Ghosh Adarsh, Li Hailong, Towbin Alexander, Turpin Brian, Trout Andrew
Cincinnati Children's Hospital Medical Center, Cincinnati, USA.
Nationwide Children's Hospital, 700 Children's Drive, Columbus, OH, 43205, USA.
Pediatr Radiol. 2025 Mar 18. doi: 10.1007/s00247-025-06205-6.
Rhabdomyosarcomas are the most common soft tissue sarcoma in children. While treatment outcomes have improved, risk-based therapy classification relies on staging and tumor subtypes for therapeutic planning.
This study investigated the utility of T2-weighted MR radiomics features and machine learning models in identifying the presence of distant metastasis and alveolar histological subtypes at baseline imaging in children diagnosed with rhabdomyosarcoma.
This retrospective cross-sectional study utilized MRIs from 86 patients, 49 (median age (IQR) 59 months (37-161), alveolar subtype=15, distant metastasis=9) of whom had been imaged at outside imaging centers (training set); and 37 (median age 52 months (24-164), alveolar subtype=14, distant metastasis=8) of whom were imaged at our institution (holdout validation set). Radiomic features were extracted from T2-weighted images. We selected features that demonstrated intra-scan repeatability and used maximum relevance and minimum redundancy supervised feature selection to identify the 50 most important features. Lasso logistic regression and support vector machine (SVM) classifiers were trained to predict binary outcomes. The median of all predictions for a given patient was used as patient-level predictions. DeLong's test compared the area under the receiver operating characteristic curves (AUC). Cut-offs obtained by maximizing the Youden index were evaluated on an external validation set, and accuracy metrics were reported.
On the validation set, the Lasso and SVM classifiers obtained patient level AUCs of 0.76 (95% CI 0.59-0.94) and 0.73 (0.54-0.92), respectively, in predicting alveolar subtype, with the Lasso regressor obtaining 71.4% (41.9-91.6) sensitivity and 60.9% (38.5-80.3) specificity. When predicting the presence of distant metastasis, the Lasso and SVM classifier had AUCs of 0.81 (0.67-0.95) and 0.77 (0.58-0.97), respectively. There were no differences between model performance (P>0.05). A total of 12 and 18 features had nonzero coefficients in the Lasso regressors for predicting alveolar subtype and tumor metastasis, respectively.
MRI radiomics from baseline T2-weighted MRI demonstrated potential in predicting alveolar subtype and distant metastatic disease at presentation. Larger studies are needed to explore multinomial multiclass models for better prognostication of pediatric rhabdomyosarcomas.
横纹肌肉瘤是儿童中最常见的软组织肉瘤。尽管治疗效果有所改善，但基于风险的治疗分类依赖于分期和肿瘤亚型来制定治疗方案。
本研究调查了T2加权磁共振成像（MRI）的影像组学特征和机器学习模型在诊断为横纹肌肉瘤的儿童基线成像中识别远处转移和肺泡组织学亚型的效用。
这项回顾性横断面研究使用了86例患者的MRI，其中49例（中位年龄（四分位间距）59个月（37 - 161个月），肺泡亚型 = 15例，远处转移 = 9例）在外部影像中心进行了成像（训练集）；37例（中位年龄52个月（24 - 164个月），肺泡亚型 = 14例，远处转移 = 8例）在我们机构进行了成像（保留验证集）。从T2加权图像中提取影像组学特征。我们选择了具有扫描内可重复性的特征，并使用最大相关性和最小冗余监督特征选择来识别50个最重要的特征。训练套索逻辑回归和支持向量机（SVM）分类器以预测二元结果。将给定患者的所有预测中位数用作患者水平的预测。德龙检验比较了受试者操作特征曲线（AUC）下的面积。在外部验证集上评估通过最大化约登指数获得的截断值，并报告准确性指标。
在验证集上，套索和SVM分类器在预测肺泡亚型时，患者水平的AUC分别为0.76（95%可信区间0.59 - 0.94）和0.73（0.54 - 0.92），套索回归器的灵敏度为71.4%（41.9 - 91.6），特异性为60.9%（38.5 - 80.3）。在预测远处转移的存在时，套索和SVM分类器的AUC分别为0.81（0.67 - 0.95）和0.77（0.58 - 0.97）。模型性能之间没有差异（P>0.05）。在预测肺泡亚型和肿瘤转移的套索回归器中，分别有12个和18个特征具有非零系数。
基线T2加权MRI的MRI影像组学在预测肺泡亚型和初诊时的远处转移疾病方面显示出潜力。需要更大规模的研究来探索多项多类模型，以更好地预测儿童横纹肌肉瘤的预后。
