EP-1902: Impact of image quality on DIR performances: results from a multi-institutional study (original) (raw)
Related papers
Journal of Applied Clinical Medical Physics
Purpose: The purpose of this study was to evaluate the performance of three common deformable image registration (DIR) packages across algorithms and institutions. Methods and Materials: The Deformable Image Registration Evaluation Project (DIREP) provides ten virtual phantoms derived from computed tomography (CT) datasets of head-and-neck cancer patients over a single treatment course. Using the DIREP phantoms, DIR results from 35 institutions were submitted using either Velocity, MIM, or Eclipse. Submitted deformation vector fields (DVFs) were compared to ground-truth DVFs to calculate target registration error (TRE) for six regions of interest (ROIs). Statistical analysis was performed to determine the variability between each DIR software package and the variability of users within each algorithm. Results: Overall mean TRE was 2.04 ± 0.35 mm for Velocity, 1.10 ± 0.29 mm for MIM, and 2.35 ± 0.15 mm for Eclipse. The MIM mean TRE was significantly different than both Velocity and Eclipse for all ROIs. Velocity and Eclipse mean TREs were not significantly different except for when evaluating the registration of the cord or mandible. Significant differences between institutions were found for the MIM and Velocity platforms. However, these differences could be explained by variations in Velocity DIR parameters and MIM software versions. Conclusions: Average TRE was shown to be <3 mm for all three software platforms. However, maximum errors could be larger than 2 cm indicating that care should be exercised when using DIR. While MIM performed statistically better than the other packages, all evaluated algorithms had an average TRE better than the largest voxel dimension. For the phantoms studied here, significant differences between algorithm users were minimal suggesting that the algorithm used may have more impact on DIR accuracy than the particular registration technique employed. A significant difference in TRE was discovered between MIM versions showing that DIR QA should be performed after software upgrades as recommended by TG-132.
Evaluation of Deformable Image Registration
2015
Deformable image registration (DIR) is a type of registration that calculates a deformable vector field (DVF) between two image data sets and permits contour and dose propagation. However the calculation of a DVF is considered an ill-posed problem, as there is no exact solution to a deformation problem, therefore all DVFs calculated contain errors. As a result it is important to evaluate and assess the accuracy and limitations of any DIR algorithm intended for clinical use. The influence of image quality on the DIR algorithms performance was also evaluated. The hybrid DIR algorithm in RayStation 4.0.1.4 was assessed using a number of evaluation methods and data. The evaluation methods were point of interest (POI) propagation, contour propagation and dose measurements. The data types used were phantom and patient data. A number of metrics were used for quantitative analysis and visual inspection was used for qualitative analysis. The quantitative and qualitative results indicated tha...
Physics in Medicine and Biology, 2014
Previous methods to estimate the inherent accuracy of deformable image registration (DIR) have typically been performed relative to a known ground truth, such as tracking of anatomic landmarks or known deformations in a physical or virtual phantom. In this study, we propose a new approach to estimate the spatial geometric uncertainty of DIR using statistical sampling techniques that can be applied to the resulting deformation vector fields (DVFs) for a given registration. The proposed DIR performance metric, the distance discordance metric (DDM), is based on the variability in the distance between corresponding voxels from different images, which are co-registered to the same voxel at location (X) in an arbitrarily chosen 'reference' image. The DDM value, at location (X) in the reference image, represents the mean dispersion between voxels, when these images are registered to other images in the image set. The method requires at least four registered images to estimate 6 the uncertainty of the DIRs, both for inter-and intra-patient DIR. To validate the proposed method, we generated an image set by deforming a software phantom with known DVFs. The registration error was computed at each voxel in the 'reference' phantom and then compared to DDM, inverse consistency error (ICE), and transitivity error (TE) over the entire phantom. The DDM showed a higher Pearson correlation (R p ) with the actual error (R p ranged from 0.6 to 0.9) in comparison with ICE and TE (R p ranged from 0.2 to 0.8). In the resulting spatial DDM map, regions with distinct intensity gradients had a lower discordance and therefore, less variability relative to regions with uniform intensity. Subsequently, we applied DDM for intra-patient DIR in an image set of ten longitudinal computed tomography (CT) scans of one prostate cancer patient and for inter-patient DIR in an image set of ten planning CT scans of different head and neck cancer patients. For both intra-and inter-patient DIR, the spatial DDM map showed large variation over the volume of interest (the pelvis for the prostate patient and the head for the head and neck patients). The highest discordance was observed in the soft tissues, such as the brain, bladder, and rectum, due to higher variability in the registration. The smallest DDM values were observed in the bony structures in the pelvis and the base of the skull. The proposed metric, DDM, provides a quantitative tool to evaluate the performance of DIR when a set of images is available. Therefore, DDM can be used to estimate and visualize the uncertainty of intra-and/or inter-patient DIR based on the variability of the registration rather than the absolute registration error.
Semi-Automated Quality Assurance of Deformable Image Registration
2019
This interdisciplinary project plans to implement big data resources from CERN to provide a method for semi-automated quality assurance of patient registration. The study used computed tomography scans and spinal canal contours of 90 head-and-neck cancer patients from the publicly listed Centuximab collection. Inter-patient deformable registrations were performed on this cohort to produce a bank of 876 registrations each labelled with two contour validation metrics: the Dice similarity coefficient and the Hausdorff distance. The deformable vector field of each registration was used in combination with patient data to train two 3D convolutional neural networks to predict each contour validation metric. A workflow for this novel method and its initial test results are presented. Access to CERN's multiple-site grid computing resources will allow the increase in the registration dataset by an order of magnitude and the training and testing of deeper network architectures.
