Department of Radiology, Baoji Center Hospital, Baoji, 721008, Shaanxi, China; Department of Radiology, Baoji Hi-Tech People's Hospital, Baoji, 721013, Shaanxi, China.
Department of Radiology, Baoji Center Hospital, Baoji, 721008, Shaanxi, China.
Clin Radiol. 2020 Jan;75(1):64-69. doi: 10.1016/j.crad.2019.08.008. Epub 2019 Sep 28.
To realise the automated prediction of soft-tissue sarcoma (STS) grading and lung metastasis based on computed tomography (CT), T1-weighted (T1W) magnetic resonance imaging (MRI), and fat-suppressed T2-weighted MRI (FST2W) via the convolutional neural networks (CNN) model.
MRI and CT images of 51 patients diagnosed with STS were analysed retrospectively. The patients could be divided into three groups based on disease grading: high-grade group (n=28), intermediate-grade group (n=15), low-grade group (n=8). Among these patients, 32 had lung metastasis, while the remaining 19 had no lung metastasis. The data were divided into the training, validation, and testing groups according to the ratio of 5:2:3. The receiver operating characteristic (ROC) curves and accuracy values were acquired using the testing dataset to evaluate the performance of the CNN model.
For STS grading, the accuracy of the T1W, FST2W, CT, and the fusion of T1W and FST2W testing data were 0.86, 0.89, 0.86, and 0.85, respectively. In addition, Area Under Curve (AUC) were 0.96, 0.97, 0.97, and 0.94 respectively. For the prediction of lung metastasis, the accuracy of the T1W, FST2W, CT, and the fusion of T1W and FST2W test data were 0.92, 0.93, 0.88, and 0.91, respectively. The corresponding AUC values were 0.97, 0.96, 0.95, and 0.95, respectively. FST2W MRI performed best for predicting STS grading and lung metastasis.
MRI and CT images combined with the CNN model can be useful for making predictions regarding STS grading and lung metastasis, thus providing help for patient diagnosis and treatment.
通过卷积神经网络（CNN）模型，实现基于计算机断层扫描（CT）、T1 加权（T1W）磁共振成像（MRI）和脂肪抑制 T2 加权 MRI（FST2W）的软组织肉瘤（STS）分级和肺转移的自动预测。
回顾性分析 51 例经病理证实的 STS 患者的 MRI 和 CT 图像。根据疾病分级，将患者分为三组：高级组（n=28）、中级组（n=15）和低级组（n=8）。其中 32 例有肺转移，19 例无肺转移。根据 5:2:3 的比例将数据分为训练组、验证组和测试组。使用测试数据集获得受试者工作特征（ROC）曲线和准确率值，以评估 CNN 模型的性能。
对于 STS 分级，T1W、FST2W、CT 和 T1W 与 FST2W 融合检测数据的准确率分别为 0.86、0.89、0.86 和 0.85，曲线下面积（AUC）分别为 0.96、0.97、0.97 和 0.94。对于肺转移的预测，T1W、FST2W、CT 和 T1W 与 FST2W 融合检测数据的准确率分别为 0.92、0.93、0.88 和 0.91，AUC 值分别为 0.97、0.96、0.95 和 0.95。FST2W MRI 对 STS 分级和肺转移的预测效果最佳。
MRI 和 CT 图像结合 CNN 模型可用于预测 STS 分级和肺转移，为患者的诊断和治疗提供帮助。
