| The brachytherapy planning system has been used as an important auxiliary tool for brachy-particle implant therapy and has been used in many clinical operations.This paper focuses on the problems in brachytherapy implantation process and the brachytherapy treatment planning system.The main contents include: research on single modal medical image registration technology,automatic needle detection based on intraoperative CT image,intraoperative dose optimization module design and experiment on the system platform.The following are the main contents and research results of this paper:First,in order to solve the failure problem of preoperative planning in the surgery,the medical image registration technology was introduced,and then a new homomorphic CT image registration algorithm was proposed.The local mutual information is introduced as the registration method of the measurement,the optimization strategy is designed,and the complete registration process based on regional mutual information is established.In addition,in order to further improve the registration speed,a multi-resolution strategy based on wavelet transform is proposed to achieve a faster registration step.On this basis,the accuracy and efficiency of the proposed algorithm are verified by specific CT image experiments.Second,to assess the needle placement and assist the optimization of dose distribution in CT image guided lung interstitial brachytherapy,an automatic needle reconstruction algorithm has been proposed.The core technology of the algorithm includes pre-test model parameter evaluation technology,local random sample consistency and principal component analysis combined local optimization technology.By tracing intensities along the axis,the needle tip is determined.Furthermore,multi-needles in a single slice are segmented at once using successive inliers deletion.Finally,a comparative experiment was designed to verify the optimization effect of the intraoperative dose optimization method based on the needle recognition technology.Finally,Designed and implemented the core technologies in the intraoperative optimization module of the new brachytherapy system.A needle detection accuracy verification experiment was designed,which shows that: the segmentation efficiency is much higher than the original random sample consensus and yet maintains a stable submillimeter accuracy;the accuracy of needle recognition depends mainly on the depth of needle penetration;the mean errors in determining needle orientation and endpoint is regulated within 2° and 1 mm,respectively.The average segmentation time is 0.236 s per needle.This paper focuses on the problems existing in the standard brachytherapy implantation procedure and in the brachytherapy treatment planning system,a multi-resolution rigid registration algorithm based on regional mutual information,an intraoperative dose optimization method based on intraoperative automatic needle detection technology and the complete intraoperative dose optimization module are proposed,greatly improved the therapeutic effect,safety and operability of the dose planning system. |