Universal encoding of pan-cancer histology by deep texture representations
Universal encoding of pan-cancer histology by deep texture representations
复制标题
DOI：
10.1016/j.celrep.2022.110424
复制
发表时间：
2022-03-01
期刊：
影响因子：
8.8
通讯作者：
Ishikawa, Shumpei
中科院分区：
文献类型：
--
作者：
Komura, Daisuke;Kawabe, Akihiro;Ishikawa, Shumpei
癌症组织学图像包含丰富的生物学和临床信息，但定量表示可能存在问题，并且阻碍了大规模数据集的直接比较和积累。在这里，我们通过双线性卷积神经网络产生的深度纹理表示（DTR）展示了癌症组织学的成功通用编码。基于DTR的无监督组织学分析可捕获形态学多样性，可应用于癌症活检，并揭示组织学特征与免疫检查点抑制剂（ICI）反应之间的关系。基于DTR的基于内容的图像检索能够使用癌症基因组图谱（TCGA）数据集快速检索组织学相似的图像。此外，通过与驱动基因和临床上可操作的基因突变的全面比较，我们成功地从苏木精和曙红染色图像中预测了309种基因组特征和癌症类型的组合。凭借其在智能手机等可访问设备上的安装能力，癌症组织学通用编码对癌症诊断和治疗的全球均衡化产生了巨大影响。
Cancer histological images contain rich biological and clinical information, but quantitative representation can be problematic and has prevented the direct comparison and accumulation of large-scale datasets. Here, we show successful universal encoding of cancer histology by deep texture representations (DTRs) produced by a bilinear convolutional neural network. DTR-based, unsupervised histological profiling, which captures the morphological diversity, is applied to cancer biopsies and reveals relationships between histologic characteristics and the response to immune checkpoint inhibitors (ICIs). Content-based image retrieval based on DTRs enables the quick retrieval of histologically similar images using The Cancer Genome Atlas (TCGA) dataset. Furthermore, via comprehensive comparisons with driver and clinically actionable gene mutations, we successfully predict 309 combinations of genomic features and cancer types from hematoxylin-and-eosin-stained images. With its mounting capabilities on accessible devices, such as smartphones, universal encoding for cancer histology has a strong impact on global-equalization for cancer diagnosis and therapies.