Pathology GAN: Learning deep representations of cancer tissue-猫眼课题宝

DOI：

10.59275/j.melba.2021-gfgg

发表时间：

2019-07

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

A. Quiros;R. Murray-Smith;Ke Yuan

肿瘤的组织病理学图像包含关于肿瘤如何生长以及它们如何与微环境相互作用的丰富信息。更好地了解这些图像中的组织表型可以揭示癌症病理过程的新决定因素，进而改善诊断和治疗选择。深度学习的进步使其成为实现这些目标的理想选择，然而，它的应用受到来自患者数据的高质量标签成本的限制。无监督学习，特别是具有表征学习特性的深度生成模型，为进一步了解癌症组织表型、捕捉组织形态提供了另一种途径。在本文中，我们开发了一个框架，该框架允许生成对抗网络（gan）捕获关键组织特征，并使用这些特征为其潜在空间提供结构。为此，我们在两个不同的数据集上训练我们的模型，一个是来自国家肿瘤疾病中心（NCT，德国）的H&E结直肠癌组织，另一个是来自荷兰癌症研究所（NKI，荷兰）和温哥华总医院（VGH，加拿大）的H&E乳腺癌组织。分别由86张幻灯片图像和576张组织微阵列（tma）组成。我们的模型产生了高质量的图像，Frechet Inception Distance （FID）为16.65（乳腺癌）和32.05（结直肠癌）。我们进一步评估具有癌组织特征（如肿瘤、淋巴细胞或基质细胞计数）的图像质量，使用定量信息计算FID，结果显示一致的性能为9.86。此外，我们模型的潜在空间显示了一个可解释的结构，并允许语义向量操作转化为组织特征转换。此外，两位病理学专家的评分发现，我们生成的组织图像与真实组织图像之间没有显著差异。代码、生成的图像和预训练的模型可在https://github.com/AdalbertoCq/Pathology-GAN上获得

Histopathological images of tumours contain abundant information about how tumours grow and how they interact with their micro-environment. Better understanding of tissue phenotypes in these images could reveal novel determinants of pathological processes underlying cancer, and in turn improve diagnosis and treatment options. Advances of Deep learning makes it ideal to achieve those goals, however, its application is limited by the cost of high quality labels from patients data. Unsupervised learning, in particular, deep generative models with representation learning properties provides an alternative path to further understand cancer tissue phenotypes, capturing tissue morphologies. In this paper, we develop a framework which allows Generative Adversarial Networks (GANs) to capture key tissue features and uses these characteristics to give structure to its latent space. To this end, we trained our model on two different datasets, an H&E colorectal cancer tissue from the National Center for Tumor diseases (NCT, Germany) and an H&E breast cancer tissue from the Netherlands Cancer Institute (NKI, Netherlands) and Vancouver General Hospital (VGH, Canada). Composed of 86 slide images and 576 tissue micro-arrays (TMAs) respectively. We show that our model generates high quality images, with a Frechet Inception Distance (FID) of 16.65 (breast cancer) and 32.05 (colorectal cancer). We further assess the quality of the images with cancer tissue characteristics (e.g. count of cancer, lymphocytes, or stromal cells), using quantitative information to calculate the FID and showing consistent performance of 9.86. Additionally, the latent space of our model shows an interpretable structure and allows semantic vector operations that translate into tissue feature transformations. Furthermore, ratings from two expert pathologists found no significant difference between our generated tissue images from real ones. The code, generated images, and pretrained model are available at https://github.com/AdalbertoCq/Pathology-GAN

Pathology GAN: Learning deep representations of cancer tissue

文献摘要

相似文献