Research On Key Problems In Simulation Training Of Vascular Interventional Surgery For Coronary Heart Desease Based On Augmented Reality

Coronary Heart Disease is a type of Cardiovascular Diseases with the highest death rate in the world.The preoperative scientific diagnosis and planning,intraoperative perceive localization and postoperative accurate assessment are three critical steps during the entire vascular interventional therapy for coronary heart diseasein order to obtain the best clinical results.Selective coronary angiography and intravascular ultrasound are the main invasive diagnosis methods.Currently noninvasive 64 slice spiral CT coronary angiography has been considered as a relatively effective method for the diagnosis of coronary heart disease.It is also a noninvasive examination technique of coronary heart disease for postoperative evaluation of stent restenosis.In fact,most surgeons are used to diagnosing the position of the vascular stenosis first and then estimating vascular stenosis depend on their clinical experiences using the selective coronary angiography images during preoperative diagnosis.Therefore the diagnostic accuracy needs to be improved and the diagnostic methods need to be updated.The invasive diagnostic modality is short of intuitive and natural interaction and the results are not highly accurate.Vascular interventional surgery has superior difficulties and high precision with radiation.The traditional training requires long period,the real-time feedback is lack of pertinence and guiding and the effect of training need to be improved.Medicine is one of the earliest practical applications of augmented reality technology.This paper combines Augmented Reality technology with interactive diagnosis of coronary heart disease and interventional surgery into simulation training.Augmented Reality technology is researched and improved in accordance with the problem of combination.The intuitive display mode and the natural characteristic of Human Computer Interaction of Augmented Reality technology is employed to provide the preoperative natural mode of interactive diagnosis thus to plan the safe and reliable operation path as well as create the realistic operating environment for trainers.Three aspects including the correction of registration and accuracy tracking,the diagnosis of interactive gesture and three-dimensional path planning of vessel based on Augmented Reality are deeply researched in this paper.The specific work and innovation is as follows:1.According to the complicated and fuzzy relationship among the spatial data of electromagnetic tracker in magnetic field,the fusion method which combined of BP neural network and least squares support vector machine based on T-S fuzzy system is proposed for the correction of registration accuracy for the electromagnetic trackers.Firstly,K-means algorithm is employed to the cluster analysis,and then T-S fuzzy system is utilised to pre-process the spatial data in local.Secondly,the training is used by BP neural network in global and the training target of BP neural network is dynamically adjusted by the final correction accuracy.At last,least squares support vector machine is used to solve the after preliminary correction.The experimental results have shown that this method is applicable to nonlinear spatial data correction,which can effectively improve the registration accuracy of electromagnetic tracker and help improve the accuracy of interactive system with augmented reality.2.The coronary heart disease preoperative gesture interactive diagnostic method based on Augmented Reality is proposed in this paper.The method uses Leap Motion to capture hand gesture video sequences and extract the features which that are the position and orientation vector of the gesture motion trajectory and the change of the hand shape.The training plane is determined by K-means algorithm and then the effect of gesture training is improved by multi-features and multi-observation sequences for gesture training.The reusability of gesture is improved by establishing the state transition model.The algorithm efficiency is improved by gesture prejudgment which is used by threshold discriminating before recognition.The integrity of the trajectory is preserved and the gesture motion space is extended by employing space rotation transformation of gesture manipulation plane.Ultimately,the gesture recognition based on space rotation transformation and Hidden Markov Model is realized.The diagnosis and measurement of the vascular stenosis are intuitively and naturally realized by operating and measuring the coronary artery model with augmented reality and gesture interaction techniques.3.The self-learning gesture recognition method based on wavelet transform and Semi-continuous Hidden Markov Model is presented.Firstly,the dynamic gesture trajectory is analyzed by using K-means cluster algorithm to determine the gesture trajectory plane.Secondly,the integrity of the trajectory is preserved on the sensor plane by employing trajectory projection and space rotation transformation.Thirdly,the azimuth of gesture trajectory is analyzed by utilizing wavelet transform and the singularity of the trajectory is detected to compute the state number of Semi-continuous Hidden Markov Model for all the dynamic gestures.The gesture training is completed by employing Baum-Welch algorithm with multi-features and multi-observation sequences.Ultimately,gesture recognition is realized by using Viterbi algorithm based on self-learning mechanism to improve the gesture recognition rate.4.The vascular three-dimensional path planning method based on improved ant colony algorithm is proposed.The method plans a vascular optimal three-dimensional path with overall consideration of factors such as catheter diameter,vascular length,and diameter as well as the curvature and torsion based on ant colony algorithm.Firstly,the problem scale is simplified by reconnaissance algorithm.Secondly,the heuristic function,pheromone increment model and pheromone evaporation strategy of ant colony algorithm is modified.Finally,the global optimal path is obtained.Moreover,the method adopts augmented reality technology to register the reconstructed vascular model and physical model meanwhile,locate catheter by the electromagnetic tracking system and uses Head Mounted Display to show the planning path in real time and monitor catheter push procedure to protect the doctor and patient from exposing to X-ray in the long-term.The research results of this paper have a certain theoretical value and practical significance to expand the new mode of simulation training for coronary heart disease vascular interventional surgery.It provides the theoretical basis for combing AR with medical training and promots the application of AR and medical industry and the further development of related theoretical research.