Microscopic image dataset of plant-parasitic nematode

Plant-parasitic nematodes (PPNs) are a significant threat to agriculture, causing substantial crop losses worldwide. Accurate identification of PPNs is crucial for effective management strategies; however, conventional methods are time-consuming and require extensive expertise. To address this challenge, we present a comprehensive microscopic image dataset of PPNs, focusing on common plant-parasitic genera. The dataset consists of 1,016 high-resolution images categorized into 11 classes, representing a diverse range of nematode morphologies, including Hemicycliophora, Radopholus, Helicotylenchus, Trichodorus, Xiphinema, Criconemoides, Criconema, Pratylenchus, Hirschmanniella, Hoplolaimus, and Meloidogyne. Nematodes were extracted from samples of various crops exhibiting infestation symptoms using a modified Whitehead-Tray method. The extracted nematodes were fixed, cleared, stained, and mounted for microscopic observation. Images were captured using optical cameras attached to a light microscope. This dataset provides a valuable resource for developing advanced AI-based tools to automate nematode identification and support precision agriculture efforts aimed at reducing crop losses caused by PPNs. Despite limitations such as imbalanced class distribution and geographic specificity, this dataset offers a foundation for further research and the development of efficient nematode identification methods.