论文标题
MLP-GAN用于脑容器图像分割
MLP-GAN for Brain Vessel Image Segmentation
论文作者
论文摘要
脑血管图像分割可以用作有前途的生物标志物，以更好地预防和治疗不同的疾病。一种成功的方法是将分割视为图像到图像的翻译任务，并执行有条件的生成对抗网络（CGAN），以学习两个分布之间的转换。在本文中，我们提出了一种新型的多视图方法MLP-GAN，该方法将3D体积脑容器图像分为三个不同的2D图像（即矢状，冠状，冠状，轴向），然后将它们喂入三个不同的2D CGAN。拟议的MLP-GAN不仅减轻了原始3D神经网络中存在的记忆问题，而且还保留了3D空间信息。具体来说，我们利用U-NET作为发电机的骨干，重新设计了与MLP混合器集成的Skip连接模式，该模式最近引起了很多关注。我们的模型获得了捕获交叉绘制信息以与MLP混合使用者学习全局信息的能力。在公共脑容器数据集上进行了广泛的实验，该数据集表明我们的MLP-GAN优于其他最先进的方法。我们在https://github.com/bxie9/mlp-gan上发布代码
Brain vessel image segmentation can be used as a promising biomarker for better prevention and treatment of different diseases. One successful approach is to consider the segmentation as an image-to-image translation task and perform a conditional Generative Adversarial Network (cGAN) to learn a transformation between two distributions. In this paper, we present a novel multi-view approach, MLP-GAN, which splits a 3D volumetric brain vessel image into three different dimensional 2D images (i.e., sagittal, coronal, axial) and then feed them into three different 2D cGANs. The proposed MLP-GAN not only alleviates the memory issue which exists in the original 3D neural networks but also retains 3D spatial information. Specifically, we utilize U-Net as the backbone for our generator and redesign the pattern of skip connection integrated with the MLP-Mixer which has attracted lots of attention recently. Our model obtains the ability to capture cross-patch information to learn global information with the MLP-Mixer. Extensive experiments are performed on the public brain vessel dataset that show our MLP-GAN outperforms other state-of-the-art methods. We release our code at https://github.com/bxie9/MLP-GAN
