Kawagishi Masami, Chen Bin, Furukawa Daisuke, Sekiguchi Hiroyuki, Sakai Koji, Kubo Takeshi, Yakami Masahiro, Fujimoto Koji, Sakamoto Ryo, Emoto Yutaka, Aoyama Gakuto, Iizuka Yoshio, Nakagomi Keita, Yamamoto Hiroyuki, Togashi Kaori
Canon Inc., 70-1, Yanagi-cho, Saiwai-ku, Kawasaki, Kanagawa, 212-8602, Japan.
Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, 54 Kawaharacho, Shogoin, Sakyo-ku, Kyoto, 606-8507, Japan.
Int J Comput Assist Radiol Surg. 2017 May;12(5):767-776. doi: 10.1007/s11548-017-1554-0. Epub 2017 Mar 11.
In our previous study, we developed a computer-aided diagnosis (CADx) system using imaging findings annotated by radiologists. The system, however, requires radiologists to input many imaging findings. In order to reduce such an interaction of radiologists, we further developed a CADx system using derived imaging findings based on calculated image features, in which the system only requires few user operations. The purpose of this study is to check whether calculated image features (CFT) or derived imaging findings (DFD) can represent information in imaging findings annotated by radiologists (AFD).
We calculate 2282 image features and derive 39 imaging findings by using information on a nodule position and its type (solid or ground-glass). These image features are categorized into shape features, texture features and imaging findings-specific features. Each imaging finding is derived based on each corresponding classifier using random forest. To check whether CFT or DFD can represent information in AFD, under an assumption that the accuracies of classifiers are the same if information included in input is the same, we constructed classifiers by using various types of information (CTT, DFD and AFD) and compared accuracies on an inferred diagnosis of a nodule. We employ SVM with RBF kernel as classifier to infer a diagnosis name.
Accuracies of classifiers using DFD, CFT, AFD and CFT [Formula: see text] AFD were 0.613, 0.577, 0.773 and 0.790, respectively. Concordance rates between DFD and AFD of shape findings, texture findings and surrounding findings were 0.644, 0.871 and 0.768, respectively.
The results suggest that CFT and AFD are similar information and CFT represent only a portion of AFD. Particularly, CFT did not contain shape information in AFD. In order to decrease an interaction of radiologists, a development of a method which overcomes these problems is necessary.
在我们之前的研究中，我们使用放射科医生标注的影像特征开发了一种计算机辅助诊断（CADx）系统。然而，该系统需要放射科医生输入许多影像特征。为了减少放射科医生的这种交互操作，我们进一步开发了一种基于计算图像特征的派生影像特征的CADx系统，该系统只需要很少的用户操作。本研究的目的是检验计算图像特征（CFT）或派生影像特征（DFD）是否能够代表放射科医生标注的影像特征（AFD）中的信息。
我们利用结节位置及其类型（实性或磨玻璃样）信息计算2282个图像特征，并派生39个影像特征。这些图像特征被分为形状特征、纹理特征和特定于影像特征的特征。每个影像特征是基于使用随机森林的每个相应分类器派生而来的。为了检验CFT或DFD是否能够代表AFD中的信息，在假设如果输入中包含的信息相同则分类器的准确率相同的情况下，我们使用各种类型的信息（CTT、DFD和AFD）构建分类器，并比较对结节推断诊断的准确率。我们采用带有径向基函数核的支持向量机作为分类器来推断诊断名称。
使用DFD、CFT、AFD和CFT[公式：见正文]AFD的分类器的准确率分别为0.613、0.577、0.773和0.790。形状特征、纹理特征和周围特征的DFD与AFD之间的一致性率分别为0.644、0.871和0.768。
结果表明CFT和AFD是相似信息，且CFT仅代表AFD的一部分。特别是，CFT不包含AFD中的形状信息。为了减少放射科医生的交互操作，有必要开发一种克服这些问题的方法。
