Network feature-based phenotyping of leaf venation robustly reconstructs the latent space

Abstract

Despite substantial variation in leaf vein architectures among angiosperms, a typical hierarchical network pattern is shared within clades. Functional demands (e.g., hydraulic conductivity, transpiration efficiency, and tolerance to damage and blockage) constrain the network structure of leaf venation, generating a biased distribution in the morphospace. Although network structures and their diversity are crucial for understanding angiosperm venation, previous studies have relied on simple morphological measurements (e.g., length, diameter, branching angles, and areole area) and their derived statistics to quantify phenotypes. To better understand the morphological diversities and constraints on leaf vein networks, we developed a simple, high-throughput phenotyping workflow for the quantification of vein networks and identified leaf venation-specific morphospace patterns. The proposed method involves four processes: leaf image acquisition using a feasible system, leaf vein segmentation based on a deep neural network model, network extraction as an undirected graph, and network feature calculation. To demonstrate the proposed method, we applied it to images of non-chemically treated leaves of five species for classification based on network features alone, with an accuracy of 90.6%. By dimensionality reduction, a one-dimensional morphospace, along which venation shows variation in loopiness, was identified for both untreated and cleared leaf images. Because the one-dimensional distribution patterns align with the Pareto front that optimizes transport efficiency, construction cost, and robustness to damage, as predicted by the earlier theoretical study, our findings suggested that venation patterns are determined by a functional trade-off. The proposed network feature-based method is a useful morphological descriptor, providing a quantitative representation of the topological aspects of venation and enabling inverse mapping to leaf vein structures. Accordingly, our approach is promising for analyses of the functional and structural properties of veins.

Plant phenotyping relevance

葉画像の取得、深層学習による葉脈セグメンテーション、ネットワーク抽出、特徴量計算から成る高スループット表現型解析ワークフローを開発しており、植物形態の定量化が研究の中心である。

Code and data availability

The paper's Data Availability statement and Methods text explicitly deposit the untreated leaf image dataset on Zenodo (10.5281/zenodo.7070266) and the analysis code and trained U-Net model weights on Zenodo (10.5281/zenodo.8020856) and GitHub (MorphometricsGroup/iwamasa-2022). These are paper-specific, public, and可直接可