用神经距离场实现高分辨率医学图像分割，保留细节且内存低。
NUDF: Neural Unsigned Distance Fields for high resolution 3D medical image segmentation
- 直接学习无符号距离场，替代传统二值体素图
- 在CT图像上实现接近体素间距精度的左心耳分割
- 适合需要精细3D结构建模的医学影像分析
医学图像分割通常将每个体素标记为解剖结构内部或外部。在原始尺寸下处理图像常导致内存不可承受，而降采样则丢失关键细节。我们提出直接从图像学习神经无符号距离场（NUDF），无需构建连续光滑表面的二值体素网格。NUDF内存开销小，支持高分辨率处理；其连续特性可生成任意拓扑的高分辨率3D网格模型（如开放曲面）。我们在计算机断层扫描（CT）图像上评估左心耳（LAA）分割任务。左心耳形状复杂且高度变异，传统基于离散标签图的方法难以准确表示。使用本方法，可预测捕捉左心耳细节的3D网格模型，并达到与CT体素间距相当的分割精度。
原文摘要 · Abstract (English)
Medical image segmentation is often considered as the task of labelling each pixel or voxel as being inside or outside a given anatomy. Processing the images at their original size and resolution often result in insuperable memory requirements, but downsampling the images leads to a loss of important details. Instead of aiming to represent a smooth and continuous surface in a binary voxel-grid, we propose to learn a Neural Unsigned Distance Field (NUDF) directly from the image. The small memory requirements of NUDF allow for high resolution processing, while the continuous nature of the distance field allows us to create high resolution 3D mesh models of shapes of any topology (i.e. open surfaces). We evaluate our method on the task of left atrial appendage (LAA) segmentation from Computed Tomography (CT) images. The LAA is a complex and highly variable shape, being thus difficult to represent with traditional segmentation methods using discrete labelmaps. With our proposed method, we are able to predict 3D mesh models that capture the details of the LAA and achieve accuracy in the order of the voxel spacing in the CT images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。