Department of Radiology, Medical Imaging Center, Imam Khomeini Hospital Complex (IKHC), Tehran University of Medical Sciences (TUMS), Tehran, Iran.
Department of Radiology, Medical Imaging Center, Imam Khomeini Hospital Complex (IKHC), Tehran University of Medical Sciences (TUMS), Tehran, Iran.
Eur J Radiol. 2019 Jan;110:203-211. doi: 10.1016/j.ejrad.2018.11.009. Epub 2018 Nov 13.
To propose a computer-assisted method for distinguishing uterine sarcoma from leiomyomas based on perfusion weighted magnetic resonance imaging (PWI).
Forty-two women confirmed to have a total of 60 masses (10 uterine sarcomas and 50 benign leiomyomas) were included. The reference diagnosis was based on postoperative histopathological examination. All women underwent the standard MRI protocol with 3-Tesla MR imager (Magnetom Trio, Siemens, Erlangen, Germany) for assessment of myometrial masses, followed by PWI. For each mass, two regions of interest (ROI) were outlined manually by an experienced radiologist; one (ROI) represented the entire tumor while the other (ROIs) was placed on the area of the lesion with the most marked contrast enhancement. Two additional ROI with diameters similar to ROI (3.0 to 3.1 mm) were placed on psoas muscle (ROI) and myometrium (ROI) in order to provide baselines for comparisons. The obtained ROIs of PWI images were then analyzed using the DCE Tool plug-in (version 2.0SP1) within ClearCanvas (Toronto, Ontario, Canada) framework. The DCE Tool provides seven parameters (K, k, V, IAUC, initial slope, peak, the mean squared error) for modelling contrast uptake within an ROI using the modified Tofts model. Parameters extracted from the ROIs were fed into a decision tree ensemble, which classified the corresponding lesions either as malignant or benign. The leave-one-out cross validation (LOOCV) was utilized to evaluate the performance of the classifier.
None of the parameters extracted from ROI or ROI differed significantly between uterine sarcoma and benign leiomyomas (all p > 0.05). The overall accuracy of 66.7% was obtained by feeding seven parameters extracted from ROI to the classifier. When 21 features extracted from ROI, ROI, and ROI were fed into the classifier an accuracy of 91.7%, sensitivity of 100%, and specificity of 90% were achieved in the optimal operating point of classifier.
Although none of the PWI parameters differed significantly between benign and malignant lesions, when the information provided by the extracted features was aggregated using a machine learning method, a promising discriminative power was obtained. This suggests that the proposed model for combining the PWI parameters is potentially useful for differentiating uterine sarcoma from leiomyomas.
提出一种基于灌注加权磁共振成像（PWI）区分子宫肉瘤和子宫肌瘤的计算机辅助方法。
纳入 42 名经手术病理证实患有 60 个肿块（10 个子宫肉瘤和 50 个良性子宫肌瘤）的女性。参考诊断基于术后组织病理学检查。所有女性均在 3.0T 磁共振成像仪（Siemens，德国 Erlangen 的 Magnetom Trio）上进行标准 MRI 检查，以评估子宫肌层肿块，然后进行 PWI。对于每个肿块，由一位经验丰富的放射科医生手动勾画两个感兴趣区（ROI）；一个（ROI）代表整个肿瘤，另一个（ROIs）放置在病变强化最明显的区域。在两侧腰大肌（ROI）和子宫肌层（ROI）中放置两个直径与 ROI 相似的额外 ROI（3.0 至 3.1mm），以提供基线进行比较。然后使用 ClearCanvas（加拿大安大略省多伦多）框架内的 DCE Tool 插件（版本 2.0SP1）分析 PWI 图像获得的 ROI。DCE Tool 使用改进的 Tofts 模型为 ROI 内的对比摄取建模提供了七个参数（K、k、V、IAUC、初始斜率、峰值、均方误差）。从 ROI 中提取的参数被输入决策树集成，该决策树将相应的病变分类为恶性或良性。采用留一法交叉验证（LOOCV）评估分类器的性能。
从 ROI 或 ROI 中提取的参数在子宫肉瘤和良性子宫肌瘤之间无显著差异（均 p>0.05）。当将从 ROI 中提取的七个参数输入分类器时，得到了 66.7%的整体准确率。当将从 ROI、ROI 和 ROI 中提取的 21 个特征输入分类器时，在分类器的最佳工作点处，获得了 91.7%的准确率、100%的灵敏度和 90%的特异性。
尽管 PWI 参数在良性和恶性病变之间无显著差异，但当使用机器学习方法聚合提取特征提供的信息时，获得了有希望的鉴别能力。这表明，结合 PWI 参数的拟议模型可能有助于区分子宫肉瘤和子宫肌瘤。
