Lung 4D CT Image Registration And Its Application In Respiratory Motion Estimation And Ventilation Estimation

Medical image registration is an important tool of medical image analysis,which has been widely used in disease diagnosis,brain atlas and image-guided radiotherapy.Compared with conventional 3-dimensional computed tomography(3D CT)technology,lung 4D CT adds time axis,which can provide information of the whole respiratory process for patients.The registration of lung 4D CT images can effectively describe the relative motion of lung tissues,thereby helping to solve the problems faced in many clinical applications,such as precise radiotherapy,tumor tracking and lung function assessment.Although the 4D CT image provides a good basis for lung motion estimation,the influence of respiratory motion and heart beats will lead to some problems,such as local intensity inhomogeneity of lung 4D CT images,lung motion discontinuities and large deformation of fine texture features,which brings great challenges to lung 4D CT image registration and its applications.In order to solve the above problems,this dissertation proposes a high-precision lung 4D CT image registration method based on high-order Markov Random Field(MRF).Based on the proposed high-precision lung 4D CT image registration method,a lung respiratory motion estimation method based on Kalman filtering and 4D CT image registration,and a lung ventilation estimation method based on 4D CT image registration and supervoxels are proposed respectively.The main innovations of this dissertation can be summarized as follows:(1)Proposed a lung 4D CT image registration based on high-order markov random fieldTo solve the problem that traditional image registration methods based on continuous optimization for large motion lung 4D CT image sequences are easy to fall into local optimal solutions and lead to serious misregistration,a novel image registration method based on high-order Markov Random Field(MRF)is proposed,By analyzing the effect of the deformation field constraint of the potential functions with different order cliques in MRF model,energy functions with high-order cliques form are designed separately for 2D and 3D images to preserve topology of the deformation field.In order to preserve the topology of the deformation field more effectively,it is necessary to apply a smooth term and a topology preservation term simultaneously in the energy function and use logarithmic function to impose a penalty on the Jacobian matrix with high-order cliques in the topology preservation term.For the complexity of the designed energy function with high-order cliques form,Markov Chain Monte Carlo(MCMC)algorithm is used to solve the optimization problem of the designed energy function.To address the high computational requirements in lung 4D CT image registration,a multi-level processing strategy is adopted to reduce the space complexity of the proposed registration method and promotes the computational efficiency.In the DIR-lab dataset with 4D CT images and the COPD dataset with 3D CT images,the average target registration error(TRE)of our proposed method can reach 0.95 mm respectively.(2)Proposed a lung respiratory motion estimation based on Kalman filtering and 4D CT image registrationRespiratory motion estimation is an important part in image-guided radiation therapy and clinical diagnosis.However,most of the respiratory motion estimation methods rely on indirect measurements of external breathing indicators,which will not only introduce great estimation errors,but also bring invasive injury for patients.In order to solve the above problems,a method of lung respiratory motion estimation based on fast Kalman filtering and 4D CT image registration(LRME-4DCT)is proposed.In order to perform dynamic motion estimation for continuous phases,a motion estimation model is constructed by combining two kinds of GPU-accelerated 4D CT image registration methods with fast Kalman filtering method.To address the high computational requirements of 4D CT image sequences,a multi-level processing strategy is adopted in the 4D CT image registration methods,and respiratory motion states are predicted from three independent directions.In the DIR-lab dataset and POPI dataset with 4D CT images,the average TRE of the LRME-4DCT method can reach 0.91 mm and 0.85 mm respectively.Compared with traditional estimation methods based on pair-wise image registration,the proposed LRME-4DCT method can estimate the physiological respiratory motion more accurately and quickly,and can fully meets the practical clinical requirements for rapid dynamic estimation of lung respiratory motion.(3)Proposed a lung ventilation estimation based on 4D CT image registration and supervoxelsMost of CT-derived ventilation estimation methods rely on deformation fields of image registration and voxel-wise relationships to directly estimate the voxel-wise ventilation image,which are easily affected by image registration results and motion artifacts of 4D CT images.In order to solve the above problems,a lung ventilation estimation method based on 4D CT image registration and supervoxels is proposed in this dissertation.First,images correspond to maximum exhale phase are represented by multi-level supervoxels.Then,according to the relationship between registered CT values and regional volume change,a ventilation estimation method is designed to calculate the whole ventilation of each supervoxel.To accurately recover the ventilation of each voxel from the supervoxel region,a linear programming model is established to obtain the ventilation of each voxel,and the final estimated lung ventilation image is obtained by averaging the recovered results of all supervoxels layers.Through the comparative analysis of various CT-derived ventilation estimation method on VAMPIRE dataset,it can be found that our proposed method has higher values of correlation than classic CT-derived ventilation estimation method,which shows that our proposed method can more accurately estimate the distribution of lung ventilation.