[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2314":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"view_count":31,"doi":32,"paper":33,"created_at":54},2314,"Spectral Transforms as a Tool to Optimize Digital Phenotyping in Biological Images","https:\u002F\u002Fdoi.org\u002F10.1111\u002Fjbg.70076","ABSTRACT Modern livestock breeding has mastered genotyping. Genome‐wide association studies, genomic selection, and SNP arrays enable genetic merit prediction at lower cost. However, phenotyping remains the bottleneck, as manual measurement is slow, expensive, subjective, and unable to capture spatial or temporal trait organization. Digital phenotyping via artificial intelligence could resolve this, but deep learning requires thousands of labelled examples, impractical when phenotyping cost itself limits datasets to hundreds of individuals. This creates a paradox: AI could accelerate phenotyping but requires large numbers of samples to train the models. Here, we demonstrate that integrating computer vision with machine learning offers sample‐efficient digital phenotyping using eggshell colour as a model system. Rather than learning features from scratch (deep learning), we engineer physically motivated features via Wavelet transforms that decompose images into multi‐scale spatial components. Wavelet features captured 14.2 percentage points more variance ( R 2 = 0.976 vs. 0.834, p \u003C 0.001) than standard colorimetry, with 50% better sample efficiency (achieving at n = 60 what colorimetry required n = 120). Variance decomposition revealed 77% of discriminative capacity derives from spatial patterns (bands, spots, gradients) invisible to scalar averages. Additionally, we identified “cryptic phenotypes” (3.3%) where spatial patterns contradicted average colour, cases where colorimeters failed but Wavelets succeeded. The underlying principle—that spatial decomposition can recover organizational information lost by scalar averaging—may be applicable to other traits with spatial or temporal structure, such as marbling, dermatitis, or pigmentation rhythms, although whether comparable performance gains would be observed remains to be tested empirically. Hence, for breeding programs implementing genomic selection, computer vision‐based digital phenotyping captures complex trait variation without massive training datasets, addressing the bottleneck that increasingly limits genetic progress as genotyping becomes trivial.","摘要 现代畜牧育种已掌握基因分型技术。全基因组关联研究、基因组选择和SNP芯片使得遗传 merit 预测成本降低。然而，表型测定仍是瓶颈，因为人工测量速度慢、成本高、主观性强，且无法捕捉性状的空间或时间组织。通过人工智能进行数字表型测定有望解决这一问题，但深度学习需要数千个标记样本，当表型测定成本本身将数据集限制在数百个个体时，这并不现实。这形成了一个悖论：人工智能可以加速表型测定，但需要大量样本才能训练模型。在此，我们证明将计算机视觉与机器学习相结合可提供样本高效的数字表型测定，并以蛋壳颜色作为模型系统。我们不是从头学习特征（深度学习），而是通过小波变换设计具有物理动机的特征，将图像分解为多尺度空间分量。小波特征捕获的方差比标准色度法多14.2个百分点（R² = 0.976 vs. 0.834，p \u003C 0.001），样本效率提高50%（在n = 60时达到色度法需要n = 120才能达到的效果）。方差分解显示，77%的判别能力来自标量平均值无法看到的空间模式（条带、斑点、梯度）。此外，我们识别出“隐蔽表型”（3.3%），即空间模式与平均颜色相矛盾的情况，这些情况下色度计失败但小波成功。其基本原理——空间分解可以恢复标量平均所丢失的组织信息——可能适用于其他具有空间或时间结构的性状，如大理石纹、皮炎或色素沉着节律，尽管是否能观察到 comparable 的性能提升仍有待实证检验。因此，对于实施基因组选择的育种项目，基于计算机视觉的数字表型测定无需大规模训练数据集即可捕获复杂性状变异，解决了随着基因分型变得轻而易举而日益限制遗传进展的瓶颈。",null,"Journal of Animal Breeding and Genetics","2026-09-10T00:00:00Z","论文",10,false,80,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,8,1,"小波变换实现样本高效数字表型，为育种表型瓶颈提供新思路，方法新颖、数据扎实，值得进入每日精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","计算机视觉","基因组选择","数字表型",0,"10.1111\u002Fjbg.70076",{"doi":32,"openalex_id":34,"authors":35,"venue":10,"cited_by_count":31,"oa_url":45,"card":46,"direction":52,"ingested_from":53},"W7212167663",[36,39,42],{"name":37,"orcid":38},"Joseane Padilha da Silva","https:\u002F\u002Forcid.org\u002F0000-0001-6681-6799",{"name":40,"orcid":41},"José V.V. Isola","https:\u002F\u002Forcid.org\u002F0000-0002-3168-3188",{"name":43,"orcid":44},"E. A. P. de Figueiredo","https:\u002F\u002Forcid.org\u002F0000-0003-0893-2489","https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdfdirect\u002F10.1111\u002Fjbg.70076",{"tldr":47,"method":48,"finding":49,"direction":50,"opportunity":51},"用离散小波变换提取蛋壳图像多尺度空间特征，实现小样本高效数字表型。","小波变换结合机器学习，以蛋壳颜色为模型系统，对比色度法。","小波特征解释方差比色度法高14.2个百分点，样本效率提升50%，77%判别力来自空间模式。","农业人工智能与决策模型","将小波空间分解表型框架迁移到其他具空间\u002F时间结构的性状，如大理石纹、皮炎或色素节律，验证普适性。","农业遥感与作物表型","openalex","2026-09-13T23:30:17.802829Z"]