当前位置: X-MOL 学术Biocybern. Biomed. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Gastric histopathology image segmentation using a hierarchical conditional random field
Biocybernetics and Biomedical Engineering ( IF 6.4 ) Pub Date : 2020-10-12 , DOI: 10.1016/j.bbe.2020.09.008
Changhao Sun , Chen Li , Jinghua Zhang , Md Mamunur Rahaman , Shiliang Ai , Hao Chen , Frank Kulwa , Yixin Li , Xiaoyan Li , Tao Jiang

For the Convolutional Neural Networks (CNNs) applied in the intelligent diagnosis of gastric cancer, existing methods mostly focus on individual characteristics or network frameworks without a policy to depict the integral information. Mainly, conditional random field (CRF), an efficient and stable algorithm for analyzing images containing complicated contents, can characterize spatial relation in images. In this paper, a novel hierarchical conditional random field (HCRF) based gastric histopathology image segmentation (GHIS) method is proposed, which can automatically localize abnormal (cancer) regions in gastric histopathology images obtained by an optical microscope to assist histopathologists in medical work. This HCRF model is built up with higher order potentials, including pixel-level and patch-level potentials, and graph-based post-processing is applied to further improve its segmentation performance. Especially, a CNN is trained to build up the pixel-level potentials and another three CNNs are fine-tuned to build up the patch-level potentials for sufficient spatial segmentation information. In the experiment, a hematoxylin and eosin (H&E) stained gastric histopathological dataset with 560 abnormal images are divided into training, validation and test sets with a ratio of 1 : 1 :2. Finally, segmentation accuracy, recall and specificity of 78.91%, 65.59%, and 81.33% are achieved on the test set. Our HCRF model demonstrates high segmentation performance and shows its effectiveness and future potential in the GHIS field.



中文翻译:

使用分层条件随机场的胃组织病理学图像分割

对于在胃癌智能诊断中应用的卷积神经网络(CNN),现有方法主要集中于个人特征或网络框架,而没有描述完整信息的策略。主要地,条件随机场(CRF)是一种用于分析包含复杂内容的图像的高效且稳定的算法,可以表征图像中的空间关系。本文提出了一种基于分层条件随机场(HCRF)的新型胃组织病理学图像分割(GHIS)方法,该方法可以自动定位由光学显微镜获得的胃组织病理学图像中的异常(癌)区域,以协助组织病理学家进行医学工作。此HCRF模型建立有较高阶的电势,包括像素级和贴片级电势,基于图的后处理技术可以进一步提高分割效果。特别是,对CNN进行训练以建立像素级电势,并对另外三个CNN进行微调以为足够的空间分割信息建立补丁级电势。在实验中,将具有560张异常图像的苏木精和曙红(H&E)染色的胃组织病理数据集分为训练集,验证集和测试集,其比例为1:1:2。最后,在测试集上实现了细分精度,召回率和特异性,分别为78.91%,65.59%和81.33%。我们的HCRF模型显示出高分割效果,并显示了其在GHIS领域的有效性和未来潜力。训练一个CNN来建立像素级电位,并对另外三个CNN进行微调以建立用于足够的空间分割信息的面片级电位。在实验中,将具有560张异常图像的苏木精和曙红(H&E)染色的胃组织病理数据集分为训练集,验证集和测试集,其比例为1:1:2。最后,在测试集上实现了细分精度,召回率和特异性,分别为78.91%,65.59%和81.33%。我们的HCRF模型显示出高分割效果,并显示了其在GHIS领域的有效性和未来潜力。训练一个CNN来建立像素级电位,并对另外三个CNN进行微调以建立用于足够的空间分割信息的面片级电位。在实验中,将具有560张异常图像的苏木精和曙红(H&E)染色的胃组织病理数据集分为训练集,验证集和测试集,其比例为1:1:2。最后,在测试集上实现了细分精度,召回率和特异性,分别为78.91%,65.59%和81.33%。我们的HCRF模型显示出高分割效果,并显示了其在GHIS领域的有效性和未来潜力。E)将具有560个异常图像的染色的胃组织病理学数据集按1:1:2的比例分为训练集,验证集和测试集。最后,在测试集上实现了细分精度,召回率和特异性,分别为78.91%,65.59%和81.33%。我们的HCRF模型显示出高分割效果,并显示了其在GHIS领域的有效性和未来潜力。E)将具有560个异常图像的染色的胃组织病理学数据集按1:1:2的比例分为训练集,验证集和测试集。最后,在测试集上实现了细分精度,召回率和特异性,分别为78.91%,65.59%和81.33%。我们的HCRF模型显示出高分割效果,并显示了其在GHIS领域的有效性和未来潜力。

更新日期:2020-10-30
down
wechat
bug