2015 年 32 巻 4 号 p. lxi-lxiv
In order to select the appropriate form of surgery, exact analysis of the invasive region of the tumour using breast MR images has become an important role in the diagnosis. However, many images are obtained for the identification of the tumour; the diagnostic ability of the physician may be decreased. The main purpose of this study was to propose a novel method for automated analysis of the region of the tumour using dynamic contrast‐enhanced breast MR images. For this method, T1‐weighted MR images of pre‐, early‐, and post‐contrast enhanced breast MR images were introduced. Early‐ and late‐subtraction images were obtained by subtracting early‐ and late‐contrast‐enhanced images, respectively, from the pre‐contrast ones. And then, tumor enhanced images were obtained using subtraction images. Subsequently, using the level‐set method, which was a type of dynamic contour extraction, the outline of the tumour in the tumour‐extracted images was obtained. We compared the tumour size listed in the interpretation report by a physician and analysed the results obtained from the proposed method. The mean absolute error of the size of tumours in all cases was less than 3.0 mm. These results indicate than propose method may be useful for the analysis of breast tumors.