Scholarlink

<p>Spatial transcriptomics (ST) measures gene expression at spatial resolution across a tissue section, but its routine clinical use is constrained by high cost, low throughput and tissue consumption. Predicting spatially resolved gene expression directly from the haematoxylin and eosin (H&amp;E) slides already produced by routine pathology offers a scalable alternative. Existing histology-to-ST predictors, however, rely on a single visual encoder that struggles to resolve fine-grained cellular morphology and broader tissue architecture simultaneously—two complementary scales that jointly shape transcriptional state. We introduce AsymST, a dual-pathway framework in which a lightweight convolutional encoder and a pathology foundation model are coupled by an asymmetric cross-attention block: the foundation-model tokens selectively absorb local texture cues from the convolutional branch, but the convolutional tokens are not updated in return, so neither branch homogenises the other. A deep latent information bottleneck provides the main regression pathway, while shallow per-branch auxiliary heads provide explicit branch-level supervision. Across 10 cancer cohorts and 9 spot- and slide-based baselines, AsymST attains the highest mean per-gene Pearson correlation (0.429), ranks first on 9 of 10 cohorts, and remains significantly better than each of the four strongest baselines in a cohort-level Wilcoxon test that treats cancer cohort as the independent unit (BH-adjusted <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(q_{\textrm{BH}}\!=\!0.002\)</EquationSource></InlineEquation> for all four comparisons). Despite using no between-spot spatial modelling at training time, AsymST also achieves higher neighbourhood-scale spatial coherence than slide-based methods at every scale tested, suggesting that spatial coherence can emerge from a sufficiently expressive per-spot visual representation. The accuracy gains concentrate on biologically interpretable immune, inflammatory and stromal programs of the tumour microenvironment, and translate into recovery of B-cell-rich regions resembling tertiary lymphoid structures on a representative lung adenocarcinoma slide—a proof of concept for inferring clinically informative tumour-immunology readouts directly from routine histology.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Asymmetric dual pathway fusion for histology driven spatial transcriptomic prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Xialin Su,
  • Rui Liu,
  • Kailin Zhang,
  • Zhixin Ou,
  • Yifu Gao

摘要

Spatial transcriptomics (ST) measures gene expression at spatial resolution across a tissue section, but its routine clinical use is constrained by high cost, low throughput and tissue consumption. Predicting spatially resolved gene expression directly from the haematoxylin and eosin (H&E) slides already produced by routine pathology offers a scalable alternative. Existing histology-to-ST predictors, however, rely on a single visual encoder that struggles to resolve fine-grained cellular morphology and broader tissue architecture simultaneously—two complementary scales that jointly shape transcriptional state. We introduce AsymST, a dual-pathway framework in which a lightweight convolutional encoder and a pathology foundation model are coupled by an asymmetric cross-attention block: the foundation-model tokens selectively absorb local texture cues from the convolutional branch, but the convolutional tokens are not updated in return, so neither branch homogenises the other. A deep latent information bottleneck provides the main regression pathway, while shallow per-branch auxiliary heads provide explicit branch-level supervision. Across 10 cancer cohorts and 9 spot- and slide-based baselines, AsymST attains the highest mean per-gene Pearson correlation (0.429), ranks first on 9 of 10 cohorts, and remains significantly better than each of the four strongest baselines in a cohort-level Wilcoxon test that treats cancer cohort as the independent unit (BH-adjusted \(q_{\textrm{BH}}\!=\!0.002\) for all four comparisons). Despite using no between-spot spatial modelling at training time, AsymST also achieves higher neighbourhood-scale spatial coherence than slide-based methods at every scale tested, suggesting that spatial coherence can emerge from a sufficiently expressive per-spot visual representation. The accuracy gains concentrate on biologically interpretable immune, inflammatory and stromal programs of the tumour microenvironment, and translate into recovery of B-cell-rich regions resembling tertiary lymphoid structures on a representative lung adenocarcinoma slide—a proof of concept for inferring clinically informative tumour-immunology readouts directly from routine histology.