Abstract
Abstract Canola blackleg is a fungal disease that causes significant yield loss and plant death of infected canola ( Brassica napus L., Brassica rapa L ., Brassica juncea L .) fields worldwide. One of the most effective methods for controlling blackleg is through the cultivation of resistant varieties. Consequently, quantitative scoring of blackleg disease severity of infected plants is a key metric for identifying and selecting resistant varieties. Traditionally, blackleg severity is scored by expert raters who evaluate disease in stem cross sections using established rating scales and reference images; however, human raters are expensive and inconsistent in their scoring. Here, we introduce a machine learning algorithm based on deep learning models that can score blackleg severity from cross‐section images of infected plants. We find that expert ratings are inconsistent across raters and across years for the same rater, creating substantial noise in resistance ratings. Meanwhile, our trained machine learning model performs more consistently than the median rater while maintaining a similar heritability as expert raters for the blackleg resistance trait. This model can be used to standardize blackleg resistance scoring across locations and years to improve canola breeding outcomes across affected regions.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 4
Claim · model-written summary
Expert blackleg severity ratings were inconsistent across raters and across years for the same rater.
- Taxon
- canola
.jpg?width=60)
Brassica napus var. napuse1 - Outcome
- expert ratingse2
- Qualifier
- across raters and across years for the same ratere2
Not reportedDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
.jpg?width=500)
Verbatim
e1“infected canola ( Brassica napus L., Brassica rapa L ., Brassica juncea L .)”
e2“expert ratings are inconsistent across raters and across years for the same rater”
Claim · model-written summary
The machine learning model scored blackleg severity more consistently than the median rater.
- Taxon
- canolaBrassica napus var. napuse1
- Outcome
- performs more consistentlye2
- Direction
- more consistentlye2
- Comparator
- median ratere2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“infected canola ( Brassica napus L., Brassica rapa L ., Brassica juncea L .)”
e2“our trained machine learning model performs more consistently than the median rater”
Claim · model-written summary
The machine learning model maintained a heritability for blackleg resistance similar to that of expert raters.
- Taxon
- canolaBrassica napus var. napuse1
- Outcome
- heritabilitye2
- Direction
- similare2
- Qualifier
- blackleg resistance traite2
- Comparator
- expert raterse2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“infected canola ( Brassica napus L., Brassica rapa L ., Brassica juncea L .)”
e2“while maintaining a similar heritability as expert raters for the blackleg resistance trait”
Claim · model-written summary
The model should be used to standardize blackleg resistance scoring across locations and years to improve canola breeding.
- Taxon
- canolaBrassica napus var. napuse1
- Outcome
- blackleg resistance scoringe2
- Qualifier
- across locations and yearse2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“infected canola ( Brassica napus L., Brassica rapa L ., Brassica juncea L .)”
e2“This model can be used to standardize blackleg resistance scoring across locations and years to improve canola breeding outcomes across affected regions”