Ngan Esther, Mullikin Dolores, Theruvath Ashok J, Annapragada Ananth V, Ghaghada Ketan B, Heczey Andras A, Starosolski Zbigniew A
Department of Radiology, Baylor College of Medicine, Houston, TX 77030, USA.
Mary Bridge Children's Hospital, Tacoma, WA 98403, USA.
Cancers (Basel). 2025 Aug 6;17(15):2586. doi: 10.3390/cancers17152586.
: Osteosarcoma (OS) is the most common malignant bone tumor in children and adolescents; the survival rate is as low as 24%. Accurate prediction of clinical outcomes remains a challenge due to tumor heterogeneity and the complexity of pediatric cases. This study aims to improve predictions of progressive disease, therapy response, relapse, and survival in pediatric OS using MRI-based radiomics and machine learning methods. : Pre-treatment contrast-enhanced coronal T1-weighted MR scans were collected from 63 pediatric OS patients, with an additional nine external cases used for validation. Three strategies were considered for target region segmentation (whole-tumor, tumor sampling, and bone/soft tissue) and used for MRI-based radiomics. These were then combined with clinical features to predict OS clinical outcomes. : The mean age of OS patients was 11.8 ± 3.5 years. Most tumors were located in the femur (65%). Osteoblastic subtype was the most common histological classification (79%). The majority of OS patients (79%) did not have evidence of metastasis at diagnosis. Progressive disease occurred in 27% of patients, 59% of patients showed adequate therapy response, 25% experienced relapse after therapy, and 30% died from OS. Classification models based on bone/soft tissue segmentation generally performed the best, with certain clinical features improving performance, especially for therapy response and mortality. The top performing classifier in each outcome achieved 0.94-1.0 validation ROC AUC and 0.63-1.0 testing ROC AUC, while those without radiomic features (RFs) generally performed suboptimally. : This study demonstrates the strong predictive capabilities of MRI-based radiomics and multi-region segmentations for predicting clinical outcomes in pediatric OS.
骨肉瘤（OS）是儿童和青少年中最常见的恶性骨肿瘤；生存率低至24%。由于肿瘤异质性和儿科病例的复杂性，准确预测临床结果仍然是一项挑战。本研究旨在使用基于MRI的放射组学和机器学习方法改善对儿童骨肉瘤进展性疾病、治疗反应、复发和生存的预测。：收集了63例儿童骨肉瘤患者治疗前的冠状位对比增强T1加权磁共振成像扫描，另外9例外部病例用于验证。考虑了三种目标区域分割策略（全肿瘤、肿瘤取样和骨/软组织）并用于基于MRI的放射组学。然后将这些与临床特征相结合，以预测骨肉瘤的临床结果。：骨肉瘤患者的平均年龄为11.8±3.5岁。大多数肿瘤位于股骨（65%）。成骨细胞亚型是最常见的组织学分类（79%）。大多数骨肉瘤患者（79%）在诊断时没有转移证据。27%的患者发生进展性疾病，59%的患者显示出充分的治疗反应，25%的患者在治疗后复发，30%的患者死于骨肉瘤。基于骨/软组织分割的分类模型通常表现最佳，某些临床特征可提高性能，尤其是对于治疗反应和死亡率。每个结果中表现最佳的分类器在验证时的ROC AUC为0.94 - 1.0，测试时的ROC AUC为0.63 - 1.0，而没有放射组学特征（RFs）的分类器通常表现欠佳。：本研究证明了基于MRI的放射组学和多区域分割在预测儿童骨肉瘤临床结果方面具有强大的预测能力。
