论文标题
在3D生物医学图像中捕获隐式层次结构
Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations
论文作者
论文摘要
我们考虑了对3D体素网格生物医学图像的无监督分割的表示的任务。我们表明，捕获子卷之间隐式分层关系的模型更适合此任务。为此，我们考虑具有双曲线潜在空间的编码器架构，以明确捕获数据子卷中存在的层次关系。我们建议使用新型的陀螺仪卷积层利用3D双曲线变异自动编码器将嵌入空间映射到3D图像。为了捕捉这些关系，我们还引入了基本的自我监督损失（除了标准的VAE损失之外），该损失还散布了近似层次结构，并鼓励隐式相关的子卷卷在嵌入空间中更近地映射。我们介绍了综合数据和生物医学数据的实验，以验证我们的假设。
We consider the task of representation learning for unsupervised segmentation of 3D voxel-grid biomedical images. We show that models that capture implicit hierarchical relationships between subvolumes are better suited for this task. To that end, we consider encoder-decoder architectures with a hyperbolic latent space, to explicitly capture hierarchical relationships present in subvolumes of the data. We propose utilizing a 3D hyperbolic variational autoencoder with a novel gyroplane convolutional layer to map from the embedding space back to 3D images. To capture these relationships, we introduce an essential self-supervised loss -- in addition to the standard VAE loss -- which infers approximate hierarchies and encourages implicitly related subvolumes to be mapped closer in the embedding space. We present experiments on both synthetic data and biomedical data to validate our hypothesis.
