arXiv 2409.150922024-12-20cs.CVcs.AI

M2OST：基于数字病理图像预测空间转录组学的多对一回归方法

M2OST: Many-to-one Regression for Predicting Spatial Transcriptomics from Digital Pathology Images

Zhejiang University（浙江大学）；Zhejiang Lab（之江实验室）；Ritsumeikan University（立命馆大学）

Hongyi Wang, Xiuju Du, Jing Liu, Shuyi Ouyang, Yen-Wei Chen, Lanfen Lin

备注：: Improved from our previous unpublished work arXiv:2401.10608. arXiv admin note: substantial text overlap with arXiv:2401.10608

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出多对一回归Transformer模型M2OST，利用数字病理图像的多尺度分层结构及点间视觉信息预测空间转录组学基因表达，在三个公共数据集上以更少参数和FLOPs达到最优性能。

摘要：

Spatial Transcriptomics (ST) 的发展促进了基于组织病理学图像的空间感知基因表达谱分析。尽管 ST 数据为肿瘤微环境提供了有价值的见解，但其获取成本仍然昂贵。因此，直接从数字病理图像预测 ST 表达是理想的选择。当前方法通常采用现有的回归主干网络并结合块采样来完成此任务，这忽略了数字病理图像金字塔数据结构中固有的多尺度信息，并浪费了对准确预测基因表达至关重要的点间视觉信息。为了解决这些局限性，我们提出了 M2OST，一种多对一回归 Transformer，它可以通过解耦的多尺度特征提取器适应病理图像的分层结构。与使用一对一图像-标签对训练的传统模型不同，M2OST 使用来自数字病理图像不同级别的多个图像来共同预测它们共同对应点中的基因表达。基于我们的多对一方案，M2OST 可以轻松扩展以适应不同数量的输入，并且其网络结构固有地结合了附近的点间特征，从而增强了回归性能。我们在三个公共 ST 数据集上测试了 M2OST，实验结果表明，M2OST 能够以更少的参数和浮点运算次数（FLOPs）实现最先进的性能。

英文摘要：

The advancement of Spatial Transcriptomics (ST) has facilitated the spatially-aware profiling of gene expressions based on histopathology images. Although ST data offers valuable insights into the micro-environment of tumors, its acquisition cost remains expensive. Therefore, directly predicting the ST expressions from digital pathology images is desired. Current methods usually adopt existing regression backbones along with patch-sampling for this task, which ignores the inherent multi-scale information embedded in the pyramidal data structure of digital pathology images, and wastes the inter-spot visual information crucial for accurate gene expression prediction. To address these limitations, we propose M2OST, a many-to-one regression Transformer that can accommodate the hierarchical structure of the pathology images via a decoupled multi-scale feature extractor. Unlike traditional models that are trained with one-to-one image-label pairs, M2OST uses multiple images from different levels of the digital pathology image to jointly predict the gene expressions in their common corresponding spot. Built upon our many-to-one scheme, M2OST can be easily scaled to fit different numbers of inputs, and its network structure inherently incorporates nearby inter-spot features, enhancing regression performance. We have tested M2OST on three public ST datasets and the experimental results show that M2OST can achieve state-of-the-art performance with fewer parameters and floating-point operations (FLOPs).

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。