用于体数据医学图像分析的正则SE(3)群卷积
Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis
AI总结：
针对体医学图像的SE(3)等变性问题，提出可分离为连续SO(3)核与空间核的SE(3)群卷积方法，在医学分类任务上准确率较常规CNN最高提升16.5%，泛化能力更优。
摘要：
正则群卷积神经网络（G-CNNs）已被证明可提升模型性能，并增强对不同几何对称性的等变性。本研究针对体数据的SE(3)即旋转-平移等变性问题展开，体图像数据在众多医疗场景中十分常见。受近期可分离群卷积相关研究的启发，我们设计了一种SE(3)群卷积核，将其拆分为连续SO(3)（旋转）核与空间核。我们通过对均匀SO(3)网格进行采样，来逼近连续场景下的等变性；其中连续SO(3)核通过在同类均匀网格上进行RBF（径向基函数）插值来参数化。我们在体数据医学图像分析任务中验证了所提方法的优势：在具有挑战性的医学分类任务上，我们的SE(3)等变模型性能始终优于常规CNN和正则离散G-CNN，泛化能力显著提升，相比常规CNN，准确率最高提升16.5%。
英文摘要：
Regular group convolutional neural networks (G-CNNs) have been shown to increase model performance and improve equivariance to different geometrical symmetries. This work addresses the problem of SE(3), i.e., roto-translation equivariance, on volumetric data. Volumetric image data is prevalent in many medical settings. Motivated by the recent work on separable group convolutions, we devise a SE(3) group convolution kernel separated into a continuous SO(3) (rotation) kernel and a spatial kernel. We approximate equivariance to the continuous setting by sampling uniform SO(3) grids. Our continuous SO(3) kernel is parameterized via RBF interpolation on similarly uniform grids. We demonstrate the advantages of our approach in volumetric medical image analysis. Our SE(3) equivariant models consistently outperform CNNs and regular discrete G-CNNs on challenging medical classification tasks and show significantly improved generalization capabilities. Our approach achieves up to a 16.5% gain in accuracy over regular CNNs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