Accuracy quantification of a deformable image registration tool applied in a clinical setting
Journal of applied clinical medical physics / American College of Medical Physics, 2014
The purpose of this study was to test the accuracy of a commercially available deformable image registration tool in a clinical situation. In addition, to demonstrate a method to evaluate the resulting transformation of such a tool to a reference defined by multiple experts. For 16 patients (seven head and neck, four thoracic, five abdominal), 30-50 anatomical landmarks were defined on recognizable spots of a planning CT and a corresponding fraction CT. A commercially available deformable image registration tool, Velocity AI, was used to align all fraction CTs with the respective planning CTs. The registration accuracy was quantified by means of the target registration error in respect to expert-defined landmarks, considering the interobserver variation of five observers. The interobserver uncertainty of the landmark definition in our data sets is found to be 1.2 ± 1.1 mm. In general the deformable image registration tool decreases the extent of observable misalignments from 4-8 mm ...
Physics in Medicine and Biology, 2013
Rationale and Objectives-Landmark point-pairs provide a strategy to assess deformable image registration (DIR) accuracy in terms of the spatial registration of the underlying anatomy depicted in medical images. In this study, we propose to augment a publicly available database (www.dir-lab.com) of medical images with large sets of manually identified anatomic feature pairs between breath-hold computed tomography (BH-CT) images for DIR spatial accuracy evaluation. Materials and Methods-10 BH-CT image pairs were randomly selected from the COPDgene study cases. Each patient had received CT imaging of the entire thorax in the supine position at 1/4 th dose normal expiration and maximum effort full dose inspiration. Using dedicated in-house software, an imaging expert manually identified large sets of anatomic feature pairs between images. Estimates of inter-and intra-observer spatial variation in feature localization were determined by repeat measurements of multiple observers over subsets of randomly selected features. Results-7298 anatomic landmark features were manually paired between the 10 sets of images. Quantity of feature pairs per case ranged from 447 to 1172. Average 3D Euclidean landmark displacements varied substantially among cases, ranging from 12.29 (SD: 6.39) to 30.90 (SD: 14.05) mm. Repeat registration of uniformly sampled subsets of 150 landmarks for each case yielded estimates of observer localization error, which ranged in average from 0.58 (SD: 0.87) to 1.06 (SD: 2.38) mm for each case. Conclusions-The additions to the online web database (www.dir-lab.com) described in this work will broaden the applicability of the reference data, providing a freely available common dataset for targeted critical evaluation of DIR spatial accuracy performance in multiple clinical settings. Estimates of observer variance in feature localization suggest consistent spatial accuracy for all observers across both 4D CT and COPDgene patient cohorts.
Physics in Medicine and Biology, 2009
Expert landmark correspondences are widely reported for evaluating deformable image registration (DIR) spatial accuracy. In this report, we present a framework for objective evaluation of DIR spatial accuracy using large sets of expert-determined landmark point pairs. Large samples (>1100) of pulmonary landmark point pairs were manually generated for five cases. Estimates of inter- and intra-observer variation were determined from repeated registration. Comparative evaluation of DIR spatial accuracy was performed for two algorithms, a gradient-based optical flow algorithm and a landmark-based moving least-squares algorithm. The uncertainty of spatial error estimates was found to be inversely proportional to the square root of the number of landmark point pairs and directly proportional to the standard deviation of the spatial errors. Using the statistical properties of this data, we performed sample size calculations to estimate the average spatial accuracy of each algorithm with 95% confidence intervals within a 0.5 mm range. For the optical flow and moving least-squares algorithms, the required sample sizes were 1050 and 36, respectively. Comparative evaluation based on fewer than the required validation landmarks results in misrepresentation of the relative spatial accuracy. This study demonstrates that landmark pairs can be used to assess DIR spatial accuracy within a narrow uncertainty range.
Quantitative evaluation of a deformable registration toolkit
An open source software, plastimatch, for deformable image registration was tested. Image registration was performed on the basis of a B-spline transformation algorithm on 4DCT data. Registration parameters were set according to an iterative optimization procedure minimizing the image difference residuals. The validation process was focused on assessing precision, accuracy, reliability and stability of the algorithm. Results showed good performances of the algorithm. Precision error magnitude was within the voxel size value. For accuracy, at least 90% of the voxels of the warped image were in the range of ±20HU. Reliability and stability of the algorithm were proven by non parametric statistical analysis. In conclusion, plastimatch allows robust image registration for CT modality; optimal transformation parameters can be automatically selected on a patient-based scale. Future work will be devoted to assess the clinical use of the software in the field of Image Guided Adaptive Radiation Therapy.
3-D Deformable Registration of Medical Images Using a Statistical Atlas
Lecture Notes in Computer Science, 1999
Registration between voxel images of human anatomy enables cross-patient diagnosis and post-treatment analysis. However, innate variations in the shape, size, and density of non-pathological anatomical structures between individuals make accurate registration difficult. Characterization of such normal but inherent variations provides guidance for registration.We extracted the pattern of normal variations in the appearances of brain structures from the T1-weighted magnetic resonance imaging (MRI) volumes of 105 subjects. This knowledge serves as a domain-relevant constraint which increases the accuracy of deformable registration.