论文标题
金字塔聚焦网络用于CT图像中的突变预测和分类
Pyramid Focusing Network for mutation prediction and classification in CT images
论文作者
论文摘要
预测基因在肿瘤中的突变状态具有很大的临床意义。最近的研究表明，通过研究计算机断层扫描（CT）数据的肿瘤的图像特征，某些突变可能是无创的。当前，这种图像特征识别方法主要依赖手动处理来单独提取通用图像特征或机器处理，而无需考虑肿瘤本身的形态差异，这使得很难实现进一步的突破。在本文中，我们提出了一个基于CT图像的突变预测和分类的金字塔聚焦网络（PFNET）。首先，根据观察到的观察，我们使用空间金字塔池在特征地图中收集语义提示，这是根据肿瘤的形状和大小变化的观察结果。第二，我们基于考虑到适当突变检测所需的特征通常在肿瘤边缘的交叉扇区中不明显地提高了这些网络的互动率，从而提高了损失函数。最后，我们基于数据增强设计了一种培训计划，以增强网络的概括能力。我们的方法对20个测试量的临床胃CT数据集进行了广泛的验证，我们的方法在预测CT图像处的HER-2基因突变状态时达到了94.90％的准确性。
Predicting the mutation status of genes in tumors is of great clinical significance. Recent studies have suggested that certain mutations may be noninvasively predicted by studying image features of the tumors from Computed Tomography (CT) data. Currently, this kind of image feature identification method mainly relies on manual processing to extract generalized image features alone or machine processing without considering the morphological differences of the tumor itself, which makes it difficult to achieve further breakthroughs. In this paper, we propose a pyramid focusing network (PFNet) for mutation prediction and classification based on CT images. Firstly, we use Space Pyramid Pooling to collect semantic cues in feature maps from multiple scales according to the observation that the shape and size of the tumors are varied.Secondly, we improve the loss function based on the consideration that the features required for proper mutation detection are often not obvious in cross-sections of tumor edges, which raises more attention to these hard examples in the network. Finally, we devise a training scheme based on data augmentation to enhance the generalization ability of networks. Extensively verified on clinical gastric CT datasets of 20 testing volumes with 63648 CT images, our method achieves the accuracy of 94.90% in predicting the HER-2 genes mutation status of at the CT image.
