Objective To evaluate the feasibility of using medical image analysis for adaptive radiotherapy of lung cancer by drawing the individual contours automatically or interactively and adjusting the planning target volume weekly for reducing the volume of the excessive irradiated normal lung tissue.Methods Many CT images of the GTV and dynamic X-ray fluoroscope data of 23 patients were acquired and all the data were used for working out the tumor radiotherapy plan(TPS) and positioning the patient and to measure reduction in GTV volume.A planning study was conducted to determine the amount of lung-sparing that could have been achieved if adaptive therapy had been used.Treatment plans were created in which the target volumes were reduced after tumor reduction was measured.Results A total of 6313 CT imaging sessions and 78 groups of X-ray dynamic fluoroscope data were performed on 23 lung patients.The GTV was reduced by 70%～80% during the course of treatment.Based on these treatment planning studies,the dose of ipsilateral lung can be reduced significantly by adapting the treatment delivery.Conclusion Medical image analysis can be used to position the GTV and CTV of the tumors.This technology can help to work out the individual TPS and adjust the radiotherapy treatment plan adaptively during the course of treatment and reduce the dose of normal tissues as well as insure the effect of tumor treatment.

Fuzzy c-means (FCM) clustering algorithm is a popular model widely used in the segmentation of magnetic resonance image (MRI). The conventional FCM doesn't involve the spatial information of MRI and then unexpected segmentation results appear when it is applied to inhomogeneous MRI with noise and bias field. Modifying the objective function of FCM and introducing a variable as the parameter to control the tight degree of neighborhood effect present a spatial model to FCM clustering algorithm. The variable can reasonably use the spatial information of MRI. The experiment results show that the proposed algorithm can provide a powerful segmentation than the conventional FCM and others.

A novel mono-hierarchical muti-axiel classification coding scheme for medical image retrieval is proposed.The so-called MOAB coding scheme consists of four axes with three to four positions ranging from0to9,from A to Z.In particular,the modality code M describes imaging modality and relevant technical detail,and the orientation code O models examined body orientation.The anatomy code A refers to the body region examined and the biology code B describes the biological system examined.The MOAB classification-coding scheme enables a unique classifi-cation of medical images so that medical image retrieval can be efficient.The code is flexible and easy to be ex-tended.

Mutual information(MI) is a tool of measuring the statistical dependence between two random variables. MI between two images, being considered as two random fields, can be calculated to determine the degree of information redundancy between the image intensities of corresponding pixels in both images. In this paper, we utilize the MI criterion to realize the generalized registration between two neighboring slices in a medical image sequence (CT, MR et al) and consider that they match with each other if the MI between them is maximal. Experimental results confirm performance of our algorithm.

Objective To develop a virtual endoscopy system which can be integrated into PACS.Methods Key techniques on virtual endoscopy were researched and we implemented a virtual endoscopy system with the help of the Visualization Toolkit VTK.Results The Virtual endoscopy system was integrated into PACS and the post-processing function of PACS was advanced.Conclusion As a novel medical image post-processing technology,virtual endoscopy provides a completely non-invaded inspection,so it has broad application prospects in the computer-aided medical teaching,surgical navigation,surgical planning and clinical diagnosis.

Objective: 3D segmentation is an important part of medical image analysis and visualization. It also continues to be large challenge in the medical image segmentation. While level sets have demonstrated a great potential for 3D medical image segmentation, these algorithms have a large computational burden thus are not suitable for real time processing requirement. To solve this problem, we propose a parallel accerelated method based on CUDA. Methods: We implement C-V level set algorithm in the CUDA environment which is the NVIDIA's GPGPU model.The segmentation speed can greatly improved by using independence of image pixel and concurrence of partial differential equation .The paper shows the flow chart of the parallel computing and gives the detailed introduction of the C-V level set algorithm which is implemented in the CUDA environment. Results: Realizing the C-V level set parallel accerelated algorithm. This method has faster segmentation speed while preserving the qualitative results, Conclusions: This method is viable and makes the fast 3D medical image segmentation come hue.

The system planning of characteristic education in biomedical engineering was performed,in which such ideas were raised as clear-cut cultivation target,self-contained curricula system and flexible experimental technique.The system planning provided systematic knowledge structure and the induction from theory to practice for undergraduates in 5 majors in our school.Based on this system planning,the teaching quality is improved.

According to the thoughts of experimental platform construction of the BME experimental teaching demonstration center,the education and institution construction relevant to concrete operating steps and methods are carried on.The engineering experimental platform featuring "Multiple-structure,Multiple-specialty,Integration,Open-type" are substantiated and perfected.A batch of advanced instruments for experimental teaching are purchased.The methods and measures for experimental teaching are improved.The scientific research is permeated into the student's experimental teaching for cultivation innovative talents.

Objective: Real time medical image registration technique is one of the key techniques in image based surgery navi-gation system. While in medical image analysis, image registration is usually a very time-cousuming operation, and this is not conducive to clinical real-time requirements. This paper studies and realizes the acceleration of the process of image registra-tion. Methods: In order to improve the regisWation rate, in this paper, we propose a new technology which is based on CUDA (Compute Unified Device Architecture) programming model to accelerate the process of registration in hardware, using paral-lel methods to achieve pixel coordinate transformation, linear interpolation, and calculate the corresponding pixel gray value residuals. Results: The registration is up to the sub-pixel level and the GPU-based registration is dozens or even hundreds of times faster than CPU-based registration. Conclusions: This method greatly enhances the speed of rigid registration without changing the alignment accuracy.

To enhance the quality project,there are four ways to ensure the quality of the undergraduate thesis and project.The first way is to inaugurate new bases: from school to company.The second is a wide choice of projects.The third way is that the project can be taken ahead of schedule.Finally,two tutors are designated to ensure the quality of thesis.