摘要
针对传统计算机辅助检测(Computer-Aided Detection,CADe)肺结节系统根据经验提取的特征难以区分部分真实结节和骨质结构,造成检测结果假阳性较高的问题,引入Mask R-CNN模型用于胸片中肺结节的检测.结合基于对比度限制自适应直方图均衡化(contrast limit adaptive histogram equalization,CLAHE)和多段活动形状模型(multi-segment active shape model,M-ASM)的预处理,增强肺结节特征.模型中使用残差网络101(Res Net-101)和特征金字塔网络(feature pyramid network,FPN)提取特征.针对日本放射技术学会(Japanese Society of Radiological Technology,JSRT)公开数据库的测试,基于Mask R-CNN的CADe方案在平均假阳性(false positives,FPs)为5.0时的灵敏度为93.57%,假阳性为2.0时的灵敏度为78%.与其它方法比较,该方案能够检测出大多数肺区以外的肺结节(10/14).
Because of the traditional computer aided detection( CADe) scheme is difficult to distinguish some real nodules and bone structures based on the features extracted from experience,which gives high false positives( FPs) in the detection results,we introduce mask region-baseel convolutional neural network( Mask R-CNN) model for nodule detection in Chest X-Ray radiograph( CXR). We apply the limited contrast adaptive histogram equalization( CLAHE) and a multi-segment active shape model( M-ASM) to enhancing the nodule in CXR. The model selects Res Net-101 and feature pyramid network( FPN) as the backbone to extract image features. According to the test of the Japanese Society of Radiological Technology( JSRT) public database,the proposed scheme achieves a sensitivity of 93.57% with an average of 5.0 false positives( FPs) and 78% with an average of 2.0 FPs. Compared with other methods,most of the pulmonary nodules outside the lung area are detected in our scheme( 10/14).
作者
储春洁
王佳雯
韩雅琪
陈胜
CHU Chunjie;WANG Jiawen;HAN Yaqi;CHEN Sheng(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology y Shanghai 200093,China)
出处
《信息与控制》
CSCD
北大核心
2020年第6期728-734,共7页
Information and Control
基金
国家自然科学基金资助项目(81101116)。
