论文标题
使用部分卷积生成对抗网络的自由形式病变合成，以增强深度学习肝肿瘤分割
Free-form Lesion Synthesis Using a Partial Convolution Generative Adversarial Network for Enhanced Deep Learning Liver Tumor Segmentation
论文作者
论文摘要
已显示自动深度学习分割模型可提高分割效率和准确性。但是，训练强大的分割模型需要大量标记的训练样本，这可能是不切实际的。这项研究旨在开发一个深度学习框架，用于产生可用于增强网络培训的合成病变。病变合成网络是一种修改的生成对抗网络（GAN）。具体而言，我们创新了部分卷积策略来构建一个类似于Unet的发电机。该鉴别器是使用具有梯度惩罚和光谱归一化的Wasserstein Gan设计的。开发了基于主成分分析的掩模生成方法，以模拟各种病变形状。然后，通过病变合成网络将生成的面膜转换为肝脏病变。评估了病变的合成框架的病变纹理，并使用合成病变来训练病变分割网络，以进一步验证该框架的有效性。所有网络均经过LIT的公共数据集训练和测试。与两个使用的纹理参数（GLCM-能量和GLCM相关）的实际病变相比，该方法产生的合成病变具有非常相似的直方图分布。 Glcm-能量和GlCM相关的Kullback-Lebler差异分别为0.01和0.10。包括肿瘤分割网络中的合成病变包括U-NET的分割骰子性能从67.3％显着提高到71.4％（p <0.05）。同时，体积的精度和灵敏度分别从74.6％提高到76.0％（P = 0.23）和66.1％到70.9％（P <0.01）。合成数据可显着提高分割性能。
Automatic deep learning segmentation models has been shown to improve both the segmentation efficiency and the accuracy. However, training a robust segmentation model requires considerably large labeled training samples, which may be impractical. This study aimed to develop a deep learning framework for generating synthetic lesions that can be used to enhance network training. The lesion synthesis network is a modified generative adversarial network (GAN). Specifically, we innovated a partial convolution strategy to construct an Unet-like generator. The discriminator is designed using Wasserstein GAN with gradient penalty and spectral normalization. A mask generation method based on principal component analysis was developed to model various lesion shapes. The generated masks are then converted into liver lesions through a lesion synthesis network. The lesion synthesis framework was evaluated for lesion textures, and the synthetic lesions were used to train a lesion segmentation network to further validate the effectiveness of this framework. All the networks are trained and tested on the public dataset from LITS. The synthetic lesions generated by the proposed approach have very similar histogram distributions compared to the real lesions for the two employed texture parameters, GLCM-energy and GLCM-correlation. The Kullback-Leibler divergence of GLCM-energy and GLCM-correlation were 0.01 and 0.10, respectively. Including the synthetic lesions in the tumor segmentation network improved the segmentation dice performance of U-Net significantly from 67.3% to 71.4% (p<0.05). Meanwhile, the volume precision and sensitivity improve from 74.6% to 76.0% (p=0.23) and 66.1% to 70.9% (p<0.01), respectively. The synthetic data significantly improves the segmentation performance.
