Voicu Ioan Paul, Dotta Francesco, Napolitano Antonio, Caulo Massimo, Piccirilli Eleonora, D'Orazio Claudia, Carai Andrea, Miele Evelina, Vinci Maria, Rossi Sabrina, Cacchione Antonella, Vennarini Sabina, Del Baldo Giada, Mastronuzzi Angela, Tomà Paolo, Colafati Giovanna Stefania
Oncological Neuroradiology and Advanced Diagnostics Unit, Bambino Gesù Children's Hospital, IRCCS, 00165 Rome, Italy.
Department of Innovative Technologies in Medicine and Dentistry, University G. d'Annunzio of Chieti-Pescara, 66100 Chieti, Italy.
Cancers (Basel). 2024 Jul 18;16(14):2578. doi: 10.3390/cancers16142578.
: Differentiating pediatric posterior fossa (PF) tumors such as medulloblastoma (MB), ependymoma (EP), and pilocytic astrocytoma (PA) remains relevant, because of important treatment and prognostic implications. Diffusion kurtosis imaging (DKI) has not yet been investigated for discrimination of pediatric PF tumors. Estimating diffusion values from whole-tumor-based (VOI) segmentations may improve diffusion measurement repeatability compared to conventional region-of-interest (ROI) approaches. Our purpose was to compare repeatability between ROI and VOI DKI-derived diffusion measurements and assess DKI accuracy in discriminating among pediatric PF tumors. : We retrospectively analyzed 34 children (M, F, mean age 7.48 years) with PF tumors who underwent preoperative examination on a 3 Tesla magnet, including DKI. For each patient, two neuroradiologists independently segmented the whole solid tumor, the ROI of the area of maximum tumor diameter, and a small 5 mm ROI. The automated analysis pipeline included inter-observer variability, statistical, and machine learning (ML) analyses. We evaluated inter-observer variability with coefficient of variation (COV) and Bland-Altman plots. We estimated DKI metrics accuracy in discriminating among tumor histology with MANOVA analysis. In order to account for class imbalances, we applied SMOTE to balance the dataset. Finally, we performed a Random Forest (RF) machine learning classification analysis based on all DKI metrics from the SMOTE dataset by partitioning 70/30 the training and testing cohort. : Tumor histology included medulloblastoma (15), pilocytic astrocytoma (14), and ependymoma (5). VOI-based measurements presented lower variability than ROI-based measurements across all DKI metrics and were used for the analysis. DKI-derived metrics could accurately discriminate between tumor subtypes (Pillai's trace: < 0.001). SMOTE generated 11 synthetic observations (10 EP and 1 PA), resulting in a balanced dataset with 45 instances (34 original and 11 synthetic). ML analysis yielded an accuracy of 0.928, which correctly predicted all but one lesion in the testing set. : VOI-based measurements presented improved repeatability compared to ROI-based measurements across all diffusion metrics. An ML classification algorithm resulted accurate in discriminating PF tumors on a SMOTE-generated dataset. ML techniques based on DKI-derived metrics are useful for the discrimination of pediatric PF tumors.
鉴别小儿后颅窝（PF）肿瘤，如髓母细胞瘤（MB）、室管膜瘤（EP）和毛细胞星形细胞瘤（PA）仍然具有重要意义，因为这对治疗和预后有重要影响。扩散峰度成像（DKI）尚未用于鉴别小儿PF肿瘤。与传统的感兴趣区（ROI）方法相比，从基于全肿瘤的（VOI）分割中估计扩散值可能会提高扩散测量的可重复性。我们的目的是比较ROI和VOI DKI衍生的扩散测量之间的可重复性，并评估DKI在鉴别小儿PF肿瘤中的准确性。我们回顾性分析了34例患有PF肿瘤的儿童（男、女，平均年龄7.48岁），他们在3特斯拉磁体上进行了术前检查，包括DKI。对于每位患者，两名神经放射科医生独立分割整个实体肿瘤、肿瘤最大直径区域的ROI以及一个5毫米的小ROI。自动分析流程包括观察者间变异性、统计和机器学习（ML）分析。我们用变异系数（COV）和布兰德-奥特曼图评估观察者间变异性。我们用多变量方差分析估计DKI指标在鉴别肿瘤组织学方面的准确性。为了考虑类别不平衡，我们应用SMOTE来平衡数据集。最后，我们基于SMOTE数据集的所有DKI指标进行随机森林（RF）机器学习分类分析，将训练和测试队列按70/30划分。肿瘤组织学包括髓母细胞瘤（15例）、毛细胞星形细胞瘤（14例）和室管膜瘤（5例）。在所有DKI指标上，基于VOI的测量比基于ROI的测量表现出更低的变异性，并用于分析。DKI衍生指标能够准确区分肿瘤亚型（皮莱迹：<0.001）。SMOTE生成了11个合成观察值（10例EP和1例PA），得到了一个包含45个实例的平衡数据集（34个原始实例和11个合成实例）。ML分析的准确率为0.928，在测试集中除一个病变外正确预测了所有病变。与基于ROI的测量相比，基于VOI的测量在所有扩散指标上表现出更好的可重复性。一种ML分类算法在SMOTE生成的数据集上能够准确鉴别PF肿瘤。基于DKI衍生指标的ML技术有助于鉴别小儿PF肿瘤。
