Performance validation of deformable image registration in the pelvic region

Evaluation of the geometric and dosimetric accuracies of deformable image registration of targets and critical organs in prostate CBCT-guided adaptive radiotherapy

PURPOSE

Kilovoltage cone beam computed tomography (kVCBCT)-guided adaptive radiation therapy (ART) uses daily deformed CT (dCT), which is generated automatically through deformable registration methods. These registration methods may perform poorly in reproducing volumes of the target organ, rectum, and bladder during treatment. We analyzed the registration errors between the daily kVCBCTs and corresponding dCTs for these organs using the default optical flow algorithm and two registration procedures. We validated the effectiveness of these registration methods in replicating the geometry for dose calculation on kVCBCT for ART.

METHODS

We evaluated three deformable image registration (DIR) methods to assess their registration accuracy and dose calculation effeciency in mapping target and critical organs. The DIR methods include (1) default intensity-based deformable registration, (2) hybrid deformable registration, and (3) a two-step deformable registration process. Each technique was applied to a computerized imaging reference system (CIRS) phantom (Model 062 M) and to five patients who received volumetric modulated arc therapy to the prostate. Registration accuracy was assessed using the 95% Hausdorff distance (HD95) and Dice similarity coefficient (DSC), and each method was compared with the intensity-based registration method. The improvement in the dCT image quality of the CIRS phantom and five patients was assessed by comparing dCT with kVCBCT. Image quality quantitative metrics for the phantom included the signal-to-noise ratio (SNR), uniformity, and contrast-to-noise ratio (CNR), whereas those for the patients included the mean absolute error (MAE), mean error, peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). To determine dose metric differences, we used a dose-volume histogram (DVH) and 3.0%/0.3 mm gamma analysis to compare planning computed tomography (pCT) and kVCBCT recalculations with restimulated CT images used as a reference.

RESULTS

The dCT images generated by the hybrid (dCTH) and two-step (dCTC) registration methods resulted in significant improvements compared to kVCBCT in the phantom model. Specifically, the SNR improved by 107% and 107.2%, the uniformity improved by 90% and 75%, and the CNR improved by 212.2% and 225.6 for dCTH and dCTC methods, respectively. For the patient images, the MAEs improved by 98% and 94%, the PSNRs improved by 16.3% and 22.9%, and the SSIMs improved by 1% and 1% in the dCTH and dCTC methods, respectively. For the geometric evaluation, only the two-step registration method improved registration accuracy. The dCTH method yielded an average HD95 of 12 mm and average DSC of 0.73, whereas dCTC yielded an average HD95 of 2.9 mm and average DSC of 0.902. The DVH showed that the dCTC-based dose calculations differed by <2% from the expected results for treatment targets and volumes of organs at risk. Additionally, gamma indices for dCTC-based treatment plans were >95% at all points, whereas they were <95% for kVCBCT-based treatment plans.

CONCLUSION

The two-step registration method outperforms the intensity-based and hybrid registration methods. While the hybrid and two-step-based methods improved the image quality of kVCBCT in a linear accelerator, only the two-step method improved the registration accuracy of the corresponding structures among the pCT and kVCBCT datasets. A two-step registration process is recommended for applying kVCBCT to ART, which achieves better registration accuracy for local and global image structures. This method appears to be beneficial for radiotherapy dose calculation in patients with pelvic cancer.

Clinical evaluation of a deep learning CBCT auto-segmentation software for prostate adaptive radiation therapy

Purpose

Aim of the present study is to characterize a deep learning-based auto-segmentation software (DL) for prostate cone beam computed tomography (CBCT) images and to evaluate its applicability in clinical adaptive radiation therapy routine.

Materials and methods

Ten patients, who received exclusive radiation therapy with definitive intent on the prostate gland and seminal vesicles, were selected. Femoral heads, bladder, rectum, prostate, and seminal vesicles were retrospectively contoured by four different expert radiation oncologists on patients CBCT, acquired during treatment. Consensus contours (CC) were generated starting from these data and compared with those created by DL with different algorithms, trained on CBCT (DL-CBCT) or computed tomography (DL-CT). Dice similarity coefficient (DSC), centre of mass (COM) shift and volume relative variation (VRV) were chosen as comparison metrics. Since no tolerance limit can be defined, results were also compared with the inter-operator variability (IOV), using the same metrics.

