential to facilitate new research methods in ecology. Especially Deep Convolutional Neural Networks (DCNNs) have been shown to outperform other approaches in automatic image analyses. Here we apply a DCNN to facilitate quantitative wood anatomical (QWA) analyses, where the main challenges reside in the detection of a high number of cells, in the intrinsic variability of wood anatomical features, and in the sample quality. To properly classify and interpret features within the images, DCNNs need to undergo a training stage. We performed the training with images from transversal wood anatomical sections, together with manually created optimal outputs of the target cell areas. The target species included an example for the most common wood anatomical structures: four conifer species; a diffuse-porous species, black alder (Alnus glutinosa L.); a diffuse to semi-diffuse-porous species, European beech (Fagus sylvatica L.); and a ring-porous species, sessile oak (Quercus petraea Liebl.). The DCNN was created in Python with Pytorch, and relies on a Mask-RCNN architecture. The developed algorithm detects and segments cells, and provides information on the measurement accuracy. To evaluate the performance of this tool we compared our Mask-RCNN outputs with U-Net, a model architecture employed in a similar study, and with ROXAS, a program based on traditional image analysis techniques. First, we evaluated how many target cells were correctly recognized. Next, we assessed the cell measurement accuracy by evaluating the number of pixels that were correctly assigned to each target cell. Overall, the “learning process” defining artificial intelligence plays a key role in overcoming the issues that are usually manually solved in QWA analyses. Mask-RCNN is the model that better detects which are the features characterizing a target cell when these issues occur. In general, U-Net did not attain the other algorithms’ performance, while ROXAS performed best for conifers, and Mask-RCNN showed the highest accuracy in detecting target cells and segmenting lumen areas of angiosperms. Our research demonstrates that future software tools for QWA analyses would greatly benefit from using DCNNs, saving time during the analysis phase, and providing a flexible approach that allows model retraining.
format article
author Giulia Resente
Alexander Gillert
Mario Trouillier
Alba Anadon-Rosell
Alba Anadon-Rosell
Richard L. Peters
Richard L. Peters
Georg von Arx
Georg von Arx
Uwe von Lukas
Uwe von Lukas
Martin Wilmking
author_facet Giulia Resente
Alexander Gillert
Mario Trouillier
Alba Anadon-Rosell
Alba Anadon-Rosell
Richard L. Peters
Richard L. Peters
Georg von Arx
Georg von Arx
Uwe von Lukas
Uwe von Lukas
Martin Wilmking
author_sort Giulia Resente
title Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy
title_short Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy
title_full Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy
title_fullStr Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy
title_full_unstemmed Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy
title_sort mask, train, repeat! artificial intelligence for quantitative wood anatomy
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/5dc098263318426dbb165835eb7a1342
work_keys_str_mv AT giuliaresente masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT alexandergillert masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT mariotrouillier masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT albaanadonrosell masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT albaanadonrosell masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT richardlpeters masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT richardlpeters masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT georgvonarx masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT georgvonarx masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT uwevonlukas masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT uwevonlukas masktrainrepeatartificialintelligenceforquantitativewoodanatomy
AT martinwilmking masktrainrepeatartificialintelligenceforquantitativewoodanatomy
_version_ 1718445022125228032