Condylar process CBCT image segmentation method based on edge and texture features

• Main Authors: WU FULI, JIN LINXIAO, HAO PENGYI
• Format: Patent
• Language: Chinese; English
• Published: 25.07.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a condyle process CBCT image segmentation method based on edge and texture features, and the method comprises the steps: enabling an original condyle process CBCT image to pass through a condyle process segmentation model, and obtaining a region of interest of a whole condyle process; then inputting the region of interest of the condyle into a condyle cortex and cancellous bone segmentation model, obtaining corresponding texture feature data through a texture feature extraction module, and inputting the texture feature data and the feature coding network into a feature decoding network containing texture attention together to further obtain texture fusion features; and inputting the low-level features and the high-level features in the feature coding network into an edge extraction module to obtain edge information of the condylar cortex and the cancellous bone, and inputting the edge information and the texture fusion features into a fusion module to finally obtain a visual result gra