首页> 外国专利> Image processing method, image composition method, data acquisition method, learning model generation method, nasal and sinus disease diagnosis support system, and nasal and sinus disease diagnosis support method

Image processing method, image composition method, data acquisition method, learning model generation method, nasal and sinus disease diagnosis support system, and nasal and sinus disease diagnosis support method

机译:图像处理方法,图像组成方法,数据采集方法,学习模型生成方法,鼻腔和鼻窦疾病诊断支持系统,以及鼻窦疾病诊断支持方法

摘要

PROBLEM TO BE SOLVED: To provide a system for supporting diagnosis of nasal and sinus diseases. A method of generating a learning model for a system that supports the diagnosis of nasal and sinus diseases includes a step of acquiring a CT image including a maxillary sinus, a frontal sinus, a lamina sinus, and a butterfly bone sinus, and the CT. Regarding the image, the partitioning step of partitioning the areas of the maxillary sinus, the frontal sinus, the anterior sinus, the posterior sinus, and the butterfly sinus into five, and the size of the five divided regions, The relationship with the area size of what was formed inside the five regions was quantified, and the difference between the bone around the maxillary sinus on one side and the bone around the maxillary sinus on the other was quantified. For each of the above, a quantification step for quantifying the shading, interview data corresponding to the CT image, quantification by the quantification step, and data for nasal and sinus diseases corresponding to the CT image. Is included as the teacher data, and includes a learning process for learning the relationship between the CT image and the nose and sinus diseases. [Selection diagram] FIG. 18
机译:要解决的问题:提供一种支持鼻腔和鼻窦疾病的诊断系统。一种为支持鼻腔和窦疾病诊断的系统生成学习模型的方法包括获取包括上颌窦,正面窦,层窦和蝶形骨窦和CT的CT图像的步骤。关于图像,将上颌窦,前窦,前窦,后窦和蝶窦分成的分区步骤,分为五个分割区域的大小,与面积大小的关系量化了在五个区域内形成的内容,并且在另一侧骨骼周围的骨骼周围的骨骼与另一侧上颌窦周围的骨骼之间的差异。对于上述每一个,用于量化阴影,对应于CT图像的访谈数据,通过量化步骤的量化的量化步骤,以及对应于CT图像的鼻腔和鼻窦疾病的数据。包括作为教师数据,并包括学习CT图像与鼻窦和鼻窦疾病之间关系的学习过程。 [选择图]图。 18.

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号