带有语义特征得分的肺结节检测方法

Pulmonary nodule detection method with semantic feature score

针对传统肺结节检测智能算法仅预测结节的位置,缺少医生临床习惯使用的"分叶""纹理""毛刺"等直观的语义解释的问题,提出一种带有语义特征得分的肺结节检测方法。将Faster R-CNN的区域建议网络(RPN)中嵌入细致度、内部结构、分叶、毛刺、边界、钙化、圆度、纹理等8个医生常用的语义特征,设计新的锚盒机制,增加全连接网络实现语义特征的回归学习,将其作为辅助信息结合Faster R-CNN训练实现肺结节检测和语义预测的联合学习。LIDC/IDRI数据集上的测试结果显示,所提方法的肺结节定位的精度为91.2%,肺结节良恶性分类的准确率、敏感性、特异性分别为81%、91.2%、70.8%。在8个语义特征得分上,医生间的差异为0.59±0.80(平均绝对误差±标准差),所提算法预测的语义解释和医生的差异为0.62±1.03,预测结果接近医生个体的差异。修改后的网络达到了较好的检测精度和语义特征预测,方便医生对机器检测结果的理解和临床解释。

Since the results of existing intelligent algorithms of pulmonary nodule detection only predict the positions of nodules and cannot give semantical interpretations which are well known to doctors in clinical diagnosis,such as"lobulation","texture"and"spiculation",a pulmonary nodule detection method with semantic feature score was proposed.Eight semantic features-subtlety,internal structure,lobulation,spiculation,margin,calcification,sphericity and texture were embedded into the Region Proposal Network(RPN)of Faster R-CNN,a new anchor box mechanism was designed,a fully connected network was added to realize the regression learning of semantic features,and the semantic scores were used as auxiliary information to realize the joint learning of pulmonary nodule detection and semantic prediction by training with Faster R-CNN.The proposed method was evaluated on the LIDC/IDRI dataset.Results show that the accuracy of pulmonary nodule localization is 91.2%,and the accuracy,sensitivity and specificity of benign and malignant classification are 81%,91.2%and 70.8%respectively.On 8 semantic feature scores,the difference between doctors is 0.58±0.78(mean absolute error±standard deviation),the proposed method achieves the difference of 0.62±1.03 with doctors,which is familiar to the former one.These results demonstrate that the modified network has good prediction accuracy and semantic feature prediction,and facilitates the understanding and clinical interpretations of machine prediction results for doctors.