Structure-constrained language-assisted diffusion model for unpaired low-dose computed tomography angiography reconstruction.
Authors
Affiliations (7)
Affiliations (7)
- Key Lab of Optoelectronic Technology and Systems and Engineering Research Center of Industrial Computed Tomography Nondestructive Testing, Ministry of Education, Chongqing University, Chongqing, 400044, China.
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, 518107, China.
- Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, Beijing, 100029, China.
- School of Information Engineering, Nanchang, Jiangxi, 330031, China.
- Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore, 138632, Republic of Singapore.
- Key Lab of Optoelectronic Technology and Systems and Engineering Research Center of Industrial Computed Tomography Nondestructive Testing, Ministry of Education, Chongqing University, Chongqing, 400044, China. Electronic address: [email protected].
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, 518107, China. Electronic address: [email protected].
Abstract
The application of iodinated contrast media (ICM) improves the sensitivity and specificity of computed tomography (CT) for a wide range of clinical indications. However, high ICM doses can cause problems such as kidney damage and life-threatening allergic reactions. Deep learning methods can generate CT images of normal-dose ICM from low-dose ICM, reducing the required dose while maintaining diagnostic power. However, existing methods struggle to achieve accurate enhancement with incompletely paired images, mainly because of the limited ability of the model to recognize specific structures. To overcome this limitation, we propose a Structure-constrained Language-assisted Diffusion Model (SLDM), a unified medical generation model that integrates structural synergy and spatial intelligence. First, the structural prior information of the image is effectively extracted to constrain the model inference process, thus ensuring structural consistency in the enhancement process. Subsequently, a language-assisted strategy with spatial intelligence is introduced, which integrates the functions of visual perception and spatial reasoning, thus prompting the model to achieve accurate enhancement. Finally, the subtraction angiography enhancement module is applied, which serves to improve the contrast of the ICM region to suitable interval for observation. Qualitative analysis of visual comparison and quantitative results of several metrics demonstrate the effectiveness of our method in angiographic reconstruction for low-dose contrast medium CT angiography.