会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 6. 发明申请
    • IMAGE PROCESSING DEVICE AND METHOD FOR PROCESSING IMAGE
    • 图像处理装置和处理图像的方法
    • US20110164064A1
    • 2011-07-07
    • US13060506
    • 2009-08-27
    • Shino TanakaTakashi ShirahataTakayuki KadomuraHiroto Kokubun
    • Shino TanakaTakashi ShirahataTakayuki KadomuraHiroto Kokubun
    • G06T7/00G06T3/40
    • A61B5/103A61B5/055A61B5/1075A61B5/7475A61B6/032A61B6/566G06F19/00G06F19/321G06T3/0037G06T7/0012G06T15/08G06T2200/24G06T2207/10081G06T2207/20068G06T2207/30032G06T2207/30096
    • A medical image processing device 100 is configured to be able to set a parameter to be used for detecting a lesion candidate region in executing a processing of detecting the lesion candidate region from an image of an organ surface in order to provide an image processing device for detecting a lesion region under the condition that an operator is allowed to easily change a detection object in accordance with diagnostic purposes. For example, a parameter P1 to be set is a polyp diameter. Values in accordance with modes or operator's desired values are set as values of the parameter P1. CPU 101 further calculates a parameter P2 such as the inter-distance between differentiation reference points based on the set parameter P1, calculates the shape (curvature value) of each point on the organ surface using the parameter P2, and extracts a point having a predetermined shape as a lesion candidate region. CPU 101 further calculates feature amounts such as a region diameter and a degree of circularity for the extracted lesion candidate region, determines whether or not the extracted lesion candidate region actually corresponds to a lesion candidate based on the feature amounts, and deletes a false-positive region.
    • 医疗用图像处理装置100被配置为能够在从器官表面的图像执行检测病变候选区域的处理时设定用于检测病变候选区域的参数,以提供图像处理装置 在允许操作者根据诊断目的容易地改变检测对象的条件下检测病变区域。 例如,要设定的参数P1是息肉直径。 根据模式或操作者的期望值的值被设置为参数P1的值。 CPU 101进一步基于设定参数P1计算差分参考点之间的距离等参数P2,使用参数P2计算器官表面上的各点的形状(曲率值),并且提取具有预定 形状作为病变候选区域。 CPU 101还对所提取的病变候选区域进一步计算特征量,例如区域直径和圆度度,基于特征量,确定所提取的病变候选区域是否实际上对应于病变候选,并且删除假阳性 地区。