Liberini Virginia, De Santi Bruno, Rampado Osvaldo, Gallio Elena, Dionisi Beatrice, Ceci Francesco, Polverari Giulia, Thuillier Philippe, Molinari Filippo, Deandreis Désirée
Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, Corso Dogliotti 14, 10126, Turin, Italy.
Biolab, Department of Electronics and Telecomunications, Politecnico di Torino, Turin, Italy.
EJNMMI Phys. 2021 Feb 27;8(1):21. doi: 10.1186/s40658-021-00367-6.
To identify the impact of segmentation methods and intensity discretization on radiomic features (RFs) extraction from Ga-DOTA-TOC PET images in patients with neuroendocrine tumors.
Forty-nine patients were retrospectively analyzed. Tumor contouring was performed manually by four different operators and with a semi-automatic edge-based segmentation (SAEB) algorithm. Three SUV fixed thresholds (20, 30, 40%) were applied. Fifty-one RFs were extracted applying two different intensity rescale factors for gray-level discretization: one absolute (AR60 = SUV from 0 to 60) and one relative (RR = min-max of the VOI SUV). Dice similarity coefficient (DSC) was calculated to quantify segmentation agreement between different segmentation methods. The impact of segmentation and discretization on RFs was assessed by intra-class correlation coefficients (ICC) and the coefficient of variance (COV). The RFs' correlation with volume and SUV was analyzed by calculating Pearson's correlation coefficients.
DSC mean value was 0.75 ± 0.11 (0.45-0.92) between SAEB and operators and 0.78 ± 0.09 (0.36-0.97), among the four manual segmentations. The study showed high robustness (ICC > 0.9): (a) in 64.7% of RFs for segmentation methods using AR60, improved by applying SUV threshold of 40% (86.5%); (b) in 50.9% of RFs for different SUV thresholds using AR60; and (c) in 37% of RFs for discretization settings using different segmentation methods. Several RFs were not correlated with volume and SUV.
RFs robustness to manual segmentation resulted higher in NET Ga-DOTA-TOC images compared to F-FDG PET/CT images. Forty percent SUV thresholds yield superior RFs stability among operators, however leading to a possible loss of biological information. SAEB segmentation appears to be an optimal alternative to manual segmentation, but further validations are needed. Finally, discretization settings highly impacted on RFs robustness and should always be stated.
确定分割方法和强度离散化对神经内分泌肿瘤患者Ga-DOTA-TOC PET图像中放射组学特征（RFs）提取的影响。
对49例患者进行回顾性分析。由四名不同的操作人员手动进行肿瘤轮廓勾画，并使用基于边缘的半自动分割（SAEB）算法。应用三个SUV固定阈值（20%、30%、40%）。应用两种不同的强度重缩放因子进行灰度离散化，提取51个RFs：一个是绝对的（AR60 = SUV范围为0至60），另一个是相对的（RR = 感兴趣区SUV的最小值-最大值）。计算骰子相似系数（DSC）以量化不同分割方法之间的分割一致性。通过组内相关系数（ICC）和变异系数（COV）评估分割和离散化对RFs的影响。通过计算Pearson相关系数分析RFs与体积和SUV的相关性。
SAEB与操作人员之间的DSC平均值为0.75±0.11（0.45 - 0.92），四种手动分割之间的DSC平均值为0.78±0.09（0.36 - 0.97）。研究显示出高稳健性（ICC > 0.9）：（a）在使用AR60的分割方法中，64.7%的RFs通过应用40%的SUV阈值得到改善（86.5%）；（b）在使用AR60的不同SUV阈值的情况下，50.9%的RFs；（c）在使用不同分割方法的离散化设置中，37%的RFs。几个RFs与体积和SUV不相关。
与F-FDG PET/CT图像相比，NET Ga-DOTA-TOC图像中RFs对手动分割的稳健性更高。40%的SUV阈值在操作人员之间产生了更高的RFs稳定性，但可能导致生物信息丢失。SAEB分割似乎是手动分割的最佳替代方法，但需要进一步验证。最后，离散化设置对RFs稳健性有很大影响，应始终说明。
