论文标题
病变的条件图像生成可改善CT图像中颅内出血的分割
Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images
论文作者
论文摘要
训练机器学习算法时，数据增强可以有效地解决图像的稀缺性。它可以使他们更加强大，可以看不见图像。我们提出了病变条件生成对抗网络LCGAN，以生成合成计算机断层扫描（CT）图像以进行数据增强。病变条件图像（分段掩模）是训练过程中LCGAN的发电机和歧视器的输入。训练有素的模型基于输入掩码生成上下文CT图像。我们使用完全卷积网络（FCN）得分和模糊来量化图像的质量。我们还训练另一个分类网络以选择更好的合成图像。然后将这些合成的CT图像增强到我们的出血病变分割网络中。通过对原始数据的2.5％，10％和25％应用这种增强方法，分割分别提高了12.8％，6％和1.6％。
Data augmentation can effectively resolve a scarcity of images when training machine-learning algorithms. It can make them more robust to unseen images. We present a lesion conditional Generative Adversarial Network LcGAN to generate synthetic Computed Tomography (CT) images for data augmentation. A lesion conditional image (segmented mask) is an input to both the generator and the discriminator of the LcGAN during training. The trained model generates contextual CT images based on input masks. We quantify the quality of the images by using a fully convolutional network (FCN) score and blurriness. We also train another classification network to select better synthetic images. These synthetic CT images are then augmented to our hemorrhagic lesion segmentation network. By applying this augmentation method on 2.5%, 10% and 25% of original data, segmentation improved by 12.8%, 6% and 1.6% respectively.
