Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images.
Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images.
复制标题
DOI：
10.1016/j.ebiom.2017.12.026
复制
发表时间：
2018-01
期刊：
影响因子：
11.1
通讯作者：
Hajirasouliha I
中科院分区：
文献类型：
--
作者：
Khosravi P;Kazemi E;Imielinski M;Elemento O;Hajirasouliha I
肿瘤组织的病理学评估对于癌症患者的诊断至关重要，自动化图像分析方法在提高诊断精度和帮助减少人为错误方面具有巨大潜力。在这项研究中，我们利用了几种基于卷积神经网络（CNN）的计算方法，并建立了一个独立的管道来有效地对不同类型癌症的不同组织病理学图像进行分类。特别是，我们展示了我们的管道区分肺癌的两种亚型，膀胱癌的四种生物标志物和乳腺癌的五种生物标志物的效用。此外，我们应用我们的管道来区分膀胱癌和乳腺癌的四种免疫组织化学（IHC）染色评分。我们的分类管道包括一个基本的CNN架构，谷歌的Inceptions与三个训练策略，以及两个最先进的算法，Inception和ResNet的集合。训练策略包括训练Google Inception的最后一层，从头开始训练网络，以及使用Google Inception架构的两个预训练版本Inception-V1和Inception-V3微调我们数据的参数。我们展示了深度学习方法识别癌症亚型的能力，以及Google Inceptions即使在存在广泛肿瘤异质性的情况下的鲁棒性。平均而言，我们的管道分别实现了100%，92%，95%和69%的各种癌症组织，亚型，生物标志物和评分的区分准确度。我们的管道和相关文档可在https://github.com/ih-_lab/CNN_Smoothie上免费获得。这项工作展示了深度学习方法在存在广泛肿瘤异质性的情况下对病理图像进行分类的能力。在开源管道中比较了基本的CNN架构和几种最先进的图像分类架构。该流水线适用于广泛的组织病理学图像。
Pathological evaluation of tumor tissue is pivotal for diagnosis in cancer patients and automated image analysis approaches have great potential to increase precision of diagnosis and help reduce human error. In this study, we utilize several computational methods based on convolutional neural networks (CNN) and build a stand-alone pipeline to effectively classify different histopathology images across different types of cancer. In particular, we demonstrate the utility of our pipeline to discriminate between two subtypes of lung cancer, four biomarkers of bladder cancer, and five biomarkers of breast cancer. In addition, we apply our pipeline to discriminate among four immunohistochemistry (IHC) staining scores of bladder and breast cancers. Our classification pipeline includes a basic CNN architecture, Google's Inceptions with three training strategies, and an ensemble of two state-of-the-art algorithms, Inception and ResNet. Training strategies include training the last layer of Google's Inceptions, training the network from scratch, and fine-tunning the parameters for our data using two pre-trained version of Google's Inception architectures, Inception-V1 and Inception-V3. We demonstrate the power of deep learning approaches for identifying cancer subtypes, and the robustness of Google's Inceptions even in presence of extensive tumor heterogeneity. On average, our pipeline achieved accuracies of 100%, 92%, 95%, and 69% for discrimination of various cancer tissues, subtypes, biomarkers, and scores, respectively. Our pipeline and related documentation is freely available at https://github.com/ih-_lab/CNN_Smoothie. This work presents the power of deep learning approaches for classifying pathology images in presence of extensive tumor heterogeneity. A basic CNN architecture and several state-of-the-art image classification architectures are compared in an open source pipeline. The pipeline is applicable to wide rang of histopathology images.
登录
查看更多内容
影响因子：
50.5
作者：
Bueno-de-Mesquita, J. M.;Nuyten, D. S. A.;van de Vijver, M. J.
通讯作者：
van de Vijver, M. J.
影响因子：
64.8
作者：
Cancer Genome Atlas Research Network
通讯作者：
Cancer Genome Atlas Research Network
影响因子：
5.7
作者：
Allouche, Omri;Tsoar, Asaf;Kadmon, Ronen
通讯作者：
Kadmon, Ronen
影响因子：
6.4
作者：
Bouzin, Caroline;Saini, Monika L.;Bol, Vanesa
通讯作者：
Bol, Vanesa
影响因子：
2.7
作者：
COHEN, J
通讯作者：
COHEN, J