Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A lightweight graph-enhanced deep learning framework for explainable cucumber leaf disease diagnosis.

Raiyan Gani1, Maherun Nessa Isty1, Yusuf Salehin1

  • 1Department of Computer Science and Engineering, East West University, Aftabnagar, Dhaka, 1212, Bangladesh.

Scientific Reports
|June 18, 2026
PubMed
Summary

Related Concept Videos

Light Acquisition02:16

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Explainable detection of goldenhar syndrome using an OD-Mamba backbone for rare craniofacial disorder diagnosis.

Scientific reports·2026
Same author

Annotation-efficient weed detection using DINOv3-distilled YOLOv12.

Scientific reports·2026
Same author

Benchmarking hybrid CNN and transformer backbones with graph convolution networks (GCN) for flower growth-stage classification.

Scientific reports·2026
Same author

Deep ensemble of multi-head attention CNNs for histopathological image-based of lung and colon cancer diagnosis.

Digital health·2026
Same author

BDFlower: Growth stage flower image dataset for precision agriculture and floriculture.

Data in brief·2026
Same author

A comprehensive coin dataset highlighting the numismatic heritage of Bangladesh.

Data in brief·2025

MobileGraph, a new graph-aided deep learning model, accurately identifies cucumber leaf diseases by analyzing local textures and spatial dependencies. This efficient approach aids in timely agricultural interventions and crop health surveillance.

Area of Science:

  • Agricultural Science
  • Computer Science
  • Artificial Intelligence

Background:

  • Accurate cucumber leaf disease identification is crucial for preventing crop loss and enabling timely agricultural interventions.
  • Current deep learning models often struggle with spatial dependencies, computational efficiency, and prediction robustness in plant disease recognition.

Purpose of the Study:

  • To propose MobileGraph, a novel graph-aided deep learning model for efficient and accurate cucumber leaf disease identification.
  • To address limitations of existing models by integrating local texture analysis with spatial dependency reasoning.

Main Methods:

  • Developed MobileGraph, a graph-aided deep learning model utilizing MobileNetV3 as a lightweight feature extractor.
  • Jointly reasoned local texture patterns and spatial dependencies among CNN-derived cucumber leaf feature regions.
Keywords:
Cucumber leaf diseaseDeep learningExplainable AI (XAI)Graph convolutional networks (GCN)Lightweight modelMobile and edge computingPlant disease diagnosisPrecision agriculture

Related Experiment Videos

  • Evaluated performance on a 4,000-image, 5-class cucumber leaf disease dataset.

    • Main Results:

    • Achieved high performance metrics: 99.75% accuracy, 99.75% macro F1-score, and 99.69% MCC.
    • Outperformed state-of-the-art models (ResNet-152, EfficientNet-B7, DenseNet-201, ConvNeXt, VGG16) with significantly lower computational cost (0.465 GFLOPs).
    • Explainability methods (Grad-CAM, LIME) confirmed focus on biologically relevant lesion regions.

    Conclusions:

    • MobileGraph offers an efficient, accurate, and interpretable solution for intelligent crop health surveillance.
    • Demonstrated feasibility for real-time diagnosis via a prototype mobile application.
    • Highlights the potential of graph-aided deep learning in precision agriculture.