Xiong Zicheng, Qiu Jun, Liang Quan, Jiang Jingcheng, Zhao Kai, Chang Hui, Lv Cheng, Zhang Wanjun, Li Boyuan, Ye Jingbo, Li Shangbo, Peng Shuo, Sun Changrong, Chen Shengbo, Long Dazhi, Shu Xujun
School of Computer and Information Engineering and Henan Engineering Research Center of Intelligent Technology and Application, Henan University, Kaifeng, China.
Department of Critical Care Medicine, The Second People's Hospital of Yibin, Yibin, China.
Quant Imaging Med Surg. 2024 Aug 1;14(8):5762-5773. doi: 10.21037/qims-24-380. Epub 2024 Jul 16.
High-grade gliomas (HGG) and solitary brain metastases (SBM) are two common types of brain tumors in middle-aged and elderly patients. HGG and SBM display a high degree of similarity on magnetic resonance imaging (MRI) images. Consequently, differential diagnosis using preoperative MRI remains challenging. This study developed deep learning models that used pre-operative T1-weighted contrast-enhanced (T1CE) MRI images to differentiate between HGG and SBM before surgery.
By comparing various convolutional neural network models using T1CE image data from The First Medical Center of the Chinese PLA General Hospital and The Second People's Hospital of Yibin (Data collection for this study spanned from January 2016 to December 2023), it was confirmed that the GoogLeNet model exhibited the highest discriminative performance. Additionally, we evaluated the individual impact of the tumoral core and peritumoral edema regions on the network's predictive performance. Finally, we adopted a slice-based voting method to assess the accuracy of the validation dataset and evaluated patient prediction performance on an additional test dataset.
The GoogLeNet model, in a five-fold cross-validation using multi-plane T1CE slices (axial, coronal, and sagittal) from 180 patients, achieved an average patient accuracy of 92.78%, a sensitivity of 95.56%, and a specificity of 90.00%. Moreover, on an external test set of 29 patients, the model achieved an accuracy of 89.66%, a sensitivity of 90.91%, and a specificity of 83.33%, with an area under the curve of 0.939 [95% confidence interval (CI): 0.842-1.000].
GoogLeNet performed better than previous methods at differentiating HGG from SBM, even for core and peritumoral edema in both. HGG and SBM could be fast screened using this end-to-end approach, improving workflow for both tumor treatments.
高级别胶质瘤（HGG）和孤立性脑转移瘤（SBM）是中老年患者中两种常见的脑肿瘤类型。HGG和SBM在磁共振成像（MRI）图像上表现出高度相似性。因此，使用术前MRI进行鉴别诊断仍然具有挑战性。本研究开发了深度学习模型，利用术前T1加权对比增强（T1CE）MRI图像在手术前区分HGG和SBM。
通过比较使用中国人民解放军总医院第一医学中心和宜宾市第二人民医院的T1CE图像数据的各种卷积神经网络模型（本研究的数据收集时间跨度为2016年1月至2023年12月），证实GoogLeNet模型具有最高的判别性能。此外，我们评估了肿瘤核心区和瘤周水肿区对网络预测性能的个体影响。最后，我们采用基于切片的投票方法评估验证数据集的准确性，并在另一个测试数据集上评估患者预测性能。
在使用来自180例患者的多平面T1CE切片（轴位、冠状位和矢状位）进行的五折交叉验证中，GoogLeNet模型的平均患者准确率为92.78%，敏感性为95.56%，特异性为90.00%。此外，在29例患者的外部测试集上，该模型的准确率为89.66%，敏感性为90.91%，特异性为83.33%，曲线下面积为0.939 [95%置信区间（CI）：0.842 - 1.000]。
在区分HGG和SBM方面，GoogLeNet的表现优于先前的方法，即使对于两者的肿瘤核心区和瘤周水肿也是如此。使用这种端到端方法可以快速筛查HGG和SBM，改善两种肿瘤治疗的工作流程。
