Radiology Department, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, HaiNing Rd.100, Shanghai, 200080, China.
Radiology Department, RuiJin Hospital, Shanghai Jiao Tong University School of Medicine, RuiJin No.2 Rd.197, Shanghai, 200025, China.
Eur Radiol. 2019 Oct;29(10):5441-5451. doi: 10.1007/s00330-019-06082-2. Epub 2019 Mar 11.
To predict the local recurrence of giant cell bone tumors (GCTB) on MR features and the clinical characteristics after curettage using a deep convolutional neural network (CNN).
MR images were collected from 56 patients with histopathologically confirmed GCTB after curettage who were followed up for 5.8 years (range, 2.0 to 9.5 years). The inception v3 CNN architecture was fine-tuned by two categories of the MR datasets (recurrent and non-recurrent GCTB) obtained through data augmentation and was validated using fourfold cross-validation to evaluate its generalization ability. Twenty-eight cases (50%) were chosen as the training dataset for the CNN and four radiologists, while the remaining 28 cases (50%) were used as the test dataset. A binary logistic regression model was established to predict recurrent GCTB by combining the CNN prediction and patient features (age and tumor location). Accuracy and sensitivity were used to evaluate the prediction performance.
When comparing the CNN, CNN regression, and radiologists, the accuracies of the CNN and CNN regression models were 75.5% (95% CI 55.1 to 89.3%) and 78.6% (59.0 to 91.7%), respectively, which were higher than the 64.3% (44.1 to 81.4%) accuracy of the radiologists. The sensitivities were 85.7% (42.1 to 99.6%) and 87.5% (47.3 to 99.7%), respectively, which were higher than the 58.3% (27.7 to 84.8%) sensitivity of the radiologists (p < 0.05).
The CNN has the potential to predict recurrent GCTB after curettage. A binary regression model combined with patient characteristics improves its prediction accuracy.
• Convolutional neural network (CNN) can be trained successfully on a limited number of pre-surgery MR images, by fine-tuning a pre-trained CNN architecture. • CNN has an accuracy of 75.5% to predict post-surgery recurrence of giant cell tumors of bone, which surpasses the 64.3% accuracy of human observation. • A binary logistic regression model combining CNN prediction rate, patient age, and tumor location improves the accuracy to predict post-surgery recurrence of giant cell bone tumors to 78.6%.
利用深度卷积神经网络（CNN）预测经刮除术后巨细胞瘤（GCTB）的局部复发，并预测复发的临床特征。
收集 56 例经病理证实的 GCTB 患者的 MRI 图像，这些患者在接受刮除术后平均随访 5.8 年（范围为 2.0-9.5 年）。通过数据扩充，对 inception v3 CNN 架构进行微调，并通过四折交叉验证进行验证，以评估其泛化能力。将 28 例（50%）患者作为 CNN 的训练数据集，4 位放射科医生和另外 28 例（50%）患者作为测试数据集。建立一个二元逻辑回归模型，通过结合 CNN 预测和患者特征（年龄和肿瘤位置）来预测 GCTB 的复发。使用准确性和敏感度来评估预测性能。
与 CNN、CNN 回归和放射科医生比较，CNN 和 CNN 回归模型的准确性分别为 75.5%（95%CI 55.1-89.3%）和 78.6%（59.0-91.7%），均高于放射科医生的 64.3%（44.1-81.4%）。敏感度分别为 85.7%（42.1-99.6%）和 87.5%（47.3-99.7%），均高于放射科医生的 58.3%（27.7-84.8%）（p<0.05）。
CNN 有潜力预测 GCTB 经刮除术后的复发情况。结合患者特征的二元回归模型可提高其预测准确性。
