基于形态学的OVH描述子计算方法及其在放疗计划检索中的应用
Calculation method for OVH descriptor based on morphology and its application in radiation treatment plan retrieval

提出了一种基于形态学的OVH描述子计算方法,并评估了其在IMRT计划检索方面的性能.首先,将靶区与危及器官之间的最小距离和最大距离分别作为靶区收缩/扩张的起始点和终止点,并根据此最小距离和最大距离确定收缩/扩张的合适步长;然后,利用形态学膨胀/腐蚀原理对病例的计算机断层扫描数据进行处理,完成OVH描述子的有效计算;最后,以OVH曲线之间的面积为度量尺度,利用28个鼻咽癌病例评价了基于OVH描述子的IMRT计划检索的性能.实验结果表明,该方法能够有效准确地计算出OVH描述子,利用OVH描述子能够有效检索出形状相似度较高的病例.
A calculation method for the overlap volume histogram(OVH)descriptor based on morphology is proposed,and its performance in intensity modulated radiation therapy(IMRT)plan retrieval is evaluated. First, the minimum distance and the maximum distance between the target and organs at risk are taken as the start point and the end point of contraction/expansion operation, respectively, and the suitable step of contraction/expansion operation is determined according to the minimum distance and the maximum distance. Then, the principle of morphology dilation/erosion is employed to process the computer tomography(CT)data of cases and compute the OVH descriptor effectively. Finally, 28 nasopharyngeal carcinoma(NPC)cases are employed to evaluate the retrieval performance of IMRT plan with the area between OVH curves being taken as the similarity measurement. The experimental results show that the proposed method can calculate the OVH descriptor effectively, and the OVH descriptor can be effectively used to retrieval the IMRT cases with high similarity