Ri.MED Foundation, via Bandiera 11, 90133, Palermo, Italy.
Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, USA.
Comput Biol Med. 2020 May;120:103701. doi: 10.1016/j.compbiomed.2020.103701. Epub 2020 Mar 16.
Delineation of tumours in Positron Emission Tomography (PET) plays a crucial role in accurate diagnosis and radiotherapy treatment planning. In this context, it is of outmost importance to devise efficient and operator-independent segmentation algorithms capable of reconstructing the tumour three-dimensional (3D) shape. In previous work, we proposed a system for 3D tumour delineation on PET data (expressed in terms of Standardized Uptake Value - SUV), based on a two-step approach. Step 1 identified the slice enclosing the maximum SUV and generated a rough contour surrounding it. Such contour was then used to initialize step 2, where the 3D shape of the tumour was obtained by separately segmenting 2D PET slices, leveraging the slice-by-slice marching approach. Additionally, we combined active contours and machine learning components to improve performance. Despite its success, the slice marching approach poses unnecessary limitations that are naturally removed by performing the segmentation directly in 3D. In this paper, we migrate our system into 3D. In particular, the segmentation in step 2 is now performed by evolving an active surface directly in the 3D space. The key points of such an advancement are that it performs the shape reconstruction on the whole stack of slices simultaneously, naturally leveraging cross-slice information that could not be exploited before. Additionally, it does not require any specific stopping condition, as the active surface naturally reaches a stable topology once convergence is achieved. Performance of this fully 3D approach is evaluated on the same dataset discussed in our previous work, which comprises fifty PET scans of lung, head and neck, and brain tumours. The results have confirmed that a benefit is indeed achieved in practice for all investigated anatomical districts, both quantitatively, through a set of commonly used quality indicators (dice similarity coefficient >87.66%, Hausdorff distance < 1.48 voxel and Mahalanobis distance < 0.82 voxel), and qualitatively in terms of Likert score (>3 in 54% of the tumours).
在正电子发射断层扫描（PET）中对肿瘤进行描绘对于准确诊断和放射治疗计划至关重要。在这种情况下，设计能够重建肿瘤三维（3D）形状的高效且不依赖于操作人员的分割算法是非常重要的。在之前的工作中，我们提出了一种基于两步法的 PET 数据（以标准化摄取值-SUV 表示）三维肿瘤描绘系统。第 1 步确定包含最大 SUV 的切片，并生成围绕其的粗略轮廓。然后，使用此轮廓初始化第 2 步，通过分别对 2D PET 切片进行分割，利用逐片前进的方法获得肿瘤的 3D 形状。此外，我们还结合了主动轮廓和机器学习组件以提高性能。尽管该方法取得了成功，但逐片前进的方法存在不必要的限制，而直接在 3D 中进行分割可以自然地消除这些限制。在本文中，我们将系统迁移到 3D 中。特别是，第 2 步中的分割现在是通过在 3D 空间中直接演化主动表面来完成的。这种改进的关键点在于它可以同时对整个切片堆栈进行形状重建，自然利用了以前无法利用的跨切片信息。此外，它不需要任何特定的停止条件，因为一旦达到收敛，主动表面自然会达到稳定的拓扑结构。这种完全 3D 方法的性能是在我们之前工作中讨论的同一个数据集上进行评估的，该数据集包括五十个肺部、头颈部和脑部肿瘤的 PET 扫描。结果证实，对于所有研究的解剖区域，实际上都可以从实践中获得收益，这不仅体现在常用质量指标（骰子相似系数>87.66%，Hausdorff 距离<1.48 体素和马哈拉诺比斯距离<0.82 体素）上，而且在利克特评分（>3 分的肿瘤占 54%）上也是如此。
