Nondestructive high-throughput sugar beet fruit analysis using X-ray CT and deep learning

Abstract

Sugar beet (Beta vulgaris L. ssp. vulgaris) accounts for roughly 20% of the global sugar production, with the remainder derived from sugar cane (Saccharum officinarum L.). To maximize sugar yield, high performing sugar beet varieties are needed, in combination with good agronomical practices. Delivering vigorous seeds to the market and meeting the highest quality standards is, therefore, essential. Seed vigor is highly determined by fruit morphology, with the main characteristics of interest being fruit and true seed size, pericarp morphology and fruit filling. Current methods for evaluating fruit morphology mostly rely on labor-intensive and destructive analyses. Here we present a high-throughput nondestructive method to quantitatively phenotype sugar beet fruit and true seeds using X-ray micro-CT imaging and deep learning. A 3D convolutional neural network was trained for the semantic segmentation of the pericarp, true seed and air in X-ray micro-CT scans. High average Dice scores of 0.996, 0.971 and 0.930 were found for the pericarp, true seed and air, respectively. Additionally, since farmers target single plants after emergence in the field, we present a method to identify whether sugar beet fruit are monogerm or contain more than one seed (bigerm). An excellent overall classification accuracy, false positive and false negative rate of respectively 98.6, 1.0and 1.8% were achieved. The presented methods have a high potential for integration into tools for breeding programs and the sample-wise monitoring and adjustment of production processes.