Jian Wu1, Martin J Murphy. 1. Department of Radiation Oncology, Virginia Commonwealth University, Richmond, Virginia 23298, USA. jwu@mcvh-vcu.edu
Abstract
PURPOSE: To develop a neural network based registration quality evaluator (RQE) that can identify unsuccessful 3D/3D image registrations for the head-and-neck patient setup in radiotherapy. METHODS: A two-layer feed-forward neural network was used as a RQE to classify 3D/3D rigid registration solutions as successful or unsuccessful based on the features of the similarity surface near the point-of-solution. The supervised training and test data sets were generated by rigidly registering daily cone-beam CTs to the treatment planning fan-beam CTs of six patients with head-and-neck tumors. Two different similarity metrics (mutual information and mean-squared intensity difference) and two different types of image content (entire image versus bony landmarks) were used. The best solution for each registration pair was selected from 50 optimizing attempts that differed only by the initial transformation parameters. The distance from each individual solution to the best solution in the normalized parametrical space was compared to a user-defined error threshold to determine whether that solution was successful or not. The supervised training was then used to train the RQE. The performance of the RQE was evaluated using the test data set that consisted of registration results that were not used in training. RESULTS: The RQE constructed using the mutual information had very good performance when tested using the test data sets, yielding the sensitivity, the specificity, the positive predictive value, and the negative predictive value in the ranges of 0.960-1.000, 0.993-1.000, 0.983-1.000, and 0.909-1.000, respectively. Adding a RQE into a conventional 3D/3D image registration system incurs only about 10%-20% increase of the overall processing time. CONCLUSIONS: The authors' patient study has demonstrated very good performance of the proposed RQE when used with the mutual information in identifying unsuccessful 3D/3D registrations for daily patient setup. The classifier had very good generality and required only to be trained once for each implementation. When the RQE is incorporated with an automated 3D/3D image registration system, it can improve the robustness of the system.
PURPOSE: To develop a neural network based registration quality evaluator (RQE) that can identify unsuccessful 3D/3D image registrations for the head-and-neck patient setup in radiotherapy. METHODS: A two-layer feed-forward neural network was used as a RQE to classify 3D/3D rigid registration solutions as successful or unsuccessful based on the features of the similarity surface near the point-of-solution. The supervised training and test data sets were generated by rigidly registering daily cone-beam CTs to the treatment planning fan-beam CTs of six patients with head-and-neck tumors. Two different similarity metrics (mutual information and mean-squared intensity difference) and two different types of image content (entire image versus bony landmarks) were used. The best solution for each registration pair was selected from 50 optimizing attempts that differed only by the initial transformation parameters. The distance from each individual solution to the best solution in the normalized parametrical space was compared to a user-defined error threshold to determine whether that solution was successful or not. The supervised training was then used to train the RQE. The performance of the RQE was evaluated using the test data set that consisted of registration results that were not used in training. RESULTS: The RQE constructed using the mutual information had very good performance when tested using the test data sets, yielding the sensitivity, the specificity, the positive predictive value, and the negative predictive value in the ranges of 0.960-1.000, 0.993-1.000, 0.983-1.000, and 0.909-1.000, respectively. Adding a RQE into a conventional 3D/3D image registration system incurs only about 10%-20% increase of the overall processing time. CONCLUSIONS: The authors' patient study has demonstrated very good performance of the proposed RQE when used with the mutual information in identifying unsuccessful 3D/3D registrations for daily patient setup. The classifier had very good generality and required only to be trained once for each implementation. When the RQE is incorporated with an automated 3D/3D image registration system, it can improve the robustness of the system.
Authors: P M Evans; J Q Gildersleve; E J Morton; W Swindell; R Coles; M Ferraro; C Rawlings; Z R Xiao; J Dyer Journal: Br J Radiol Date: 1992-08 Impact factor: 3.039
Authors: Laurence E Court; Lei Dong; Noah Taylor; Matthew Ballo; Kei Kitamura; Andrew K Lee; Jennifer O'Daniel; R Allen White; Rex Cheung; Deborah Kuban Journal: Int J Radiat Oncol Biol Phys Date: 2004-06-01 Impact factor: 7.038
Authors: Eung-Joo Lee; William Plishker; Nobuhiko Hata; Paul B Shyn; Stuart G Silverman; Shuvra S Bhattacharyya; Raj Shekhar Journal: J Digit Imaging Date: 2021-10-13 Impact factor: 4.903
Authors: Suicheng Gu; Xin Meng; Frank C Sciurba; Hongxia Ma; Joseph Leader; Naftali Kaminski; David Gur; Jiantao Pu Journal: Comput Med Imaging Graph Date: 2014-01-25 Impact factor: 4.790