首页> 外国专利> DEEP LEARNING BASED IMAGE SEGMENTATION METHOD INCLUDING BIODEGRADABLE STENT IN INTRAVASCULAR OPTICAL TOMOGRAPHY IMAGE

DEEP LEARNING BASED IMAGE SEGMENTATION METHOD INCLUDING BIODEGRADABLE STENT IN INTRAVASCULAR OPTICAL TOMOGRAPHY IMAGE

机译:基于深度学习的图像分割方法,包括血管内光学断层摄影图像中的可生物降解支架

摘要

According to some embodiments of the present disclosure, an image segmentation apparatus is disclosed. The image segmentation apparatus may include: a storage unit for storing a segmentation model learned to segment at least one preset object; and at least one processor for inputting input data into the segmentation model and segmenting at least one preset object from the input data. Including, wherein the partition model comprises: an encoder including at least one dimension reduction block for reducing the dimension of the input data; a decoder including at least one dimension increase block for increasing a dimension of output data output from the encoder using data output from the at least one dimension reduction block; and an auxiliary classification model that receives the output data and recognizes whether a specific object is included in the output data.
机译:根据本公开的一些实施例,公开了一种图像分割装置。 图像分割设备可以包括:存储单元,用于存储分割模型以将至少一个预设对象进行分段; 和至少一个处理器,用于将输入数据输入分段模型并从输入数据分段至少一个预设对象。 包括,其中分区模型包括:编码器,包括用于减小输入数据的维度的至少一个尺寸减少块; 包括至少一个维度增加块的解码器,用于使用从所述至少一个尺寸减少块输出的数据输出从所述编码器输出的输出数据的维度; 和一个辅助分类模型,其接收输出数据并识别特定对象是否包括在输出数据中。

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