Deformable image registration plays a crucial role in medical image analysis. Despite various advanced registration models having been proposed, achieving accurate and efficient deformable registration remains challenging. Leveraging the recent outstanding performance of Mamba in computer vision, we introduced a novel model called MCRDP-Net. MCRDP-Net adapted a dual-stream network architecture that combined Mamba blocks and convolutional blocks to simultaneously extract global and local information from fixed and moving images. In the decoding stage, we employed a pyramid network structure to obtain high-resolution deformation fields, achieving efficient and precise registration. The effectiveness of MCRDP-Net was validated on public brain registration datasets, OASIS and IXI. Experimental results demonstrated significant advantages of MCRDP-Net in medical image registration, with DSC, HD95, and ASD reaching 0.815, 8.123, and 0.521 on the OASIS dataset and 0.773, 7.786, and 0.871 on the IXI dataset. In summary, MCRDP-Net demonstrates superior performance in deformable image registration, proving its potential in medical image analysis. It effectively enhances the accuracy and efficiency of registration, providing strong support for subsequent medical research and applications.
In the process of positron emission tomography (PET) data acquiring, respiratory motion reduces the quality of PET imaging. In this paper, we present a correction method using three level grids B-spline elastic method to correct denoised and reorganized sinograms for respiratory motion correction. Using GATE simulates NCAT respiratory motion model to generate raw data which are used in experiment, the experiment results showed a significantly improved respiratory image with higher quality of PET, and the motion blur and structural information were fixed. The results proved the method of this paper would be effective for the elastic registration.
The medical image registration between preoperative three-dimensional (3D) scan data and intraoperative two-dimensional (2D) image is a key technology in the surgical navigation. Most previous methods need to generate 2D digitally reconstructed radiographs (DRR) images from the 3D scan volume data, then use conventional image similarity function for comparison. This procedure includes a large amount of calculation and is difficult to archive real-time processing. In this paper, with using geometric feature and image density mixed characteristics, we proposed a new similarity measure function for fast 2D-3D registration of preoperative CT and intraoperative X-ray images. This algorithm is easy to implement, and the calculation process is very short, while the resulting registration accuracy can meet the clinical use. In addition, the entire calculation process is very suitable for highly parallel numerical calculation by using the algorithm based on CUDA hardware acceleration to satisfy the requirement of real-time application in surgery.
Objective The baseline, clinical characteristics, and risk factors were analyzed in the stroke registry program of the Xinjiang Production Constraction Corp’s Hospital aimed to aid the clinical management and stroke prevention. Method A single center prospective method based on Lausanne Stroke Registry was used in this study. Patients generally, past history, living conditions, onset to treatment time, the stroke scale were collected with 1 year follow up. The investigators of follow up were single blinded. Result Eight hundred and ten ischemic stroke patients were included, of which 478 (59.01%) were male, 332 (40.99%) were female. The average age of these patients was 66.50±10.66 years. One year loss rate of follow up was 4.64%. Seven hundred and sixty-nine patients were diagnosis as acute cerebral infarction, 41 patients were TIA. The median time from onset to treatment was 15 hours. Lacunar infarction was the most common type with 334 (43.43%) patients. The average score of the National Institutes of Heath Stroke Scale was 5.55±7.24. The incidence of carotid artery plaque was 82.2%. Conclution Xinjiang region has its own characteristics of stroke with a higher carotid artery plaque rate and thrombolytic therapy ratio. Good stroke registration system could standardize the clinical behavior and promote the continuous improvement of medical quality.
ObjectivesTo analyze the research status and hot spots of hypertension-related clinical trials in special Chinese population registered on the Chinese Clinical Trial Registry (ChiCTR), so as to provide a basis for the development of hypertension-related research in special population in China.MethodsThe ChiCTR was searched online (up to August 31st, 2019, no limitation in the status of trial registration), all clinical trials on hypertension in special population were collected, and the general characteristics, researched diseases, research types, intervention measures and main outcomes of the trials were analyzed.ResultsA total of 64 hypertension-related clinical trials in special population registered in the ChiCTR were included, including 41 (64.1%) trials registered in last 3 years. The registration status of 46 (71.9%) trials was pre-registration. The registered authors were mainly from colleges and universities or medical institutions (n = 61, 95.3%), of which 60.9% were registered in Beijing, Shanghai, Guangdong, Zhejiang, Jiangsu and Hebei. The researched diseases mainly included elderly hypertension and hypertensive stroke, accounting for 50% of the total. Additionally, 37 (57.8%) clinical trials were intervention studies, of which 21 (56.7%) were drug-based intervention studies. Blood pressure, blood glucose, cardiovascular and cerebrovascular events, blood lipid, cranial MRI and Glasgow Coma Scale were the commonly used outcomes, accounting for 58.5% of the total outcomes. Most blood pressure measurements did not indicate the measurement method (n = 22, 64.7%).ConclusionsThe quantity of hypertension-related clinical trials in special population registered on the ChiCTR is increasing, however, there exists regional imbalance. The drug intervention-related clinical trials of elderly hypertension have become a research hot spot. However, blood pressure measurement method is not indicated in most trials, and some researchers do not register in time. Therefore, it is suggested that researchers should further strengthen the awareness of carrying out high-quality clinical trials.
