Classification of lung adenocarcinoma transcriptome subtypes from pathological images using deep convolutional networks.
Classification of lung adenocarcinoma transcriptome subtypes from pathological images using deep convolutional networks.
复制标题
DOI：
10.1007/s11548-018-1835-2
复制
发表时间：
2018-12
影响因子：
3
通讯作者：
Kanaya S
中科院分区：
文献类型：
--
作者：
Antonio VAA;Ono N;Saito A;Sato T;Altaf-Ul-Amin M;Kanaya S
卷积神经网络由于其强大的潜力而在图像识别和图像分析中迅速流行。本文提出了一种基于神经网络的肺腺癌亚型分类方法，该方法能够从更广的区域评估表型特征，并考虑细胞分布。为了识别肿瘤的类型，我们不仅需要详细描述细胞的特征，还需要结合不同类型细胞的统计分布。实现了自动编码器的变体作为神经网络的预训练卷积层的构建块。然后提出了一种稀疏深度自动编码器，它最大限度地减少了编码层上的局部信息熵，并应用于大小的图像。我们应用该模型从肺腺癌的病理图像中提取特征，肺腺癌由先前由癌症基因组图谱网络定义的三种转录组亚型组成。由于肿瘤组织由异质细胞群组成，识别肿瘤转录组亚型需要比局部细胞模式更多的信息。然后，使用这种方法提取的参数将用于多个缩减阶段，以对较大的图像执行分类。我们能够证明，这些网络成功地识别肺腺癌的形态学特征。我们还进行了分类和重建实验，以比较变体的输出。结果表明，需要覆盖组织的特定区域的较大输入图像来识别转录组亚型。具有输入的稀疏自动编码器网络提供了98.9%的分类准确率。这项研究显示了自动编码器作为特征提取范例的潜力，并为整个载玻片图像分析工具从病理特征预测肿瘤的分子亚型铺平了道路。
Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions. In order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size . We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images. We were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with input provides a 98.9% classification accuracy. This study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features.
登录
查看更多内容
影响因子：
--
作者：
Malon CD;Cosatto E
通讯作者：
Cosatto E
影响因子：
19.5
作者：
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者：
Fei-Fei, Li
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred
DOI：
10.1136/amiajnl-2012-001540
发表时间：
2013-11
期刊：
Journal of the American Medical Informatics Association : JAMIA
影响因子：
--
作者：
Kothari S;Phan JH;Stokes TH;Wang MD
通讯作者：
Wang MD
DOI：
10.1016/j.trsl.2015.08.001
发表时间：
2015-12
期刊：
Translational research : the journal of laboratory and clinical medicine
影响因子：
--
作者：
Chang JT;Lee YM;Huang RS
通讯作者：
Huang RS