A novel diagnostic method for pituitary adenoma based on magnetic resonance imaging using a convolutional neural network
A novel diagnostic method for pituitary adenoma based on magnetic resonance imaging using a convolutional neural network
复制标题
DOI：
10.1007/s11102-020-01032-4
复制
发表时间：
2020-02-15
期刊：
影响因子：
3.8
通讯作者：
Sun, Jin-Yu
中科院分区：
文献类型：
--
作者：
Qian, Yu;Qiu, Yue;Sun, Jin-Yu
目的建立一个基于卷积神经网络（CNN）的计算机辅助诊断（CAD）系统，用于垂体瘤的诊断。方法选择临床诊断为垂体腺瘤的成人患者（垂体腺瘤组）和无垂体腺瘤的成人患者（对照组）。预处理后，所有MRI数据以8：2的比例随机分为训练或测试数据集，以创建或评估CNN模型。将多个结构相同的CNN分别应用于不同类型的MR图像，并基于不同类型的MR图像的分类结果，使用等权重的多数投票策略进行综合诊断。最后，我们通过准确性、灵敏度、特异性、阳性预测值和F1评分评估了CAD系统的诊断性能。结果我们招募了149名参与者，共796张MR图像，并采用数据增强技术创建了7960张新图像。提出的CAD方法显示出显着的诊断性能，总体准确性为91.02%，敏感性为92.27%，特异性为75.70%，阳性预测值为93.45%，F1评分为92.67%，在单独的MRI类型。在综合诊断中，CAD的准确性、敏感性和特异性分别为96.97%、94.44%和100%。结论CAD系统能根据MRI图像准确诊断垂体瘤。此外，我们将通过增加数据集的数量来改进该CAD系统，并通过外部数据集来评估其性能。
Purpose This study was designed to develop a computer-aided diagnosis (CAD) system based on a convolutional neural network (CNN) to diagnose patients with pituitary tumors. Methods We included adult patients clinically diagnosed with pituitary adenoma (pituitary adenoma group), or adult individuals without pituitary adenoma (control group). After pre-processing, all the MRI data were randomly divided into training or testing datasets in a ratio of 8:2 to create or evaluate the CNN model. Multiple CNNs with the same structure were applied for different types of MR images respectively, and a comprehensive diagnosis was performed based on the classification results of different types of MR images using an equal-weighted majority voting strategy. Finally, we assessed the diagnostic performance of the CAD system by accuracy, sensitivity, specificity, positive predictive value, and F1 score. Results We enrolled 149 participants with 796 MR images and adopted the data augmentation technology to create 7960 new images. The proposed CAD method showed remarkable diagnostic performance with an overall accuracy of 91.02%, sensitivity of 92.27%, specificity of 75.70%, positive predictive value of 93.45%, and F1-score of 92.67% in separate MRI type. In the comprehensive diagnosis, the CAD achieved better performance with accuracy, sensitivity, and specificity of 96.97%, 94.44%, and 100%, respectively. Conclusion The CAD system could accurately diagnose patients with pituitary tumors based on MR images. Further, we will improve this CAD system by augmenting the amount of dataset and evaluate its performance by external dataset.