Image registration is of great clinical importance in computer aided diagnosis and surgical planning of liver diseases. Deep learning-based registration methods endow liver computed tomography (CT) image registration with characteristics of real-time and high accuracy. However, existing methods in registering images with large displacement and deformation are faced with the challenge of the texture information variation of the registered image, resulting in subsequent erroneous image processing and clinical diagnosis. To this end, a novel unsupervised registration method based on the texture filtering is proposed in this paper to realize liver CT image registration. Firstly, the texture filtering algorithm based on L0 gradient minimization eliminates the texture information of liver surface in CT images, so that the registration process can only refer to the spatial structure information of two images for registration, thus solving the problem of texture variation. Then, we adopt the cascaded network to register images with large displacement and large deformation, and progressively align the fixed image with the moving one in the spatial structure. In addition, a new registration metric, the histogram correlation coefficient, is proposed to measure the degree of texture variation after registration. Experimental results show that our proposed method achieves high registration accuracy, effectively solves the problem of texture variation in the cascaded network, and improves the registration performance in terms of spatial structure correspondence and anti-folding capability. Therefore, our method helps to improve the performance of medical image registration, and make the registration safely and reliably applied in the computer-aided diagnosis and surgical planning of liver diseases.
Mitral valve disease is one of the most popular heart valve diseases. Precise positioning and displaying of the valve characteristics is necessary for the minimally invasive mitral valve repairing procedures. This paper presents a multi-resolution elastic registration method to compute the deformation functions constructed from cubic B-splines in three dimensional ultrasound images, in which the objective functional to be optimized was generated by maximum likelihood method based on the probabilistic distribution of the ultrasound speckle noise. The algorithm was then applied to register the mitral valve voxels. Numerical results proved the effectiveness of the algorithm.
Complete three-dimensional (3D) tooth model provides essential information to assist orthodontists for diagnosis and treatment planning. Currently, 3D tooth model is mainly obtained by segmentation and reconstruction from dental computed tomography (CT) images. However, the accuracy of 3D tooth model reconstructed from dental CT images is low and not applicable for invisalign design. And another serious problem also occurs,i.e. frequentative dental CT scan during different intervals of orthodontic treatment often leads to radiation to the patients. Hence, this paper proposed a method to reconstruct tooth model based on fusion of dental CT images and laser-scanned images. A complete 3D tooth model was reconstructed with the registration and fusion between the root reconstructed from dental CT images and the crown reconstructed from laser-scanned images. The crown of the complete 3D tooth model reconstructed with the proposed method has higher accuracy. Moreover, in order to reconstruct complete 3D tooth model of each orthodontic treatment interval, only one pre-treatment CT scan is needed and in the orthodontic treatment process only the laser-scan is required. Therefore, radiation to the patients can be reduced significantly.
Objective To analyze the current research status, characteristics and development trends of traditional medicine-related clinical trials registration, and to provide ideas and directions for further development of traditional medicine clinical trials. Methods The International Traditional Medicine Clinical Trial Registry (ITMCTR) database was searched by computer from inception to June 30, 2024, with unlimited trial registration status, to collect all the clinical trials on traditional medicine, and analyze the basic information of the trials, the diseases studied and the interventions. Results A total of 4 349 clinical trials related to traditional medicine were included, with the number of registrations peaking in the second half of 2020, and showing a steady upward trend after 2023. The trial sponsors of the study covered 9 countries and a total of 34 provinces/autonomous regions/municipalities in China, led by Beijing, Shanghai, Guangdong, Sichuan, and Zhejiang provinces, accounting for 69.72% of the total. The financial support for the studies was dominated by local government funds in various provinces and cities, accounting for 29.66%. Disease types studied were mainly circulatory system diseases, musculoskeletal system or connective tissue diseases, and tumor diseases, accounting for 29.91% of the total. A total of 3 751 (86.3%) clinical trials were interventional studies, of which randomized parallel control was predominant, and 213 large-sample studies with a sample size of more than 1 000 cases were included. A total of 20 types of interventions were involved, of which 1 114 (29.86%) clinical trials utilized oral prescription of herbal medicine interventions. Conclusion Clinical trial enrollment in traditional medicine has increased overall, but with significant geographic unevenness. Oral herbal soup/granule intervention studies are the mainstream hotspots. It is recommended to strengthen international cooperation, enrich the types of interventions, refine the trial design, and raise the awareness of researchers about the registration of high-quality traditional medicine clinical trials.
Medical image registration is very challenging due to the various imaging modality, image quality, wide inter-patients variability, and intra-patient variability with disease progressing of medical images, with strict requirement for robustness. Inspired by semantic model, especially the recent tremendous progress in computer vision tasks under bag-of-visual-word framework, we set up a novel semantic model to match medical images. Since most of medical images have poor contrast, small dynamic range, and involving only intensities and so on, the traditional visual word models do not perform very well. To benefit from the advantages from the relative works, we proposed a novel visual word model named directional visual words, which performs better on medical images. Then we applied this model to do medical registration. In our experiment, the critical anatomical structures were first manually specified by experts. Then we adopted the directional visual word, the strategy of spatial pyramid searching from coarse to fine, and the k-means algorithm to help us locating the positions of the key structures accurately. Sequentially, we shall register corresponding images by the areas around these positions. The results of the experiments which were performed on real cardiac images showed that our method could achieve high registration accuracy in some specific areas.