Scholarlink

Background <p>Accurate segmentation of foliar diseases under field conditions is essential for large-scale phenotyping, as breeding programs rely on reliable severity estimates to identify genotypes with improved resistance. However, most deep learning approaches have been developed as pathogen-specific models, which limits scalability in field-grown barley where multiple diseases naturally co-occur and exhibit substantial visual similarity.</p> Results <p>We evaluated whether a multiclass segmentation model can simultaneously detect and distinguish two fungal diseases of barley, <i>Puccinia hordei</i> and <i>Ramularia collo-cygni</i>, and compared its performance with two disease-specific binary models. Using 336 high-resolution leaf scans collected in the field with naturally occurring co-infections, the multiclass model achieved higher Dice scores for brown rust (0.59 vs 0.40; +47.5% relative improvement) and ramularia (0.60 vs 0.53; +13.2% relative improvement). It also captured a greater proportion of individual lesions across both classes. At the genotype level, the model-predicted disease area percentages were highly consistent with those from ground truth annotations (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(r &gt; 0.99\)</EquationSource> </InlineEquation>).</p> Conclusions <p>A unified multiclass framework can more effectively segment visually similar foliar diseases than separate binary models, while simplifying the computational workflow. This provides a scalable basis for automated resistance assessment within breeding pipelines. Code and data are publicly available at <a href="https://github.com/grimmlab/BarleyDiseaseSegmentation,">https://github.com/grimmlab/BarleyDiseaseSegmentation,</a> with Mendeley Data dataset DOI 10.17632/4ny92p2r8f.1.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning–based identification of visually similar foliar diseases in field-grown barley

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月18日

查看全文
  • Sofia Martello,
  • Nikita Genze,
  • Dominik G. Grimm

摘要

Background

Accurate segmentation of foliar diseases under field conditions is essential for large-scale phenotyping, as breeding programs rely on reliable severity estimates to identify genotypes with improved resistance. However, most deep learning approaches have been developed as pathogen-specific models, which limits scalability in field-grown barley where multiple diseases naturally co-occur and exhibit substantial visual similarity.

Results

We evaluated whether a multiclass segmentation model can simultaneously detect and distinguish two fungal diseases of barley, Puccinia hordei and Ramularia collo-cygni, and compared its performance with two disease-specific binary models. Using 336 high-resolution leaf scans collected in the field with naturally occurring co-infections, the multiclass model achieved higher Dice scores for brown rust (0.59 vs 0.40; +47.5% relative improvement) and ramularia (0.60 vs 0.53; +13.2% relative improvement). It also captured a greater proportion of individual lesions across both classes. At the genotype level, the model-predicted disease area percentages were highly consistent with those from ground truth annotations ( \(r > 0.99\) ).

Conclusions

A unified multiclass framework can more effectively segment visually similar foliar diseases than separate binary models, while simplifying the computational workflow. This provides a scalable basis for automated resistance assessment within breeding pipelines. Code and data are publicly available at https://github.com/grimmlab/BarleyDiseaseSegmentation, with Mendeley Data dataset DOI 10.17632/4ny92p2r8f.1.