基于迭代切片传播的椎体弱监督分割
Weakly Supervised Segmentation of Vertebral Bodies with Iterative Slice-propagation
AI总结：
提出弱监督迭代脊柱分割方法WISS，仅用单切片四个角点弱标签实现椎体自动体积分割，在公开数据集上取得较高Dice系数并大幅节省标注成本。
摘要：
椎体（VB）分割是迈向脊柱疾病医学视觉诊断的重要初步步骤。然而，以往的大多数工作需要像素/体素级的强监督，这对专家而言标注成本高昂、繁琐且耗时。本文提出了一种弱监督迭代脊柱分割（WISS）方法，该方法仅利用单个矢状切片上的四个角点地标弱标签，即可实现从CT图像中对VBs进行自动体积分割。WISS首先以迭代自训练方式在标注的矢状切片上分割VBs。该自训练方法在训练集的训练与标签优化之间交替进行。随后，WISS通过切片传播方法逐层分割整个VBs，以获得体积分割结果。我们在一个私有脊柱转移瘤CT数据集和一个公开腰椎CT数据集上评估了WISS的性能。在第一个数据集上，WISS在两种不同的骨干网络下均取得了显著提升。在第二个数据集上，WISS在正中矢状切片和3D CT体积上分别取得了$91.7\%$和$83.7\%$的Dice系数，节省了大量标注成本，且仅牺牲了少许分割性能。
英文摘要：
Vertebral body (VB) segmentation is an important preliminary step towards medical visual diagnosis for spinal diseases. However, most previous works require pixel/voxel-wise strong supervisions, which is expensive, tedious and time-consuming for experts to annotate. In this paper, we propose a Weakly supervised Iterative Spinal Segmentation (WISS) method leveraging only four corner landmark weak labels on a single sagittal slice to achieve automatic volumetric segmentation from CT images for VBs. WISS first segments VBs on an annotated sagittal slice in an iterative self-training manner. This self-training method alternates between training and refining labels in the training set. Then WISS proceeds to segment the whole VBs slice by slice with a slice-propagation method to obtain volumetric segmentations. We evaluate the performance of WISS on a private spinal metastases CT dataset and the public lumbar CT dataset. On the first dataset, WISS achieves distinct improvements with regard to two different backbones. For the second dataset, WISS achieves dice coefficients of $91.7\%$ and $83.7\%$ for mid-sagittal slices and 3D CT volumes, respectively, saving a lot of labeling costs and only sacrificing a little segmentation performance.
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。
