基于混合损失联合调优与多尺度分类相结合的肺结节检测算法

Pulmonary nodule detection via hybrid loss based joint fine-tuning and multi-scale classification

针对CT图像的肺结节自动检测任务中检测灵敏度低及存在大量假阳性的问题,提出了一个基于混合损失的三维全卷积网络与基于注意力的多尺度三维残差网络相结合的肺结节检测方法。首先,基于相似度损失预训练三维全卷积网络,利用该网络筛选难例样本,并基于混合损失将难例与正样本进行联合调优得到候选结节检测网络,用于快速筛选疑似结节;然后,利用基于注意力的多尺度三维残差卷积网络对疑似结节进行分类,从候选结节中精确地分辨出真正结节。在LUNA16数据集上,候选结节检测阶段的灵敏度在每个病例的假阳数目为59. 1时达到97. 18%,检测系统的平均灵敏度为0. 880,表明本算法可以提高肺结节检测的灵敏度并有效控制假阳性,在LUNA16数据集上获得了更优的性能。

To solve the problem that lung nodule automatic detection methods for CT images can only get low sensitivities with a lot of false positives,this paper proposed an integrated method with hybrid loss based 3 D fully convolutional network as candidate detection and attention-based multi-scale residual network as nodule classification. Firstly,this paper established a 3 D fully convolutional network based on dice coefficient loss,and the network filtered hard negative samples uniting with positives to finetune. Then,it designed an attention based multi-scale 3 D residual convolutional network to classify the candidate and recognize true nodules. Experiment results on the LUNA16 dataset show that the proposed method achieves the sensitivity of 97. 18% at59. 1 false positives per scan in the candidate detection stage,and the whole system achieves the average sensitivity of 0. 880,which demonstrates this proposed method can improve sensitivity with fewer false positives and achieve superior performance.