利用自监督学习在无标签、无注释的病理切片上绘制组织形态学癌症表型图谱
Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unlabeled, unannotated pathology slides
AI总结：
本文提出自监督方法HPL，无需注释即可从病理切片自动发现判别性特征，分组形成组织形态学表型库，揭示良性到恶性轨迹，并与肺癌患者生存及多癌种临床分子表型对齐。
摘要：
癌症的明确诊断和管理依赖于病理学家从显微镜图像中提取信息。这些图像包含复杂的信息，需要耗时且易受人类偏见影响的专家人工解读。监督式深度学习方法已被证明在分类任务中表现强大，但其本质上受限于用于训练这些模型的注释的成本和质量。为解决监督方法的这一局限性，我们开发了组织形态学表型学习（HPL），这是一种完全自监督的方法，无需专家标签或注释，通过在小图像块中自动发现判别性图像特征来运作。图像块被分组为形态相似的聚类，构成组织形态学表型的库，揭示了通过炎症和反应性表型从良性到恶性组织的轨迹。这些聚类具有可通过正交方法识别的独特特征，将组织学、分子和临床表型联系起来。应用于肺癌组织时，我们表明它们与患者生存率、组织病理学公认的肿瘤类型和生长模式以及免疫表型的转录组学测量密切相关。随后，我们证明这些特性在多癌种研究中得以保持。这些结果表明，聚类代表了在自然选择下出现的复发性宿主反应和肿瘤生长模式。代码、预训练模型、学习嵌入和文档可在 https://github.com/AdalbertoCq/Histomorphological-Phenotype-Learning 获取。
英文摘要：
Definitive cancer diagnosis and management depend upon the extraction of information from microscopy images by pathologists. These images contain complex information requiring time-consuming expert human interpretation that is prone to human bias. Supervised deep learning approaches have proven powerful for classification tasks, but they are inherently limited by the cost and quality of annotations used for training these models. To address this limitation of supervised methods, we developed Histomorphological Phenotype Learning (HPL), a fully blue{self-}supervised methodology that requires no expert labels or annotations and operates via the automatic discovery of discriminatory image features in small image tiles. Tiles are grouped into morphologically similar clusters which constitute a library of histomorphological phenotypes, revealing trajectories from benign to malignant tissue via inflammatory and reactive phenotypes. These clusters have distinct features which can be identified using orthogonal methods, linking histologic, molecular and clinical phenotypes. Applied to lung cancer tissues, we show that they align closely with patient survival, with histopathologically recognised tumor types and growth patterns, and with transcriptomic measures of immunophenotype. We then demonstrate that these properties are maintained in a multi-cancer study. These results show the clusters represent recurrent host responses and modes of tumor growth emerging under natural selection. Code, pre-trained models, learned embeddings, and documentation are available to the community at https://github.com/AdalbertoCq/Histomorphological-Phenotype-Learning
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。
