RGB imaging and computer vision-based approaches for identifying spike number loci for wheat

The spike number (SN) is an important trait that significantly impacts grain yield in wheat. Manual counting of SN is time-consuming, hindering large-scale breeding efforts. Hence, there is an urgent need to develop efficient and accurate methodologies for SN counting. A YOLOX algorithm was used to...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Lei, Hassan, Muhammad Adeel, Wang, Duoxia, Wan, Guoliang, Beegum, Sahila, Rasheed, Awais, Xia, Xianchun, He, Yong, Zhang, Yong, He, Zhonghu, Liu, Jindong, Xiao, Yonggui
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/179248
_version_ 1855533914072809472
author Li, Lei
Hassan, Muhammad Adeel
Wang, Duoxia
Wan, Guoliang
Beegum, Sahila
Rasheed, Awais
Xia, Xianchun
He, Yong
Zhang, Yong
He, Zhonghu
Liu, Jindong
Xiao, Yonggui
author_browse Beegum, Sahila
Hassan, Muhammad Adeel
He, Yong
He, Zhonghu
Li, Lei
Liu, Jindong
Rasheed, Awais
Wan, Guoliang
Wang, Duoxia
Xia, Xianchun
Xiao, Yonggui
Zhang, Yong
author_facet Li, Lei
Hassan, Muhammad Adeel
Wang, Duoxia
Wan, Guoliang
Beegum, Sahila
Rasheed, Awais
Xia, Xianchun
He, Yong
Zhang, Yong
He, Zhonghu
Liu, Jindong
Xiao, Yonggui
author_sort Li, Lei
collection Repository of Agricultural Research Outputs (CGSpace)
description The spike number (SN) is an important trait that significantly impacts grain yield in wheat. Manual counting of SN is time-consuming, hindering large-scale breeding efforts. Hence, there is an urgent need to develop efficient and accurate methodologies for SN counting. A YOLOX algorithm was used to determine the optimal growth stage for developing wheat spike detection models among recombinant inbred lines (RILs) across Zhongmai 175 x Lunxuan 987 and a diverse panel of 166 cultivars. We subsequently increased the precision of spike identification by developing a new YOLOX-P algorithm that incorporates the convolutional block attention module and increasing the resolution of the input images. We also used these SN data to identify underlying loci in the Zhongmai 578 x Jimai 22 RIL population. The results revealed that the late grain-filling stage presented the highest precision among the SN detection models, with accuracies ranging from 91.8 to 95.02 %. The improved YOLOX-P algorithm demonstrated higher mean average precision scores (5.30-5.99 %) and F1 scores (0.06) than did the YOLOX algorithm when it was applied to the same subsets. Three new SN loci, namely, QSN.caas-4A2, QSN.caas-4D and QSN.caas-5B2, were identified using the 50k SNP arrays. Two kompetitive allele-specific PCR markers linked with QSN.caas-4A2 and QSN.caas-5B2 were developed, and their genetic effects were validated in a diverse panel of 166 cultivars. These findings provide useful tools for high-throughput identification of SNs and novel loci in wheat.
format Journal Article
id CGSpace179248
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1792482025-12-24T02:12:07Z RGB imaging and computer vision-based approaches for identifying spike number loci for wheat Li, Lei Hassan, Muhammad Adeel Wang, Duoxia Wan, Guoliang Beegum, Sahila Rasheed, Awais Xia, Xianchun He, Yong Zhang, Yong He, Zhonghu Liu, Jindong Xiao, Yonggui triticum aestivum genetics spikes datasets The spike number (SN) is an important trait that significantly impacts grain yield in wheat. Manual counting of SN is time-consuming, hindering large-scale breeding efforts. Hence, there is an urgent need to develop efficient and accurate methodologies for SN counting. A YOLOX algorithm was used to determine the optimal growth stage for developing wheat spike detection models among recombinant inbred lines (RILs) across Zhongmai 175 x Lunxuan 987 and a diverse panel of 166 cultivars. We subsequently increased the precision of spike identification by developing a new YOLOX-P algorithm that incorporates the convolutional block attention module and increasing the resolution of the input images. We also used these SN data to identify underlying loci in the Zhongmai 578 x Jimai 22 RIL population. The results revealed that the late grain-filling stage presented the highest precision among the SN detection models, with accuracies ranging from 91.8 to 95.02 %. The improved YOLOX-P algorithm demonstrated higher mean average precision scores (5.30-5.99 %) and F1 scores (0.06) than did the YOLOX algorithm when it was applied to the same subsets. Three new SN loci, namely, QSN.caas-4A2, QSN.caas-4D and QSN.caas-5B2, were identified using the 50k SNP arrays. Two kompetitive allele-specific PCR markers linked with QSN.caas-4A2 and QSN.caas-5B2 were developed, and their genetic effects were validated in a diverse panel of 166 cultivars. These findings provide useful tools for high-throughput identification of SNs and novel loci in wheat. 2025-06 2025-12-23T17:37:24Z 2025-12-23T17:37:24Z Journal Article https://hdl.handle.net/10568/179248 en Open Access application/pdf Elsevier Li, L., Hassan, M. A., Wang, D., Wan, G., Beegum, S., Rasheed, A., Xia, X., He, Y., Zhang, Y., He, Z., Liu, J., & Xiao, Y. (2025). RGB imaging and computer vision-based approaches for identifying spike number loci for wheat. Plant Phenomics, 7(2), 100051. https://doi.org/10.1016/j.plaphe.2025.100051
spellingShingle triticum aestivum
genetics
spikes
datasets
Li, Lei
Hassan, Muhammad Adeel
Wang, Duoxia
Wan, Guoliang
Beegum, Sahila
Rasheed, Awais
Xia, Xianchun
He, Yong
Zhang, Yong
He, Zhonghu
Liu, Jindong
Xiao, Yonggui
RGB imaging and computer vision-based approaches for identifying spike number loci for wheat
title RGB imaging and computer vision-based approaches for identifying spike number loci for wheat
title_full RGB imaging and computer vision-based approaches for identifying spike number loci for wheat
title_fullStr RGB imaging and computer vision-based approaches for identifying spike number loci for wheat
title_full_unstemmed RGB imaging and computer vision-based approaches for identifying spike number loci for wheat
title_short RGB imaging and computer vision-based approaches for identifying spike number loci for wheat
title_sort rgb imaging and computer vision based approaches for identifying spike number loci for wheat
topic triticum aestivum
genetics
spikes
datasets
url https://hdl.handle.net/10568/179248
work_keys_str_mv AT lilei rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT hassanmuhammadadeel rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT wangduoxia rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT wanguoliang rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT beegumsahila rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT rasheedawais rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT xiaxianchun rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT heyong rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT zhangyong rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT hezhonghu rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT liujindong rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat
AT xiaoyonggui rgbimagingandcomputervisionbasedapproachesforidentifyingspikenumberlociforwheat