Wageningen Food Safety Research, Akkermaalsbos 2, 6721 WB Wageningen, The Netherlands.
Wageningen Plant Research, Wageningen University & Research, 6708 PB Wageningen, The Netherlands.
Toxins (Basel). 2024 Aug 13;16(8):354. doi: 10.3390/toxins16080354.
Fusarium head blight (FHB) is a plant disease caused by various species of the fungus. One of the major concerns associated with spp. is their ability to produce mycotoxins. Mycotoxin contamination in small grain cereals is a risk to human and animal health and leads to major economic losses. A reliable site-specific precise spp. infection early warning model is, therefore, needed to ensure food and feed safety by the early detection of contamination hotspots, enabling effective and efficient fungicide applications, and providing FHB prevention management advice. Such precision farming techniques contribute to environmentally friendly production and sustainable agriculture. This study developed a predictive model, Sága, for on-site FHB detection in wheat using imaging spectroscopy and deep learning. Data were collected from an experimental field in 2021 including (1) an experimental field inoculated with spp. (52.5 m × 3 m) and (2) a control field (52.5 m × 3 m) not inoculated with spp. and sprayed with fungicides. Imaging spectroscopy data (hyperspectral images) were collected from both the experimental and control fields with the ground truth of -infected ear and healthy ear, respectively. Deep learning approaches (pretrained YOLOv5 and DeepMAC on Global Wheat Head Detection (GWHD) dataset) were used to segment wheat ears and XGBoost was used to analyze the hyperspectral information related to the wheat ears and make predictions of -infected wheat ear and healthy wheat ear. The results showed that deep learning methods can automatically detect and segment the ears of wheat by applying pretrained models. The predictive model can accurately detect infected areas in a wheat field, achieving mean accuracy and F1 scores exceeding 89%. The proposed model, Sága, could facilitate the early detection of spp. to increase the fungicide use efficiency and limit mycotoxin contamination.
镰刀菌穗腐病（FHB）是一种由多种真菌引起的植物病害。与 spp. 相关的主要问题之一是它们产生真菌毒素的能力。小粒谷类作物中的真菌毒素污染对人类和动物健康构成威胁，并导致重大经济损失。因此，需要一种可靠的、针对特定地点的、精确的 spp. 感染早期预警模型，通过早期检测污染热点，确保食品安全和饲料安全，实现高效、有针对性的杀菌剂应用，并提供 FHB 预防管理建议。这种精准农业技术有助于实现环境友好型生产和可持续农业。本研究开发了一种预测模型 Sága，用于使用成像光谱学和深度学习对小麦进行现场 FHB 检测。数据是 2021 年从一个实验田收集的，包括（1）一个接种了 spp. 的实验田（52.5 m × 3 m）和（2）一个未接种 spp. 且用杀菌剂喷洒的对照田（52.5 m × 3 m）。从实验田和对照田分别采集成像光谱数据（高光谱图像），并记录受感染耳和健康耳的地面实况。使用深度学习方法（在 Global Wheat Head Detection (GWHD) 数据集上预训练的 YOLOv5 和 DeepMAC）来分割小麦穗，使用 XGBoost 分析与小麦穗相关的高光谱信息，并对感染的小麦穗和健康的小麦穗进行预测。结果表明，深度学习方法可以通过应用预训练模型自动检测和分割小麦穗。预测模型可以准确检测麦田中的感染区域，平均准确率和 F1 得分超过 89%。提出的 Sága 模型可以促进对 spp. 的早期检测，提高杀菌剂使用效率，限制真菌毒素污染。
