Image filtering to make computer-aided detection robust to image reconstruction kernel choice in lung cancer CT screening
Image filtering to make computer-aided detection robust to image reconstruction kernel choice in lung cancer CT screening
复制标题
图像过滤使计算机辅助检测对肺癌 CT 筛查中的图像重建内核选择具有鲁棒性
作者：
Ohkubo M;Narita A;Wada S;Murao K;Matsumoto T.
目的在肺癌CT筛查中，计算机辅助检测（CAD）系统的性能取决于图像重建核的选择。为了减少对重建核的依赖，作者提出了一种新的图像滤波方法的应用。方法采用两个重构核的调制传递函数（mtf）之比作为空频域的滤波函数。这种方法被称为mtf滤波。测试图像数据来自67名受试者的CT筛查扫描，每个受试者有一个结节。使用两个核重建图像：fSTD（用于标准肺成像）和fsharp（用于锐边增强肺成像）。mtf滤波是利用对这些核测量的mtf实现的，并应用于重建的sharpimages，以获得与fstimages相似的图像。分别应用均值滤波器和中值滤波器进行比较。所有重建和滤波后的图像都使用他们的原型CAD系统进行处理。结果mtf滤波后的图像与stt图像具有较好的一致性。这些图像之间差异的标准偏差非常小，约6.0 Hounsfield单位（HU）。然而，平均滤光图像和中值滤光图像与fstimage的差异分别为~ 48.1和~ 57.9 HU。fsharp图像的自由响应接收器工作特性（FROC）曲线显示，与fstimage的FROC曲线相比，fsharp图像的性能更差。mtfratify滤波图像的FROC曲线与fstimages的曲线等效。然而，这种相似性不能通过使用均值滤波器或中值滤波器来实现。结论MTFratioimage滤波的准确性得到了验证，该方法可以有效地降低CAD性能对核的依赖。
PurposeIn lung cancer computed tomography (CT) screening, the performance of a computer‐aided detection (CAD) system depends on the selection of the image reconstruction kernel. To reduce this dependence on reconstruction kernels, the authors propose a novel application of an image filtering method previously proposed by their group.MethodsThe proposed filtering process uses the ratio of modulation transfer functions (MTFs) of two reconstruction kernels as a filtering function in the spatial‐frequency domain. This method is referred to as MTFratiofiltering. Test image data were obtained from CT screening scans of 67 subjects who each had one nodule. Images were reconstructed using two kernels:fSTD(for standard lung imaging) andfSHARP(for sharp edge‐enhancement lung imaging). The MTFratiofiltering was implemented using the MTFs measured for those kernels and was applied to the reconstructedfSHARPimages to obtain images that were similar to thefSTDimages. A mean filter and a median filter were applied (separately) for comparison. All reconstructed and filtered images were processed using their prototype CAD system.ResultsThe MTFratiofiltered images showed excellent agreement with thefSTDimages. The standard deviation for the difference between these images was very small, ∼6.0 Hounsfield units (HU). However, the mean and median filtered images showed larger differences of ∼48.1 and ∼57.9 HU from thefSTDimages, respectively. The free‐response receiver operating characteristic (FROC) curve for thefSHARPimages indicated poorer performance compared with the FROC curve for thefSTDimages. The FROC curve for the MTFratiofiltered images was equivalent to the curve for thefSTDimages. However, this similarity was not achieved by using the mean filter or median filter.ConclusionsThe accuracy of MTFratioimage filtering was verified and the method was demonstrated to be effective for reducing the kernel dependence of CAD performance.