Results

The best agreement between DL and CC was observed for femoral heads (DSC of 0.96 for both DL-CBCT and DL-CT). Performance worsened for low-contrast soft tissue organs: the worst results were found for seminal vesicles (DSC of 0.70 and 0.59 for DL-CBCT and DL-CT, respectively). The analysis shows that it is appropriate to use algorithms trained on the specific imaging modality. Furthermore, the statistical analysis showed that, for almost all considered structures, there is no significant difference between DL-CBCT and human operator in terms of IOV.

Conclusions

The accuracy of DL-CBCT is in accordance with CC; its use in clinical practice is justified by the comparison with the inter-operator variability.

CBCT-based deformable dose accumulation of external beam radiotherapy in cervical cancer

Background: Delivered radiotherapy doses do not exactly match those planned for a course of treatment, largely due to inter-fraction changes in anatomy. In this study, accumulated delivered dose was calculated for a sample of cervical cancer patients, by deformably registering daily cone beam computed tomography (CBCT) images to the planning computed tomography (CT) scan. Planned and accumulated doses were compared for the clinical target volume (CTV), bladder, and rectum.Material and Methods: For 10 patients receiving 45 Gy in 25 fractions of external beam radiotherapy, daily dose distributions were calculated on CBCT. These images were deformed onto the planning CT and the dose was accumulated using Velocity 4.1 (Varian Medical Systems, Palo Alto, USA). The quality of deformable image registration was evaluated visually and by calculating Dice similarity coefficients and mean distance to agreement.Results: V95%>99% was achieved for the primary CTV in 9/10 patients for the planned dose distribution and 7/10 patients for the accumulated dose distribution. Primary CTV coverage by 95% of the prescription dose was reduced in one patient, due to an increase in anterior-posterior separation. Comparison of planned and accumulated dose volume histograms (DVHs) for the bladder and rectum found agreement within 5% at low and intermediate doses, but differences exceeded 20% at higher doses. Direct addition of CBCT DVHs was seen to be a poor estimate for the accumulated DVH at higher doses.Conclusion: Computation of delivered radiotherapy dose that accounts for inter-fraction anatomical changes is important for establishing dose-effect relationships. Updating delivered dose distributions after each fraction would support informed clinical decision making on any potential treatment interventions.

Deep learning-based segmentation in prostate radiation therapy using Monte Carlo simulated cone-beam computed tomography

PURPOSE

Segmenting organs in cone-beam CT (CBCT) images would allow to adapt the radiotherapy based on the organ deformations that may occur between treatment fractions. However, this is a difficult task because of the relative lack of contrast in CBCT images, leading to high inter-observer variability. Deformable image registration (DIR) and deep-learning based automatic segmentation approaches have shown interesting results for this task in the past years. However, they are either sensitive to large organ deformations, or require to train a convolutional neural network (CNN) from a database of delineated CBCT images, which is difficult to do without improvement of image quality. In this work, we propose an alternative approach: to train a CNN (using a deep learning-based segmentation tool called nnU-Net) from a database of artificial CBCT images simulated from planning CT, for which it is easier to obtain the organ contours.

METHODS

Pseudo-CBCT (pCBCT) images were simulated from readily available segmented planning CT images, using the GATE Monte Carlo simulation. CT reference delineations were copied onto the pCBCT, resulting in a database of segmented images used to train the neural network. The studied segmentation contours were: bladder, rectum, and prostate contours. We trained multiple nnU-Net models using different training: (1) segmented real CBCT, (2) pCBCT, (3) segmented real CT and tested on pseudo-CT (pCT) generated from CBCT with cycleGAN, and (4) a combination of (2) and (3). The evaluation was performed on different datasets of segmented CBCT or pCT by comparing predicted segmentations with reference ones thanks to Dice similarity score and Hausdorff distance. A qualitative evaluation was also performed to compare DIR-based and nnU-Net-based segmentations.

