Zhang Fan, Yang Junlin, Nezami Nariman, Laage-Gaupp Fabian, Chapiro Julius, De Lin Ming, Duncan James
Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA.
Patch Based Tech Med Imaging (2018). 2018 Sep;11075:59-66. doi: 10.1007/978-3-030-00500-9_7. Epub 2018 Sep 15.
In this project, our goal is to classify different types of liver tissue on 3D multi-parameter magnetic resonance images in patients with hepatocellular carcinoma. In these cases, 3D fully annotated segmentation masks from experts are expensive to acquire, thus the dataset available for training a predictive model is usually small. To achieve the goal, we designed a novel deep convolutional neural network that incorporates auto-context elements directly into a U-net-like architecture. We used a patch-based strategy with a weighted sampling procedure in order to train on a sufficient number of samples. Furthermore, we designed a multi-resolution and multi-phase training framework to reduce the learning space and to increase the regularization of the model. Our method was tested on images from 20 patients and yielded promising results, outperforming standard neural network approaches as well as a benchmark method for liver tissue classification.
在这个项目中，我们的目标是对肝细胞癌患者的三维多参数磁共振图像上的不同类型肝组织进行分类。在这些病例中，获取专家提供的三维完全标注分割掩码成本高昂，因此可用于训练预测模型的数据集通常较小。为实现这一目标，我们设计了一种新颖的深度卷积神经网络，它将自动上下文元素直接融入类似U-net的架构中。我们采用基于图像块的策略和加权采样程序，以便在足够数量的样本上进行训练。此外，我们设计了一个多分辨率和多阶段训练框架，以减少学习空间并增加模型的正则化。我们的方法在20名患者的图像上进行了测试，取得了令人满意的结果，优于标准神经网络方法以及肝组织分类的基准方法。
