Benhabib Hadas, Brandenberger Daniel, Lajkosz Katherine, Demicco Elizabeth G, Tsoi Kim M, Wunder Jay S, Ferguson Peter C, Griffin Anthony M, Naraghi Ali, Haider Masoom A, White Lawrence M
Department of Medical Imaging, University of Toronto, Toronto, Ontario, Canada.
Joint Department of Medical Imaging, University Health Network, Sinai Health System, Women's College Hospital, Mount Sinai Hospital, Toronto, Ontario, Canada.
J Magn Reson Imaging. 2025 Jun;61(6):2630-2641. doi: 10.1002/jmri.29691. Epub 2025 Jan 22.
Differentiation of benign myxomas and malignant myxoid sarcomas can be difficult with an overlapping spectrum of morphologic MR findings.
To assess the diagnostic utility of MRI radiomics in the differentiation of musculoskeletal myxomas and myxoid sarcomas.
Retrospective.
A total of 523 patients were included; histologically proven myxomas (N = 201) and myxoid sarcomas (N = 322), randomly divided (70:30) into training:test subsets.
SEQUENCE/FIELD STRENGTH: T1-weighted (T1W), T2-weighted fat-suppressed (fluid-sensitive), and T1-weighted post-contrast (T1W + C) sequences at 1.0 T, 1.5 T, or 3.0 T.
Seven semantic (qualitative) tumor features were assessed in each case. Manual 3D tumor segmentations performed with radiomics features extracted from T1W, fluid-sensitive, and T1W + C acquisitions. Models were constructed based on radiomic features from individual sequences and from their combination, both with and without the addition of qualitative tumor features.
Intraclass correlation evaluated in 60 cases segmented by three readers. Features with intraclass correlation <0.7 excluded from further analysis. Boruta feature selection and Random Forest modeling performed using the training-dataset, with resultant models used to assess class discrimination (myxoma vs. myxoid sarcoma) in the test dataset. Radiomics score defined as probability class = myxoma. Logistic regression modeling employed to estimate performance of the radiomics score. Area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance, and DeLong's test to assess performance between constructed models. A P-value <0.05 was considered significant.
Four qualitative semantic features showed significant predictive power in class discrimination. Radiomic models demonstrated excellent differentiation of myxomas from myxoid sarcomas: AUC of 0.9271 (T1W), 0.9049 (fluid-sensitive), and 0.9179 (T1W + C). Incorporation of multiparametric data or semantic features did not significantly improve model performance (P ≥ 0.08) compared to radiomic models derived from any individual MRI sequence alone.
MRI radiomics appears to be accurate in the differentiation of myxomas from myxoid sarcomas. Classification performance did not improve when incorporating qualitative features or multiparametric imaging data.
Accurately distinguishing between benign soft tissue myxomas and malignant myxoid sarcomas is essential for guiding appropriate management but remains challenging with conventional MRI interpretation. This study utilized radiomics, a method that extracts quantitative mathematically derived features from images, to develop predictive models based on routine MRI examination. Analyzing over 500 cases, MRI radiomics demonstrated excellent diagnostic accuracy in differentiating between benign myxomas and malignant myxoid sarcomas, highlighting the potential of the technique, as a powerful non-invasive tool that could complement current diagnostic approaches, and enhance clinical decision-making in patients with soft tissue myxoid tumors of the musculoskeletal system.
3 TECHNICAL EFFICACY: Stage 2.
良性黏液瘤和恶性黏液样肉瘤的鉴别可能存在困难，因为其形态学磁共振成像（MR）表现存在重叠。
评估MRI影像组学在肌肉骨骼黏液瘤和黏液样肉瘤鉴别诊断中的应用价值。
回顾性研究。
共纳入523例患者，包括经组织学证实的黏液瘤（N = 201）和黏液样肉瘤（N = 322），随机分为训练集和测试集，比例为70:30。
序列/场强：1.0T、1.5T或3.0T场强下的T1加权（T1W）、T2加权脂肪抑制（液体敏感）及T1加权增强后（T1W + C）序列。
对每个病例评估7个语义（定性）肿瘤特征。通过从T1W、液体敏感序列及T1W + C采集图像中提取影像组学特征，进行手动三维肿瘤分割。基于单个序列及其组合的影像组学特征构建模型，同时考虑是否添加定性肿瘤特征。
对60例由三位阅片者分割的病例进行组内相关分析。组内相关性<0.7的特征排除在进一步分析之外。使用训练数据集进行Boruta特征选择和随机森林建模，所得模型用于评估测试数据集中的类别区分（黏液瘤与黏液样肉瘤）。影像组学评分定义为类别为黏液瘤的概率。采用逻辑回归建模评估影像组学评分的性能。使用受试者工作特征曲线下面积（AUC）评估诊断性能，使用DeLong检验评估构建模型之间的性能差异。P值<0.05认为具有统计学意义。
四个定性语义特征在类别区分中显示出显著的预测能力。影像组学模型在区分黏液瘤和黏液样肉瘤方面表现出色：T1W序列的AUC为0.9271，液体敏感序列的AUC为0.9049，T1W + C序列的AUC为0.9179。与仅从任何单个MRI序列得出的影像组学模型相比，纳入多参数数据或语义特征并未显著提高模型性能（P≥0.08）。
MRI影像组学在区分黏液瘤和黏液样肉瘤方面似乎是准确的。纳入定性特征或多参数成像数据时，分类性能并未改善。
准确区分良性软组织黏液瘤和恶性黏液样肉瘤对于指导恰当治疗至关重要，但传统MRI解读仍具有挑战性。本研究利用影像组学，即一种从图像中提取定量数学衍生特征的方法，基于常规MRI检查开发预测模型。通过分析500多例病例，MRI影像组学在区分良性黏液瘤和恶性黏液样肉瘤方面显示出出色的诊断准确性，凸显了该技术作为一种强大的非侵入性工具的潜力，可补充当前诊断方法，并改善肌肉骨骼系统软组织黏液样肿瘤患者的临床决策。
3级 技术效能：2级
