MRI-Seed-Wizard: combining deep learning algorithms with magnetic resonance imaging enables advanced seed phenotyping

Abstract

Evaluation of relevant seed traits is an essential part of most plant breeding and biotechnology programmes. There is a need for non-destructive, three-dimensional assessment of the morphometry, composition, and internal features of seeds. Here, we introduce a novel tool, MRI-Seed-Wizard, which integrates deep learning algorithms with non-invasive magnetic resonance imaging (MRI) for use in a new domain-plant MRI. The tool enabled in vivo quantification of 23 grain traits, including volumetric parameters of inner seed structure. Several of these features cannot be assessed using conventional techniques, including X-ray computed tomography. MRI-Seed-Wizard was designed to automate the manual processes of identifying, labeling, and analysing digital MRI data. We further provide advanced MRI protocols that allow the evaluation of multiple seeds simultaneously to increase throughput. The versatility of MRI-Seed-Wizard in seed phenotyping is demonstrated for wheat (Triticum aestivum) and barley (Hordeum vulgare) grains, and it is applicable to a wide range of crop seeds. Thus, artificial intelligence, combined with the most versatile imaging modality, MRI, opens up new perspectives in seed phenotyping and crop improvement.

Plant phenotyping relevance

MRIと深層学習を統合した種子表現型解析ツールを開発し、多数の種子形質を自動・非破壊・高スループットに定量化する中心的な方法論研究である。

Code and data availability

The paper's MRI-Seed-Wizard segmentation/phenotyping pipeline (Python/PyTorch scripts, nnU-Net/U-Net models) and demonstration data are explicitly published online by the authors at the GitHub repository akvilonBrown/mri-wizard, matching an allowed URL.