一种皮肤提取方法及系统
By using nonlinear regression fitting and inter-layer geometric constraints, a skin cutting threshold and masking region are generated, which solves the instability problem of skin extraction in CBCT images, improves the accuracy of skin extraction and cross-sample adaptability, and is suitable for data registration and fusion in digital oral diagnosis and treatment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING STOMATOLOGY HOSPITAL CAPITAL MEDICAL UNIV
- Filing Date
- 2026-05-08
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for extracting facial skin tissue from CBCT images are easily affected by factors such as differences in scanning equipment parameters, patient tilt, and intraoral metal artifacts, resulting in poor consistency in the accuracy of skin extraction results and weak cross-sample adaptability, making it difficult to meet the needs of high-precision data registration and fusion.
By performing nonlinear regression fitting on the prior anatomical features of skin tissue in historical oral images, a skin cutting threshold is generated. Combined with the cross-sectional feature extraction and inter-layer geometric consistency constraints of the CBCT image to be processed, a target skin masking region is generated. Background value suppression and isosurface mesh processing are then performed to generate the skin extraction result.
It improves the stability and accuracy of skin extraction results, reduces the interference of scanning equipment and patient position changes on extraction results, enhances cross-sample adaptability, and adapts to high-precision registration and fusion of CBCT and facial scan data in digital oral diagnosis and treatment.
Smart Images
Figure CN122134732B_ABST