Related Experiment Video
Updated: Aug 5, 2026
An Easy and Flexible Inoculation Method for Accurately Assessing Powdery Mildew-Infection Phenotypes of Arabidopsis and Other Plants
Published on: March 9, 2021
Quantitative morphological phenotyping of infection structures in cucumber downy mildew and powdery mildew
1School of Computing and Data Science, Xiamen University Malaysia, Sepang, Selangor, Malaysia.
Introduction:
Cucumber diseases severely affect yield and quality. Deep learning-based analysis of microscopic pathogen images enables high-throughput identification and counting of pathogens, thereby facilitating early disease detection. However, most existing pathogen-recognition methods focus mainly on qualitative identification and cannot quantitatively characterize pathogen morphology, which limits their ability to reveal the developmental characteristics and functional differentiation of different infection structures from the perspective of pathogen morphology-function adaptability.
Methods:
To address this issue, this study focused on cucumber powdery mildew and downy mildew and achieved precise extraction and characterization of pathogen morphological features based on microscopic image instance segmentation. First, an in situ stained microscopic image dataset of cucumber pathogens was constructed. Second, an instance segmentation model, SWS-YOLO11n, was developed for cucumber pathogen infection structures to accurately identify and segment different infection structures in microscopic images. Finally, morphological analysis methods were used to quantitatively extract and characterize pathogen infection-structure features.
Results:
Experimental results showed that SWS-YOLO11n achieved a detection mAP@0.5 of 97.4% and a segmentation mAP@0.5 of 96.2%, with a model size of only 5.6 MB. The extraction accuracy of perimeter, area, and curvature reached R2 values greater than 0.90. In addition, category-wise morphological distribution analysis showed that different infection-structure types exhibited clear differentiation in size, contour complexity, and elongation.
Discussion:
This study provides an effective tool for high-throughput phenotyping of cucumber pathogen infection structures. The proposed method offers methodological support for disease diagnosis, pathogen morphological phenotyping, and precision disease management in horticultural production.
Insights
This study introduces SWS-YOLO11n, a deep learning model for precise cucumber pathogen identification and morphological analysis. It enables accurate characterization of infection structures, aiding in early disease detection and management.
Area of Science:
- Plant pathology
- Deep learning applications in agriculture
- Microscopic image analysis
Background:
- Cucumber diseases significantly impact crop yield and quality.
- Existing deep learning methods for pathogen recognition primarily offer qualitative identification, limiting quantitative morphological characterization.
- Understanding pathogen morphology-function adaptability is crucial for disease management.
Purpose of the Study:
- To develop a method for precise extraction and characterization of cucumber pathogen morphological features using instance segmentation.
- To enable quantitative analysis of pathogen infection structures for improved disease diagnosis.
- To support high-throughput phenotyping and precision disease management in cucumber cultivation.
Main Methods:
- Construction of an in situ stained microscopic image dataset of cucumber pathogens.
- Development of the SWS-YOLO11n instance segmentation model for accurate identification and segmentation of pathogen infection structures.
- Application of morphological analysis techniques for quantitative feature extraction.
Main Results:
- The SWS-YOLO11n model achieved high detection (97.4% mAP@0.5) and segmentation (96.2% mAP@0.5) accuracy with a small model size (5.6 MB).
- Extraction accuracy for perimeter, area, and curvature exceeded R² values of 0.90.
- Analysis revealed distinct morphological differentiation (size, contour complexity, elongation) among different infection-structure types.
Conclusions:
- The SWS-YOLO11n model provides an effective tool for high-throughput phenotyping of cucumber pathogen infection structures.
- This approach offers methodological support for accurate disease diagnosis and pathogen morphological phenotyping.
- The findings contribute to precision disease management strategies in horticultural production.