RESULTS

Training with pCBCT was found to lead to comparable results to using real CBCT images. When evaluated on CBCT obtained from the same hospital as the CT images used in the simulation of the pCBCT, the model trained with pCBCT scored mean DSCs of 0.92 ± 0.05, 0.87 ± 0.02, and 0.85 ± 0.04 and mean Hausdorff distance 4.67 ± 3.01, 3.91 ± 0.98, and 5.00 ± 1.32 for the bladder, rectum, and prostate contours respectively, while the model trained with real CBCT scored mean DSCs of 0.91 ± 0.06, 0.83 ± 0.07, and 0.81 ± 0.05 and mean Hausdorff distance 5.62 ± 3.24, 6.43 ± 5.11, and 6.19 ± 1.14 for the bladder, rectum, and prostate contours, respectively. It was also found to outperform models using pCT or a combination of both, except for the prostate contour when tested on a dataset from a different hospital. Moreover, the resulting segmentations demonstrated a clinical acceptability, where 78% of bladder segmentations, 98% of rectum segmentations, and 93% of prostate segmentations required minor or no corrections, and for 76% of the patients, all structures of the patient required minor or no corrections.

CONCLUSION

We proposed to use simulated CBCT images to train a nnU-Net segmentation model, avoiding the need to gather complex and time-consuming reference delineations on CBCT images.

Evaluation of DIR algorithm performance in real patients for radiotherapy treatments: A systematic review of operator-dependent strategies

PURPOSE

The performance of deformable medical image registration (DIR) algorithms has become a major concern.

METHODS

We aimed to obtain updated information on DIR algorithm performance quantification through a literature review of articles published between 2010 and 2022. We focused only on studies using operator-based methods to treat real patients. The PubMed, Google Scholar and Embase databases were searched following PRISMA guidelines.

RESULTS

One hundred and seven articles were identified. The mean number of patients and registrations per publication was 20 and 63, respectively. We found 23 different geometric metrics appearing at least twice, and the dosimetric impact of DIR was quantified in 32 articles. Forty-eight different at-risk organs were described, and target volumes were studied in 43 publications. Prostate, head-and-neck and thoracic locations represented more than ¾ of the studied locations. We summarized the type of DIR and the images used, and other key elements. Intra/interobserver variability, threshold values and the correlation between metrics were also discussed.

CONCLUSIONS

This literature review covers the past decade and should facilitate the implementation of DIR algorithms in clinical practice by providing practical and pertinent information to quantify their performance on real patients.

Domain adversarial networks and intensity-based data augmentation for male pelvic organ segmentation in cone beam CT

In radiation therapy, a CT image is used to manually delineate the organs and plan the treatment. During the treatment, a cone beam CT (CBCT) is often acquired to monitor the anatomical modifications. For this purpose, automatic organ segmentation on CBCT is a crucial step. However, manual segmentations on CBCT are scarce, and models trained with CT data do not generalize well to CBCT images. We investigate adversarial networks and intensity-based data augmentation, two strategies leveraging large databases of annotated CTs to train neural networks for segmentation on CBCT. Adversarial networks consist of a 3D U-Net segmenter and a domain classifier. The proposed framework is aimed at encouraging the learning of filters producing more accurate segmentations on CBCT. Intensity-based data augmentation consists in modifying the training CT images to reduce the gap between CT and CBCT distributions. The proposed adversarial networks reach DSCs of 0.787, 0.447, and 0.660 for the bladder, rectum, and prostate respectively, which is an improvement over the DSCs of 0.749, 0.179, and 0.629 for "source only" training. Our brightness-based data augmentation reaches DSCs of 0.837, 0.701, and 0.734, which outperforms the morphons registration algorithms for the bladder (0.813) and rectum (0.653), while performing similarly on the prostate (0.731). The proposed adversarial training framework can be used for any segmentation application where training and test distributions differ. Our intensity-based data augmentation can be used for CBCT segmentation to help achieve the prescribed dose on target and lower the dose delivered to healthy organs.

