A joint MRI reconstruction and segmentation method based on depth unfolding
CN117456029BActive Publication Date: 2026-11-17EAST CHINA NORMAL UNIV
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202311399126.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-25
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-10-25
Smart Images

Figure CN117456029B_ABST
Abstract
This invention discloses a joint MRI reconstruction and segmentation method based on depth unfolding. Its key feature is the use of compressed sensing theory and level set methods to construct a joint reconstruction and segmentation network model based on depth unfolding for direct segmentation of undersampled k-space MRI data. The method specifically includes steps such as dataset acquisition and processing, network model construction and training, and lesion segmentation. Compared with existing technologies, this invention improves the adaptability and accuracy of the segmentation network to various lesions or organs, can directly segment k-space undersampled MR images, and preserves important edge information while smoothing the image, thereby improving the continuity and accuracy of the segmentation results. It also enhances the interpretability of the model while improving performance, demonstrating promising application prospects.
Need to check novelty before this filing date? Find Prior Art
