An open-source machine-learning approach for obtaining high-quality quantitative wood anatomy data from E. grandis and P. radiata xylem

Rafael Keret; Paul M Schliephack; Dominik F Stangler; Thomas Seifert; Hans-Peter Kahle; David M Drew; Paul N Hills

doi:10.1016/j.plantsci.2023.111970

An open-source machine-learning approach for obtaining high-quality quantitative wood anatomy data from E. grandis and P. radiata xylem

Plant Sci. 2024 Mar:340:111970. doi: 10.1016/j.plantsci.2023.111970. Epub 2023 Dec 30.

Authors

Rafael Keret¹, Paul M Schliephack², Dominik F Stangler², Thomas Seifert³, Hans-Peter Kahle², David M Drew⁴, Paul N Hills⁵

Affiliations

¹ Institute for Plant Biotechnology, Department of Genetics, Stellenbosch University, Private Bag X1, Matieland 7602, Stellenbosch, South Africa; Department of Forestry and Wood Sciences, Stellenbosch University, Bosman St, 7599, Stellenbosch central, South Africa.
² Chair of Forest Growth and Dendroecology, Institute of Forest Sciences, University of Freiburg, Tennenbacher Str. 4, Freiburg im Breisgau, Germany.
³ Department of Forestry and Wood Sciences, Stellenbosch University, Bosman St, 7599, Stellenbosch central, South Africa; Chair of Forest Growth and Dendroecology, Institute of Forest Sciences, University of Freiburg, Tennenbacher Str. 4, Freiburg im Breisgau, Germany.
⁴ Department of Forestry and Wood Sciences, Stellenbosch University, Bosman St, 7599, Stellenbosch central, South Africa. Electronic address: drew@sun.ac.za.
⁵ Institute for Plant Biotechnology, Department of Genetics, Stellenbosch University, Private Bag X1, Matieland 7602, Stellenbosch, South Africa.

PMID: 38163623
DOI: 10.1016/j.plantsci.2023.111970

Abstract

Quantitative wood anatomy is a subfield in dendrochronology that requires effective open-source image analysis tools. In this research, the bioimage analysis software QuPath (v0.4.4) is introduced as a candidate for accurately quantifying the cellular properties of the xylem in an automated manner. Additionally, the potential of QuPath to detect the transition of early- to latewood tracheids over the growing season was evaluated to assess a potential application in dendroecological studies. Various algorithms in QuPath were optimized to quantify different xylem cell types in Eucalyptus grandis and the transition of early- to latewood tracheids in Pinus radiata. These algorithms were coded into cell detection scripts for automatic quantification of stem microsections and compared to a manually curated method to assess the accuracy of the cell detections. The automatic cell detection approach, using QuPath, has been validated to be reproducible with an acceptable error when assessing fibers, vessels, early- and latewood tracheids. However, further optimization for parenchyma is still required. This proposed method developed in QuPath provides a scalable and accurate approach for quantifying anatomical features in stem microsections. With minor amendments to the detection and classification algorithms, this strategy is likely to be viable in other plant species.

Keywords: Cell-detection; Hardwood; Histology; Machine learning; Softwood; Xylogenesis.

MeSH terms

Eucalyptus*
Pinus*
Seasons
Wood / anatomy & histology
Xylem