Unsupervised learning for deformable registration of thoracic CT and cone-beam CT based on multiscale features matching with spatially adaptive weighting

PURPOSE

Cone-beam computed tomography (CBCT) is a common on-treatment imaging widely used in image-guided radiotherapy. Fast and accurate registration between the on-treatment CBCT and planning CT is significant for and precise adaptive radiotherapy treatment (ART). However, existing CT-CBCT registration methods, which are mostly affine or time-consuming intensity- based deformation registration, still need further study due to the considerable CT-CBCT intensity discrepancy and the artifacts in low-quality CBCT images. In this paper, we propose a deep learning-based CT-CBCT registration model to promote rapid and accurate CT-CBCT registration for radiotherapy.

METHODS

The proposed CT-CBCT registration model consists of a registration network and an innovative deep similarity metric network. The registration network is a novel fully convolution network adapted specially for patch-wise CT-CBCT registration. The metric network, going beyond intensity, automatically evaluates the high-dimensional attribute-based dissimilarity between the registered CT and CBCT images. In addition, considering the artifacts in low-quality CBCT images, we add spatial weighting (SW) block to adaptively attach more importance to those informative voxels while inhibit the interference of artifact regions. Such SW-based metric network is expected to extract the most meaningful and discriminative deep features, and form a more reliable CT-CBCT similarity measure to train the registration network.

RESULTS

We evaluate the proposed method on clinical thoracic CBCT and CT dataset, and compare the registration results with some other common image similarity metrics and some state-of-the-art registration algorithms. The proposed method provides the highest Structural Similarity index (86.17 ± 5.09), minimum Target Registration Error of landmarks (2.37 ± 0.32 mm), and the best DSC coefficient (78.71 ± 10.95) of tumor volumes. Moreover, our model also obtains comparable distance error of lung surfaces (1.75 ± 0.35 mm).

CONCLUSION

The proposed model shows both efficiency and efficacy for reliable thoracic CT-CBCT registration, and can generate the matched CT and CBCT images within few seconds, which is of great significance to clinical radiotherapy.

Accuracy of multimodal image fusion for oral and maxillofacial tumors: A revised evaluation method and its application

OBJECTIVE

To develop a revised evaluation method for accuracy of multimodal image fusion for oral and maxillofacial tumors and explore its application for comparing the accuracy of three commonly used fusion algorithms, automatic fusion, manual fusion, and registration point-based fusion.

MATERIALS AND METHODS

Image sets of patients with oral and maxillofacial tumor were fused using the iPlan 3.0 navigation system. Fusion accuracy included two aspects: (1) overall fusion accuracy: represented by the mean value of the coordinate differences along the x-, y-, and z- axes (Δx, Δy, and Δz), mean deviation (MD), and root mean square (RMS) of six pairs of landmarks on the two image sets; (2) tumor volume fusion accuracy: represented by Fusion Index (FI), which was calculated based on the volume of tumor delineated on the two image sets.

RESULTS

Eighteen pairs of image sets of 17 patients were enrolled in this study. The Δx and Δy values for the three algorithms were less than 1.5 mm. The Δz values for automatic fusion, manual fusion and registration point-based fusion was 1.049 mm, 1.864 mm and 1.254 mm. The MD for automatic fusion, manual fusion and registration point-based fusion was 1.978 mm, 2.788 mm and 1.926 mm. Significant differences existed in Δz for manual fusion and that for automatic fusion (P = 0.058), in MD for manual fusion and that for automatic fusion (P = 0.087), and in MD for manual fusion and that for registration point-based fusion (P = 0.069). The FI for automatic fusion, manual fusion, and registration point-based fusion was 0.594, 0.520, and 0.549; the inter-algorithm differences were not significant (P = 0.290).

CONCLUSION

The automatic fusion and the registration point-based fusion were more accurate than manual fusion, and therefore were recommended to be used in multimodal image fusion for oral and maxillofacial tumors.

Dosimetric impact of organ at risk daily variation during prostate stereotactic ablative radiotherapy

OBJECTIVE

Prostate stereotactic ablative radiotherapy (SABR) delivers large doses using a fast dose rate. This amplifies the effect geometric uncertainties have on normal tissue dose. The aim of this study was to determine whether the treatment dose-volume histogram (DVH) agrees with the planned dose to organs at risk (OAR).

