Chen Sheng, Yao Liping, Chen Bao
School of Optical Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China.
Xinhua Hospital, School of Biomedical Engineering, Shanghai Jiaotong University, Shanghai, China.
Med Biol Eng Comput. 2016 Nov;54(11):1793-1806. doi: 10.1007/s11517-016-1469-x. Epub 2016 Mar 25.
The enhancement of lung nodules in chest radiographs (CXRs) plays an important role in the manual as well as computer-aided detection (CADe) lung cancer. In this paper, we proposed a parameterized logarithmic image processing (PLIP) method combined with the Laplacian of a Gaussian (LoG) filter to enhance lung nodules in CXRs. We first applied several LoG filters with varying parameters to an original CXR to enhance the nodule-like structures as well as the edges in the image. We then applied the PLIP model, which can enhance lung nodule images with high contrast and was beneficial in extracting effective features for nodule detection in the CADe scheme. Our method combined the advantages of both the PLIP algorithm and the LoG algorithm, which can enhance lung nodules in chest radiographs with high contrast. To test our nodule enhancement method, we tested a CADe scheme, with a relatively high performance in nodule detection, using a publically available database containing 140 nodules in 140 CXRs enhanced through our nodule enhancement method. The CADe scheme attained a sensitivity of 81 and 70 % with an average of 5.0 frame rate (FP) and 2.0 FP, respectively, in a leave-one-out cross-validation test. By contrast, the CADe scheme based on the original image recorded a sensitivity of 77 and 63 % at 5.0 FP and 2.0 FP, respectively. We introduced the measurement of enhancement by entropy evaluation to objectively assess our method. Experimental results show that the proposed method obtains an effective enhancement of lung nodules in CXRs for both radiologists and CADe schemes.
胸部X光片（CXR）中肺结节的增强在肺癌的人工检测以及计算机辅助检测（CADe）中都起着重要作用。在本文中，我们提出了一种参数化对数图像处理（PLIP）方法，结合高斯拉普拉斯（LoG）滤波器来增强CXR中的肺结节。我们首先将几个具有不同参数的LoG滤波器应用于原始CXR，以增强图像中的结节状结构以及边缘。然后我们应用PLIP模型，该模型可以增强具有高对比度的肺结节图像，并且有利于在CADe方案中提取用于结节检测的有效特征。我们的方法结合了PLIP算法和LoG算法的优点，能够以高对比度增强胸部X光片中的肺结节。为了测试我们的结节增强方法，我们使用一个公开可用的数据库测试了一种在结节检测方面具有较高性能的CADe方案，该数据库包含通过我们的结节增强方法增强的140张CXR中的140个结节。在留一法交叉验证测试中，该CADe方案在平均帧率为5.0帧/秒（FP）和2.0帧/秒时，灵敏度分别达到81%和70%。相比之下，基于原始图像的CADe方案在5.0帧/秒和2.0帧/秒时的灵敏度分别为77%和63%。我们引入了通过熵评估进行增强测量，以客观地评估我们的方法。实验结果表明，所提出的方法对于放射科医生和CADe方案都能有效地增强CXR中的肺结节。
