Masami Kawagishi1, Bin Chen2, Daisuke Furukawa2, Hiroyuki Sekiguchi3, Koji Sakai4, Takeshi Kubo3, Masahiro Yakami3, Koji Fujimoto3, Ryo Sakamoto3, Yutaka Emoto5, Gakuto Aoyama2, Yoshio Iizuka2, Keita Nakagomi2, Hiroyuki Yamamoto2, Kaori Togashi3. 1. Canon Inc., 70-1, Yanagi-cho, Saiwai-ku, Kawasaki, Kanagawa, 212-8602, Japan. kawagishi.masami@canon.co.jp. 2. Canon Inc., 70-1, Yanagi-cho, Saiwai-ku, Kawasaki, Kanagawa, 212-8602, Japan. 3. Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, 54 Kawaharacho, Shogoin, Sakyo-ku, Kyoto, 606-8507, Japan. 4. Human Health Science, Graduate School of Medicine, Kyoto University, 53 Kawaharacho, Shogoin, Sakyo-ku, Kyoto, 606-8507, Japan. 5. Department of Medical Science, Kyoto College of Medical Science, 1-3, Imakita, Oyama-Higashimachi, Sonobe-cho, Nantan, Kyoto, 622-0041, Japan.
Abstract
PURPOSE: 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). METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.
PURPOSE: 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). METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.
Authors: L J Warren Burhenne; S A Wood; C J D'Orsi; S A Feig; D B Kopans; K F O'Shaughnessy; E A Sickles; L Tabar; C J Vyborny; R A Castellino Journal: Radiology Date: 2000-05 Impact factor: 11.105
Authors: Michael F McNitt-Gray; Samuel G Armato; Charles R Meyer; Anthony P Reeves; Geoffrey McLennan; Richie C Pais; John Freymann; Matthew S Brown; Roger M Engelmann; Peyton H Bland; Gary E Laderach; Chris Piker; Junfeng Guo; Zaid Towfic; David P-Y Qing; David F Yankelevitz; Denise R Aberle; Edwin J R van Beek; Heber MacMahon; Ella A Kazerooni; Barbara Y Croft; Laurence P Clarke Journal: Acad Radiol Date: 2007-12 Impact factor: 3.173
Authors: David S Gierada; Thomas K Pilgram; Melissa Ford; Richard M Fagerstrom; Timothy R Church; Hrudaya Nath; Kavita Garg; Diane C Strollo Journal: Radiology Date: 2007-11-16 Impact factor: 11.105