Genetic Diversity in Stomatal Density among Soybeans Elucidated Using High-throughput Technique Based on an Algorithm for Object Detection.

Abstract

The stomatal density (SD) can be a promising target to improve the leaf photosynthesis in soybeans (Glycine max (L.) Merr). In a conventional SD evaluation, the counting process of the stomata during a manual operation can be time-consuming. We aimed to develop a high-throughput technique for evaluating the SD and elucidating the variation in the SD among various soybean accessions. The central leaflet of the first trifoliolate was sampled, and microscopic images of the leaflet replica were obtained among 90 soybean accessions. The Single Shot MultiBox Detector, an algorithm for an object detection based on deep learning, was introduced to develop an automatic detector of the stomata in the image. The developed detector successfully recognized the stomata in the microscopic image with high-throughput. Using this technique, the value of R 2 reached 0.90 when the manually and automatically measured SDs were compared in the 150 images. This technique discovered a variation in SD from 93 ± 3 to 166 ± 4 mm -2 among the 90 accessions. Our detector can be a powerful tool for a SD evaluation with a large-scale population in crop species, accelerating the identification of useful alleles related to the SD in future breeding programs.

Plant phenotyping relevance

気孔密度という植物形質を画像から自動抽出する高スループット手法を開発し、手動測定との比較で技術検証しているため、方法論が中心です。

Code and data availability

The paper's phenotype image datasets, trained SSD stoma-detector models, and modified analysis code are not publicly deposited; the authors state they are available only upon reasonable request. The only public URL mentioned (github.com/rykov8/ssd_keras) is the unmodified third-party SSD library the authors adapted, so

No evidence-backed public reproduction asset is currently recorded.