Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks
Abstract Background Late and early leaf spot in peanuts is a foliar disease contributing to a significant amount of lost yield globally. Peanut breeding programs frequently focus on developing disease-resistant peanut genotypes. However, existing phenotyping protocols employ subjective rating scales...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Plant Methods |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13007-024-01316-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849723980514066432 |
|---|---|
| author | Joshua Larsen Jeffrey Dunne Robert Austin Cassondra Newman Michael Kudenov |
| author_facet | Joshua Larsen Jeffrey Dunne Robert Austin Cassondra Newman Michael Kudenov |
| author_sort | Joshua Larsen |
| collection | DOAJ |
| description | Abstract Background Late and early leaf spot in peanuts is a foliar disease contributing to a significant amount of lost yield globally. Peanut breeding programs frequently focus on developing disease-resistant peanut genotypes. However, existing phenotyping protocols employ subjective rating scales, performed by human raters, who determine the severity of leaf spot infection. The objective of this study was to develop an objective end-to-end pipeline that can serve to replace an expert human scorer in the field. This was accomplished using image capture protocols and segmentation neural networks that extracted lesion areas from plot-level images to determine an appropriate rating for infection severity. Results The pipeline incorporated a neural network that accurately determined the infected leaf surface area and identified dead leaves from plot-level cellphone imagery. Image processing algorithms then convert these labels into quality metrics that can efficiently score these images based on infected versus non-infected area. The pipeline was evaluated using field data from plots with varying leaf spot severity, creating a dataset of thousands of images that spanned conventional visual severity scores ranging from 1–9. These predictions were based on the amount of infected leaf area and the presence of defoliated leaves in the surrounding area. We were able to demonstrate automated scoring, as compared to expert visual scoring, with a root mean square error of 0.996 visual scores, on individual images (one image per plot), and 0.800 visual scores when three images were captured of each plot. Conclusion Results indicated that the model and image processing pipeline can serve as an alternative to human scoring. Eliminating human subjectivity for the scoring protocols will allow non-experts to collect scores and may enable drone-based data collection. This could reduce the time needed to obtain new lines or identify new genes responsible for leaf spot resistance in peanut. |
| format | Article |
| id | doaj-art-e48b1eba5752403b9dca054084c940f7 |
| institution | DOAJ |
| issn | 1746-4811 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Plant Methods |
| spelling | doaj-art-e48b1eba5752403b9dca054084c940f72025-08-20T03:10:52ZengBMCPlant Methods1746-48112025-02-0121111510.1186/s13007-024-01316-xAutomated pipeline for leaf spot severity scoring in peanuts using segmentation neural networksJoshua Larsen0Jeffrey Dunne1Robert Austin2Cassondra Newman3Michael Kudenov4Department of Electrical and Computer Engineering, NC State UniversityDepartment of Crop and Soil Science, NC State UniversityDepartment of Crop and Soil Science, NC State UniversityDepartment of Crop and Soil Science, NC State UniversityDepartment of Electrical and Computer Engineering, NC State UniversityAbstract Background Late and early leaf spot in peanuts is a foliar disease contributing to a significant amount of lost yield globally. Peanut breeding programs frequently focus on developing disease-resistant peanut genotypes. However, existing phenotyping protocols employ subjective rating scales, performed by human raters, who determine the severity of leaf spot infection. The objective of this study was to develop an objective end-to-end pipeline that can serve to replace an expert human scorer in the field. This was accomplished using image capture protocols and segmentation neural networks that extracted lesion areas from plot-level images to determine an appropriate rating for infection severity. Results The pipeline incorporated a neural network that accurately determined the infected leaf surface area and identified dead leaves from plot-level cellphone imagery. Image processing algorithms then convert these labels into quality metrics that can efficiently score these images based on infected versus non-infected area. The pipeline was evaluated using field data from plots with varying leaf spot severity, creating a dataset of thousands of images that spanned conventional visual severity scores ranging from 1–9. These predictions were based on the amount of infected leaf area and the presence of defoliated leaves in the surrounding area. We were able to demonstrate automated scoring, as compared to expert visual scoring, with a root mean square error of 0.996 visual scores, on individual images (one image per plot), and 0.800 visual scores when three images were captured of each plot. Conclusion Results indicated that the model and image processing pipeline can serve as an alternative to human scoring. Eliminating human subjectivity for the scoring protocols will allow non-experts to collect scores and may enable drone-based data collection. This could reduce the time needed to obtain new lines or identify new genes responsible for leaf spot resistance in peanut.https://doi.org/10.1186/s13007-024-01316-xAutomationPhenotypingPeanutLeaf spotImagingComputer vision |
| spellingShingle | Joshua Larsen Jeffrey Dunne Robert Austin Cassondra Newman Michael Kudenov Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks Plant Methods Automation Phenotyping Peanut Leaf spot Imaging Computer vision |
| title | Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks |
| title_full | Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks |
| title_fullStr | Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks |
| title_full_unstemmed | Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks |
| title_short | Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks |
| title_sort | automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks |
| topic | Automation Phenotyping Peanut Leaf spot Imaging Computer vision |
| url | https://doi.org/10.1186/s13007-024-01316-x |
| work_keys_str_mv | AT joshualarsen automatedpipelineforleafspotseverityscoringinpeanutsusingsegmentationneuralnetworks AT jeffreydunne automatedpipelineforleafspotseverityscoringinpeanutsusingsegmentationneuralnetworks AT robertaustin automatedpipelineforleafspotseverityscoringinpeanutsusingsegmentationneuralnetworks AT cassondranewman automatedpipelineforleafspotseverityscoringinpeanutsusingsegmentationneuralnetworks AT michaelkudenov automatedpipelineforleafspotseverityscoringinpeanutsusingsegmentationneuralnetworks |