A cornerstone3D-based medical image segmentation ROI data conversion method and system
By converting the ROI data format in Cornerstone3D, the compatibility issues between 3D Slicer and Cornerstone3D were resolved, enabling seamless migration and efficient conversion of AI segmentation algorithms, and ensuring the spatial consistency and clinical application accuracy of the converted segmentation data.
Patent Information
- Application Number
- CN202610313365.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-16
- Publication Date
- 2026-06-26
- Estimated Expiration
- 2046-03-16
AI Technical Summary
The existing ROI data format output by 3D Slicer has compatibility differences with Cornerstone3D's Labelmap format, resulting in high migration costs, low conversion efficiency, and loss of accuracy for AI segmentation algorithms, which affects clinical applications, especially in the processing of large-size 3D image data.
By acquiring target medical image data and its ROI data, multi-format recognition and parsing are performed to construct a standardized array of ROI objects. The data is then loaded using Cornerstone3D's image loading method, coordinate system transformation and voxel filling are performed, and Labelmap data is generated to ensure that the transformed segmented data is consistent with the original ROI in spatial location.
The AI segmentation algorithm in 3D Slicer was seamlessly applied to Cornerstone3D's web imaging system, reducing development costs and meeting the accuracy requirements of clinical applications, ensuring that the converted segmented data is completely consistent with the original ROI in spatial location.