Search

Wheat stripe rust-damaged leaves present challenges to automatic disease index calculation, including high similarity between spores and spots, and difficulty in distinguishing edge contours. In actual field applications, investigators rely on the naked eye to judge the disease extent, which is subjective, of low accuracy, and essentially qualitative. To address the above issues, this study undertook a task of semantic segmentation of wheat stripe rust damage images using deep learning. To address the problem of small available datasets, the first large-scale open dataset of wheat stripe rust images from Qinghai province was constructed through field and greenhouse image acquisition, screening, filtering, and manual annotation. There were 33,238 images in our dataset with a size of 512 × 512 pixels. A new segmentation paradigm was defined. Dividing indistinguishable spores and spots into different classes, the task of accurate segmentation of the background, leaf (containing spots), and spores was investigated. To assign different weights to high- and low-frequency features, we used the Octave-UNet model that replaces the original convolutional operation with the octave convolution in the U-Net model. The Octave-UNet model obtained the best benchmark results among four models (PSPNet, DeepLabv3, U-Net, Octave-UNet), the mean intersection over a union of the Octave-UNet model was 83.44%, the mean pixel accuracy was 94.58%, and the accuracy was 96.06%, respectively. The results showed that the state-of-art Octave-UNet model can better represent and discern the semantic information over a small region and improve the segmentation accuracy of spores, leaves, and backgrounds in our constructed dataset. [ABSTRACT FROM AUTHOR]

Wheat stripe rust, caused by Puccinia striiformis f. sp. tritici (Pst), is one of the most devastating diseases in wheat. Due to the large-scale and widely-distributed planting pattern of wheat, the directional selection pressure of the pathogen is very strong. Therefore, it is urgent to pyramid more stripe rust resistance genes in wheat cultivars to enhance resistance durability and ensure wheat production safety. In this study, two quantitative trait loci (QTL) for adult plant resistance (APR) to stripe rust, QYr.nafu-2BL and QYr.nafu-3BS, were validated and introgressed from wheat line P9897 into three Chinese elite wheat cultivars, Chuanmai 42, Xiangmai 25, and Zhengmai 9023, through marker validation. The three Chinese elite varieties were used as the female parent to cross with wheat line P9897, and they were selfed to the F6 generation. A total of 114 lines were then selected based on field agronomic traits and stripe rust resistance. Four markers (Xcfd73, Xgwm120, Xbarc87 and Xbarc133) linked with the QTL's regions were employed to screen the 114 F6 lines. Subsequently, 27 lines combining two target QTL from P9897 were selected. The combination of agronomic traits and disease resistance results showed that 13 of these selected lines had favorable application prospects. The promising lines selected in this study could enrich the genetic resources of wheat stripe rust resistance genes, as well as provide material support and a theoretical basis for the prevention and control of wheat stripe rust in China. [ABSTRACT FROM AUTHOR]