Histopathological images provide the definitive source of cancer diagnosis, containing information used by pathologists to identify and subclassify malignant disease, and to guide therapeutic choices. These images contain vast amounts of information, much of which is currently unavailable to human interpretation. Supervised deep learning approaches have been powerful for classification tasks, but they are inherently limited by the cost and quality of annotations. Therefore, we developed Histomorphological Phenotype Learning, an unsupervised methodology, which requires no annotations and operates via the self-discovery of discriminatory image features in small image tiles. Tiles are grouped into morphologically similar clusters which appear to represent recurrent modes of tumor growth emerging under natural selection. These clusters have distinct features which can be identified using orthogonal methods. Applied to lung cancer tissues, we show that they align closely with patient outcomes, with histopathologically recognised tumor types and growth patterns, and with transcriptomic measures of immunophenotype.
翻译:病理学图象是癌症诊断的决定性来源,含有病理学家用来识别恶性疾病并将其分类并指导治疗选择的信息。这些图象包含大量信息,目前人类无法解释其中的大部分信息。受监督的深层次学习方法对于分类任务来说是强大的,但从本质上说,它们受到说明的成本和质量的限制。因此,我们开发了历史形态基因学学习,这是一种不受监督的方法,不需要说明,通过在小图象上自我发现歧视性图象特征来操作。轮胎被分组成形态相似的组群,似乎代表自然选择下出现的经常肿瘤生长模式。这些组群具有独特的特征,可以使用直观的方法加以识别。应用于肺癌组织,我们表明它们与病人的结果、其病理学上公认的肿瘤类型和生长模式以及免疫基因型的定型测量方法密切吻合。