Automatic organ segmentation method based on laryngoscope medical image

• Main Authors: BAI WEIDONG, PAN XIAOYING, MU YAYA
• Format: Patent
• Language: Chinese; English
• Published: 02.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention belongs to the technical field of computer application, and particularly relates to an automatic organ segmentation method based on laryngoscope medical images. The method comprises the steps that remote dependence and multi-scale contexts can be effectively coded through a mixed Transform coding module, so that a model can effectively capture semantic features of different degrees, and the detail segmentation effect is improved; through an RRM decoding module, in the erasing process from high-level semantic information to bottom-level semantic information, an inaccurate segmented region is gradually refined into a complete region; and through a convolution conditional random field module, a probability model is used to optimize a segmentation result, a small mistakenly segmented region is eliminated, and segmentation is refined. According to the method, organ context information is established successively, organ and soft tissue structures are distinguished, long-distance dependent codes are es