<p dir="ltr">The dataset contains micrographs of <i>Hoplolaimus</i>, <i>Helicotylenchus</i>, <i>Meloidogyne</i>, <i>Mesocriconema,</i> <i>Pratylenchus</i>, <i>Trichodorus</i>, and <i>Tylenchorhynchus </i>nematodes. The data were collected using 10×, 20× objectives with a Zeiss Observer Z1 fitted with a Zeiss Axiocam 503 color camera and with 10× and 40× objectives using an Olympus BX51 fitted with a DP74 Olympus camera. Data collected with the Zeiss microscope setup were processed with Zen blue version 2.6 and data collected with the Olympus microscope were processed with CellSens version 4.1. Individual images in the dataset were extracted from videos recorded with Zen blue and CellSens software.</p><p dir="ltr">Micrographs are grouped by three objectives (10×, 20×, 40×) for seven nematode genera (<i>Hoplolaimus, Helicotylenchus, Meloidogyne, Mesocriconema, Pratylenchus, Trichodorus, Tylenchorhynchus</i>). </p><p dir="ltr">Number of images:</p><p dir="ltr"><i>Helicotylenchus</i></p><p>827</p><p dir="ltr"><br></p><p dir="ltr"><i>Hoplolaimus</i></p><p>995</p><p dir="ltr"><br></p><p dir="ltr"><i>Mesocriconema</i></p><p>527</p><p dir="ltr"><br></p><p dir="ltr"><i>Meloidogyne</i></p><p>433</p><p dir="ltr"><br></p><p dir="ltr"><i>Pratylenchus</i></p><p>666</p><p dir="ltr"><br></p><p dir="ltr"><i>Trichodorus</i></p><p>507</p><p dir="ltr"><br></p><p dir="ltr"><i>Tylenchorhynchus</i></p><p>1425</p><p dir="ltr"><br></p>
The image dataset is intended to serve as a resource for training or validating machine learning algorithms for identification of plant-parasitic nematodes.
Use limitations
1. Lighting conditions vary in the dataset.
2. Background debris may be present in some images.
3. Nematodes only identified to genus level.
4. Single individual contained in each image.
Temporal Extent Start Date
2022-06-16
Temporal Extent End Date
2024-07-30
Frequency
notPlanned
Theme
Non-geospatial
Geographic location - description
Nematode specimens extracted from samples collected in Maryland from golf courses and the USDA Beltsville Agricultural Research Center.
Vikram Rangarajan, Fereshteh Shahoveisi, Benjamin D. Waldo, and Sadegh Jafari.
Identification of plant-parasitic nematode genera in turfgrass using deep learning algorithms.
Scientific Reports (in press)