Deep learning-based quantification of arbuscular mycorrhizal fungi in plant roots

© 2021 The Authors. New Phytologist © 2021 New Phytologist Foundation.

Bibliographische Detailangaben
Veröffentlicht in:The New phytologist. - 1979. - 232(2021), 5 vom: 01. Dez., Seite 2207-2219
1. Verfasser: Evangelisti, Edouard (VerfasserIn)
Weitere Verfasser: Turner, Carl, McDowell, Alice, Shenhav, Liron, Yunusov, Temur, Gavrin, Aleksandr, Servante, Emily K, Quan, Clément, Schornack, Sebastian
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:The New phytologist
Schlagworte:Journal Article Research Support, Non-U.S. Gov't Rhizophagus ClearSee ConvNet classification image analysis mycorrhiza root
LEADER 01000naa a22002652 4500
001 NLM329927213
003 DE-627
005 20231225210202.0
007 cr uuu---uuuuu
008 231225s2021 xx |||||o 00| ||eng c
024 7 |a 10.1111/nph.17697  |2 doi 
028 5 2 |a pubmed24n1099.xml 
035 |a (DE-627)NLM329927213 
035 |a (NLM)34449891 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Evangelisti, Edouard  |e verfasserin  |4 aut 
245 1 0 |a Deep learning-based quantification of arbuscular mycorrhizal fungi in plant roots 
264 1 |c 2021 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 06.01.2022 
500 |a Date Revised 06.01.2022 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a © 2021 The Authors. New Phytologist © 2021 New Phytologist Foundation. 
520 |a Soil fungi establish mutualistic interactions with the roots of most vascular land plants. Arbuscular mycorrhizal (AM) fungi are among the most extensively characterised mycobionts to date. Current approaches to quantifying the extent of root colonisation and the abundance of hyphal structures in mutant roots rely on staining and human scoring involving simple yet repetitive tasks which are prone to variation between experimenters. We developed Automatic Mycorrhiza Finder (AMFinder) which allows for automatic computer vision-based identification and quantification of AM fungal colonisation and intraradical hyphal structures on ink-stained root images using convolutional neural networks. AMFinder delivered high-confidence predictions on image datasets of roots of multiple plant hosts (Nicotiana benthamiana, Medicago truncatula, Lotus japonicus, Oryza sativa) and captured the altered colonisation in ram1-1, str, and smax1 mutants. A streamlined protocol for sample preparation and imaging allowed us to quantify mycobionts from the genera Rhizophagus, Claroideoglomus, Rhizoglomus and Funneliformis via flatbed scanning or digital microscopy, including dynamic increases in colonisation in whole root systems over time. AMFinder adapts to a wide array of experimental conditions. It enables accurate, reproducible analyses of plant root systems and will support better documentation of AM fungal colonisation analyses. AMFinder can be accessed at https://github.com/SchornacklabSLCU/amfinder 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
650 4 |a Rhizophagus 
650 4 |a ClearSee 
650 4 |a ConvNet 
650 4 |a classification 
650 4 |a image analysis 
650 4 |a mycorrhiza 
650 4 |a root 
700 1 |a Turner, Carl  |e verfasserin  |4 aut 
700 1 |a McDowell, Alice  |e verfasserin  |4 aut 
700 1 |a Shenhav, Liron  |e verfasserin  |4 aut 
700 1 |a Yunusov, Temur  |e verfasserin  |4 aut 
700 1 |a Gavrin, Aleksandr  |e verfasserin  |4 aut 
700 1 |a Servante, Emily K  |e verfasserin  |4 aut 
700 1 |a Quan, Clément  |e verfasserin  |4 aut 
700 1 |a Schornack, Sebastian  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t The New phytologist  |d 1979  |g 232(2021), 5 vom: 01. Dez., Seite 2207-2219  |w (DE-627)NLM09818248X  |x 1469-8137  |7 nnns 
773 1 8 |g volume:232  |g year:2021  |g number:5  |g day:01  |g month:12  |g pages:2207-2219 
856 4 0 |u http://dx.doi.org/10.1111/nph.17697  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 232  |j 2021  |e 5  |b 01  |c 12  |h 2207-2219