Plot-average disease scores hide most of the signal a pathologist needs. Two genotypes can share the same canopy-level severity while differing sharply in how symptoms distribute across organs — information that visual 1-to-9 scales simply cannot capture at scale.
Ground-based high-throughput imaging with PhenoMobile brings the camera close enough to segment individual leaves and stems. AI models trained on annotated symptoms return diseased area, lesion count and necrotic fraction per organ, converting a subjective ordinal note into continuous, organ-resolved variables across the entire plot.
Breeders and pathologists gain a far finer ranking of partial resistance, earlier detection of symptom onset, and quantitative phenotypes that feed directly into genomic selection and QTL analysis.