3D-CNN detection of systemic symptoms induced by different Potexvirus infections in four Nicotiana benthamiana genotypes using leaf hyperspectral imaging

Abstract

Purpose Hyperspectral imaging combined with machine learning offers a promising, cost-effective alternative to invasive chemical analysis for early plant disease detection. In this study, the use of 3D Convolutional Neural Networks (3D-CNNs) was explored to detect presymptomatic viral infections in the model plant Nicotiana benthamiana L. and assess the generalization of these models across different plant genotypes. Methods Four genotypes of Nicotiana benthamiana L. (wild-type, DCL2/4, AGO2, and NahG) were inoculated with different potexviruses (PepMV mild or severe strain, PVX, BaMV). Viral infection was verified via northern blot analysis at 5 and 10 days post inoculation (DPI). Hyperspectral images were captured over 10 days following inoculation, focusing on the top 3 leaves where symptoms typically appear. The dataset was carefully processed to remove errors, and raster masks were generated to isolate only the leaf pixels. The Extremely Randomized Trees algorithm was used for Effective Wavelength selection, and a novel 3D-CNN architecture was developed to classify 16 × 16 × 16 nonoverlapping cubes extracted from the unmasked leaf surfaces. The aim was to classify each cube into healthy or diseased for each of the four viruses at different time points. Results Accuracies of 0.78 - 0.87 were achieved for AGO2 mutants at the cube level, and overall plant-level accuracies of 0.68 - 0.89 . The model's generalization capabilities were tested across other genotypes, yielding accuracies of up to 0.75 for DCL2/4, 0.83 for NahG, and 0.78 for the wild-type. The timing of disease detection was also assessed, finding that accuracies approached 0.8 as early as 6 - 8 DPI depending on the virus. The results were validated against northern blot analyses and benchmarked against another state-of-the-art methodology for Nicotiana benthamiana viral infections, achieving superior overall classification accuracies. Conclusion The proposed patch-based method demonstrated key advantages: (a) exploiting both spectral and textural information, (b) deriving a large training dataset from few hyperspectral images, (c) providing localized classification explainability within leaf regions, and (d) achieving high accuracy for early detection of viral infections.

Plant phenotyping relevance

葉のハイパースペクトル画像からウイルス感染による植物病徴を抽出する3D-CNN手法を開発し、異なる遺伝子型で検証・ベンチマークしており、植物フェノタイピング手法が研究の中心である。

Code and data availability

The paper identifies an authors' GitHub repository containing the hyperspectral dataset and Python analysis code, but the supplied text states it would be made public only upon paper acceptance/publication, so public availability cannot be confirmed from the article blocks alone.

No evidence-backed public reproduction asset is currently recorded.