PDF(Pubmed)
Abstract：
BACKGROUND: Cotton accounts for 80% of the global natural fibre production. Its leaf hairiness affects insect resistance, fibre yield, and economic value. However, this phenotype is still qualitatively assessed by visually attributing a Genotype Hairiness Score (GHS) to a leaf/plant, or by using the HairNet deep-learning model which also outputs a GHS. Here, we introduce HairNet2, a quantitative deep-learning model which detects leaf hairs (trichomes) from images and outputs a segmentation mask and a Leaf Trichome Score (LTS).
RESULTS: Trichomes of 1250 images were annotated (AnnCoT) and a combination of six Feature Extractor modules and five Segmentation modules were tested alongside a range of loss functions and data augmentation techniques. HairNet2 was further validated on the dataset used to build HairNet (CotLeaf-1), a similar dataset collected in two subsequent seasons (CotLeaf-2), and a dataset collected on two genetically diverse populations (CotLeaf-X). The main findings of this study are that (1) leaf number, environment and image position did not significantly affect results, (2) although GHS and LTS mostly correlated for individual GHS classes, results at the genotype level revealed a strong LTS heterogeneity within a given GHS class, (3) LTS correlated strongly with expert scoring of individual images.
CONCLUSIONS: HairNet2 is the first quantitative and scalable deep-learning model able to measure leaf hairiness. Results obtained with HairNet2 concur with the qualitative values used by breeders at both extremes of the scale (GHS 1-2, and 5-5+), but interestingly suggest a reordering of genotypes with intermediate values (GHS 3-4+). Finely ranking mild phenotypes is a difficult task for humans. In addition to providing assistance with this task, HairNet2 opens the door to selecting plants with specific leaf hairiness characteristics which may be associated with other beneficial traits to deliver better varieties.
RESULTS: Trichomes of 1250 images were annotated (AnnCoT) and a combination of six Feature Extractor modules and five Segmentation modules were tested alongside a range of loss functions and data augmentation techniques. HairNet2 was further validated on the dataset used to build HairNet (CotLeaf-1), a similar dataset collected in two subsequent seasons (CotLeaf-2), and a dataset collected on two genetically diverse populations (CotLeaf-X). The main findings of this study are that (1) leaf number, environment and image position did not significantly affect results, (2) although GHS and LTS mostly correlated for individual GHS classes, results at the genotype level revealed a strong LTS heterogeneity within a given GHS class, (3) LTS correlated strongly with expert scoring of individual images.
CONCLUSIONS: HairNet2 is the first quantitative and scalable deep-learning model able to measure leaf hairiness. Results obtained with HairNet2 concur with the qualitative values used by breeders at both extremes of the scale (GHS 1-2, and 5-5+), but interestingly suggest a reordering of genotypes with intermediate values (GHS 3-4+). Finely ranking mild phenotypes is a difficult task for humans. In addition to providing assistance with this task, HairNet2 opens the door to selecting plants with specific leaf hairiness characteristics which may be associated with other beneficial traits to deliver better varieties.
摘要：
背景：棉花占全球天然纤维产量的80％。它的叶片毛羽影响昆虫抗性，纤维产量，和经济价值。然而,这种表型仍然是定性评估通过视觉归因基因型毛羽评分（GHS）到叶/植物，或使用也输出GHS的HairNet深度学习模型。这里,我们引入了HairNet2，这是一种定量的深度学习模型，可从图像中检测叶毛（毛状体），并输出分割掩码和叶状毛状体评分（LTS）。
结果：对1250个图像的Trichome进行了注释（AnnCoT），并测试了六个特征提取器模块和五个分割模块的组合以及一系列损失函数和数据增强技术。在用于构建HairNet（CotLeaf-1）的数据集上进一步验证了HairNet2，在随后的两个季节中收集的类似数据集（CotLeaf-2），以及在两个遗传多样性种群（CotLeaf-X）上收集的数据集。本研究的主要发现是(1)叶数，环境和图像位置没有显着影响结果，(2)尽管GHS和LTS与个别GHS类别大多相关，基因型水平的结果表明，在给定的GHS类别中存在很强的LTS异质性，（3）LTS与单个图像的专家评分密切相关。
结论：HairNet2是第一个能够测量叶片毛羽的定量和可扩展的深度学习模型。使用HairNet2获得的结果与育种者在两个极端尺度（GHS1-2和5-5）使用的定性值一致，但有趣的是，建议对具有中间值的基因型进行重新排序(GHS3-4+)。精细排列轻度表型对人类来说是一项艰巨的任务。除了为这项任务提供帮助之外，HairNet2为选择具有特定叶片毛羽特性的植物打开了大门，这些特性可能与其他有益性状相关，以提供更好的品种。
结果：对1250个图像的Trichome进行了注释（AnnCoT），并测试了六个特征提取器模块和五个分割模块的组合以及一系列损失函数和数据增强技术。在用于构建HairNet（CotLeaf-1）的数据集上进一步验证了HairNet2，在随后的两个季节中收集的类似数据集（CotLeaf-2），以及在两个遗传多样性种群（CotLeaf-X）上收集的数据集。本研究的主要发现是(1)叶数，环境和图像位置没有显着影响结果，(2)尽管GHS和LTS与个别GHS类别大多相关，基因型水平的结果表明，在给定的GHS类别中存在很强的LTS异质性，（3）LTS与单个图像的专家评分密切相关。
结论：HairNet2是第一个能够测量叶片毛羽的定量和可扩展的深度学习模型。使用HairNet2获得的结果与育种者在两个极端尺度（GHS1-2和5-5）使用的定性值一致，但有趣的是，建议对具有中间值的基因型进行重新排序(GHS3-4+)。精细排列轻度表型对人类来说是一项艰巨的任务。除了为这项任务提供帮助之外，HairNet2为选择具有特定叶片毛羽特性的植物打开了大门，这些特性可能与其他有益性状相关，以提供更好的品种。
