Leaf Venation Networks of Bornean Trees: Images and Hand‐Traced Segmentations

Both²,

et al. 2020

New Phytologist

Self Cite

Leaf venation networks evolved along several functional axes, including resource transport, damage resistance, mechanical strength, and construction cost. Because functions may depend on architectural features at different scales, network architecture may vary across spatial scales to satisfy functional tradeoffs. We develop a framework for quantifying network architecture with multiscale statistics describing elongation ratios, circularity ratios, vein density, and minimum spanning tree ratios. We quantify vein networks for leaves of 260 southeast Asian tree species in samples of up to 2 cm 2 , pairing multiscale statistics with traits representing axes of resource transport, damage resistance, mechanical strength, and cost. We show that these multiscale statistics clearly differentiate species' architecture and delineate a phenotype space that shifts at larger scales; functional linkages vary with scale and are weak, with vein density, minimum spanning tree ratio, and circularity ratio linked to mechanical strength (measured by force to punch) and elongation ratio and circularity ratio linked to damage resistance (measured by tannins); and phylogenetic conservatism of network architecture is low but scale-dependent. This work provides tools to quantify the function and evolution of venation networks. Future studies including primary and secondary veins may uncover additional insights.

“…This study integrates venation network imagery (Blonder et al ., 2019) with functional trait data that were collected from the study sites (Table 3) (Both et al ., 2018).…”

Section: Methodsmentioning

confidence: 99%

Linking functional traits to multiscale statistics of leaf venation networks

Both²,

et al. 2020

New Phytologist

Self Cite

“…In total, 727 samples were obtained from 295 species (50 families). The sampling protocols and nonvein datasets have been described previously (Both et al, 2019) and the complete set of vein images published (Blonder et al, 2019).…”

Section: Leaf Vein Imagingmentioning

confidence: 99%

Automated and accurate segmentation of leaf venation networks via deep learning

et al. 2020

New Phytologist

Self Cite

Leaf vein network geometry can predict levels of resource transport, defence and mechanical support that operate at different spatial scales. However, it is challenging to quantify network architecture across scales due to the difficulties both in segmenting networks from images and in extracting multiscale statistics from subsequent network graph representations. Here we developed deep learning algorithms using convolutional neural networks (CNNs) to automatically segment leaf vein networks. Thirty-eight CNNs were trained on subsets of manually defined ground-truth regions from >700 leaves representing 50 southeast Asian plant families. Ensembles of six independently trained CNNs were used to segment networks from larger leaf regions (c. 100 mm 2). Segmented networks were analysed using hierarchical loop decomposition to extract a range of statistics describing scale transitions in vein and areole geometry. The CNN approach gave a precision-recall harmonic mean of 94.5% AE 6%, outperforming other current network extraction methods, and accurately described the widths, angles and connectivity of veins. Multiscale statistics then enabled the identification of previously undescribed variation in network architecture across species. We provide a LEAFVEINCNN software package to enable multiscale quantification of leaf vein networks, facilitating the comparison across species and the exploration of the functional significance of different leaf vein architectures.

“…A total of 727 samples were obtained from 295 species (50 families). The sampling protocols and non-vein datasets have been described previously (Both et al, 2018), and the complete set of vein images published (Blonder et al, 2019).…”

Section: Leaf Vein Imagingmentioning

confidence: 99%

“…S2) are available from (URL provided on acceptance). The dataset, including GTs, is publicly available (Blonder et al, 2019). The CNN predictions and networks for the image dataset are available from the Oxford Research Archive (ORA) (URL provided on acceptance).…”

Section: Data and Algorithm Availabilitymentioning

confidence: 99%

Automated and accurate segmentation of leaf venation networks via deep learning

et al. 2020

Preprint

Leaf vein network geometry can predict levels of resource transport, defence, and mechanical support that operate at different spatial scales. However, it is challenging to quantify network architecture across scales, due to the difficulties both in segmenting networks from images, and in extracting multi-scale statistics from subsequent network graph representations. Here we develop deep learning algorithms using convolutional neural networks (CNNs) to automatically segment leaf vein networks. Thirty-eight CNNs were trained on subsets of manually-defined ground-truth regions from >700 leaves representing 50 southeast Asian plant families. Ensembles of 6 independently trained CNNs were used to segment networks from larger leaf regions (~100 mm2). Segmented networks were analysed using hierarchical loop decomposition to extract a range of statistics describing scale transitions in vein and areole geometry. The CNN approach gave a precision-recall harmonic mean of 94.5% ± 6%, outperforming other current network extraction methods, and accurately described the widths, angles, and connectivity of veins. Multi-scale statistics then enabled identification of previously-undescribed variation in network architecture across species. We provide a LeafVeinCNN software package to enable multi-scale quantification of leaf vein networks, facilitating comparison across species and exploration of the functional significance of different leaf vein architectures.