Search

• X-ray CT scans were taken from batches of sugar beet fruit. • Pericarp, true seed and air were manually annotated in the CT volumes. • A 3D U-Net model was trained to segment pericarp, true seed and air in CT data. • A CNN network was trained to detect bigerm fruit. • The methods can be used for nondestructive and high-throughput phenotyping of seeds. 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, 1.0 and 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. [ABSTRACT FROM AUTHOR]

• A dataset of X-ray radiographs of pear fruit was simulated from CT scans. • Deep anomaly detection models were trained on data of healthy pears and tested on data of healthy and defect pears. • Synthetic anomalies in training improved performance over the unsupervised case. • High AUC scores (up to 0.96) and classification accuracy (up to 95%) were obtained. • Defect pears with a cavity percentage > 1.0% could be detected 100% accurate. To preserve the quality of fresh fruit after harvest and to meet the year-round demand for high-quality fruit, pears are stored under a controlled atmosphere. However, due to preharvest events or suboptimal storage conditions, internal disorders might develop resulting in severe quality loss. Examples include internal browning and cavities, which are invisible externally. Here, X-ray radiography is investigated as a technique for internal quality inspection. The detection of defect fruit is approached as an anomaly detection (AD) problem, in which a model is constructed using nominal data and an anomaly score is used to identify defect fruit. In this work, multiple deep AD methods are shown to be effective to detect pears with internal cavity and browning disorders using X-ray radiographs (mean area under the receiver operating characteristic curve (AUC) up to 0.962). The best performing methods were found on par with a state-of-the-art multisensor disorder detection method (mean AUC up to 0.966). By investigating AD performance in function of internal disorder severity, it was shown that defect fruit with a cavity volume percentage > 1.0% could be detected 100% accurate using inline X-ray imaging. For lower cavity area percentages, the accuracy depended on the internal browning severity. Additionally, the explainability of the deep AD methods, i.e., how well human interpretable insight can be provided from each method's predictions, were qualitatively evaluated using anomaly heatmaps, which provided useful insight in the execution of the deep learning algorithms. [ABSTRACT FROM AUTHOR]

[Display omitted] • Deep learning was able to label defects in X-ray radiographs of pear fruit. • A large amount of ground truth data were obtained by simulations from X-ray CT data. • Synthetic training data improved segmentation of browning and cavity defects. A particular challenge for food quality inspection remains the quantification of internal defects. This work addresses the challenge of internal defects segmentation in pear fruit (cv. Conference) based on high-throughput inline X-ray radiography images in combination with deep learning. Unlike previous approaches, which focused on healthy vs defect classification, the current segmentation approach is able to determine the type of defect, its dimensions, and location. To this end, a novel simulation method was designed to obtain input-target image pairs of radiography data, and more diverse defect pears were generated using a conditioned generator model. The obtained data contributed to the design of a segmentation model that labeled every pixel in the X-ray radiographs of pear fruit as 'external air', 'healthy tissue', 'core', 'browning', or 'cavity'. We demonstrated that additional synthetic data in the learning process drastically improved the model performance. For instance, the mean IoU increased from 0.781 ± 0.112 to 0.883 ± 0.088 for consumable pears with minor cavities and browning. In terms of utility, our segmentation maps provide more detailed information about the type, size, and location of the disorders compared to the heatmaps produced by existing benchmark classifiers. [ABSTRACT FROM AUTHOR]