A multi‐task deep learning–based approach to identify and assess dry root rot disease in chickpea
- 1BRIC–National Institute of Plant Genome Research, Aruna Asaf Ali Marg 110067 New Delhi India
- 2Department of Soil and Crop Sciences Texas A&M University College Station Texas USA
Abstract
Premise: Dry root rot (DRR), an emerging global disease exacerbated by drought, affects a wide range of crops. The disease symptoms are manually scored for large‐scale germplasm screening to identify disease‐resistant varieties and test transgenic lines and other varieties. Despite its use in the past, manual disease identification is not only cumbersome but also often incapable of distinguishing between similar stress phenotypes. Manual disease scoring is tedious, time‐consuming, and often error‐prone, especially when screening large numbers of plants. To overcome this limitation, we developed a machine learning model that employs a learning‐based approach using convolutional neural networks for automated feature extraction and image‐based identification and severity assessment of DRR.
Methods: Our models were trained, tested, and validated using an in‐house dataset of 10,800 unique RGB images. A total of 51 deep learning models, including single‐task and multi‐task models, were developed using the Xception and Vision Transformer (ViT) architectures with standard image augmentations, and then validated on stratified independent test sets to demonstrate robustness across camera, scanner, and microscope modalities.
Results: The best multi‐task ViT model, capable of scoring across combined datasets, achieved 94% accuracy in distinguishing DRR from the control and had a root mean square error of 1 in predicting DRR severity score.
Discussion: This model's metrics, including confusion matrix performance, underscore its potential as an efficient and accessible tool for large‐scale germplasm screening for DRR, overcoming the challenges of manual scoring.
Related
- Integrated multi-omics and machine learning identify core mechanobiology-associated immune genes in pulmonary arterial hypertension
- Enhanced disease resistance in chickpea and canola via MAGPIE: Major‐Effect Allele and Genomic Polygenic Integration for Enhancement
- Multi‐omics integration and machine learning identify an ACKR1+ endothelial cell‐based lactate‐immune signature associated with carotid plaque vulnerability and progression
- Multi-tissue proteome atlas reveals constitutive and reactive cold responses in wild and domesticated chickpea
- MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models
BibTeX
@article{priya2026multitask,
title = {{A multi‐task deep learning–based approach to identify and assess dry root rot disease in chickpea}},
author = {Piyush Priya and Joe Johnson and Athimoolam Durgadevi and Navaneeth Vinayachandran and Meghna Pillai and Bharat Maitraya and Muthukumar V. Bagavathiannan and Muthappa Senthil‐Kumar},
journal = {Applications in plant sciences},
year = {2026},
month = oct,
doi = {10.1002/aps3.70075},
url = {https://europepmc.org/article/PMC/PMC13722823},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - A multi‐task deep learning–based approach to identify and assess dry root rot disease in chickpea
AU - Piyush Priya
AU - Joe Johnson
AU - Athimoolam Durgadevi
AU - Navaneeth Vinayachandran
AU - Meghna Pillai
AU - Bharat Maitraya
AU - Muthukumar V. Bagavathiannan
AU - Muthappa Senthil‐Kumar
PY - 2026
DA - 2026/10/30
JO - Applications in plant sciences
DO - 10.1002/aps3.70075
UR - https://europepmc.org/article/PMC/PMC13722823
AB - Premise: Dry root rot (DRR), an emerging global disease exacerbated by drought, affects a wide range of crops. The disease symptoms are manually scored for large‐scale germplasm screening to identify disease‐resistant varieties and test transgenic lines and other varieties. Despite its use in the past, manual disease identification is not only cumbersome but also often incapable of distinguishing between similar stress phenotypes. Manual disease scoring is tedious, time‐consuming, and often error‐prone, especially when screening large numbers of plants. To overcome this limitation, we developed a machine learning model that employs a learning‐based approach using convolutional neural networks for automated feature extraction and image‐based identification and severity assessment of DRR. Methods: Our models were trained, tested, and validated using an in‐house dataset of 10,800 unique RGB images. A total of 51 deep learning models, including single‐task and multi‐task models, were developed using the Xception and Vision Transformer (ViT) architectures with standard image augmentations, and then validated on stratified independent test sets to demonstrate robustness across camera, scanner, and microscope modalities. Results: The best multi‐task ViT model, capable of scoring across combined datasets, achieved 94% accuracy in distinguishing DRR from the control and had a root mean square error of 1 in predicting DRR severity score. Discussion: This model's metrics, including confusion matrix performance, underscore its potential as an efficient and accessible tool for large‐scale germplasm screening for DRR, overcoming the challenges of manual scoring.
SN - 2168-0450
ER -