METHODS

41 low-intermediate risk prostate cancer patients were treated with SABR using a linac based technique. Dose prescribed was 35 Gy in five fractions delivered on alternate days, planned using volumetric modulated arc therapy (VMAT) with 10X flattening filter free (FFF). On treatment, prostate was matched to fiducial markers on cone beam CT (CBCT). OAR were retrospectively delineated on 205 pre-treatment CBCT images. Daily CBCT contours were overlaid on the planning CT for dosimetric analysis. Verification plan used to evaluate the daily DVH for each structure. The daily doses received by OAR were recorded using the D%.

RESULTS

The median rectum and bladder volumes at planning were 67.1 cm3 (interquartile range 56.4-78.2) and 164.4 cm3 (interquartile range 120.3-213.4) respectively. There was no statistically significant difference in median rectal volume at each of the five treatment scans compared to the planning scan (p = 0.99). This was also the case for median bladder volume (p = 0.79). The median dose received by rectum and bladder at each fraction was higher than planned, at the majority of dose levels. For rectum the increase ranged from 0.78-1.64Gy and for bladder 0.14-1.07Gy. The percentage of patients failing for rectum D35% < 18 Gy (p = 0.016), D10% < 28 Gy (p = 0.004), D5% < 32 Gy (p = 0.0001), D1% < 35 Gy (p = 0.0001) and bladder D1% < 35 Gy (p = 0.001) at treatment were all statistically significant.

CONCLUSION

In this cohort of prostate SABR patients, we estimate the OAR treatment DVH was higher than planned. This was due to rectal and bladder organ variation.

ADVANCES IN KNOWLEDGE

OAR variation in prostate SABR using a FFF technique, may cause the treatment DVH to be higher than planned.

Associations between voxel-level accumulated dose and rectal toxicity in prostate radiotherapy

Background and Purpose

Associations between dose and rectal toxicity in prostate radiotherapy are generally poorly understood. Evaluating spatial dose distributions to the rectal wall (RW) may lead to improvements in dose-toxicity modelling by incorporating geometric information, masked by dose-volume histograms. Furthermore, predictive power may be strengthened by incorporating the effects of interfraction motion into delivered dose calculations.Here we interrogate 3D dose distributions for patients with and without toxicity to identify rectal subregions at risk (SRR), and compare the discriminatory ability of planned and delivered dose.

Material and Methods

Daily delivered dose to the rectum was calculated using image guidance scans, and accumulated at the voxel level using biomechanical finite element modelling. SRRs were statistically determined for rectal bleeding, proctitis, faecal incontinence and stool frequency from a training set (n = 139), and tested on a validation set (n = 47).

Results

SRR patterns differed per endpoint. Analysing dose to SRRs improved discriminative ability with respect to the full RW for three of four endpoints. Training set AUC and OR analysis produced stronger toxicity associations from accumulated dose than planned dose. For rectal bleeding in particular, accumulated dose to the SRR (AUC 0.76) improved upon dose-toxicity associations derived from planned dose to the RW (AUC 0.63). However, validation results could not be considered significant.

Conclusions

Voxel-level analysis of dose to the RW revealed SRRs associated with rectal toxicity, suggesting non-homogeneous intra-organ radiosensitivity. Incorporating spatial features of accumulated delivered dose improved dose-toxicity associations. This may be an important tool for adaptive radiotherapy in the future.

Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT

For prostate cancer patients, large organ deformations occurring between radiotherapy treatment sessions create uncertainty about the doses delivered to the tumor and surrounding healthy organs. Segmenting those regions on cone beam CT (CBCT) scans acquired on treatment day would reduce such uncertainties. In this work, a 3D U-net deep-learning architecture was trained to segment bladder, rectum, and prostate on CBCT scans. Due to the scarcity of contoured CBCT scans, the training set was augmented with CT scans already contoured in the current clinical workflow. Our network was then tested on 63 CBCT scans. The Dice similarity coefficient (DSC) increased significantly with the number of CBCT and CT scans in the training set, reaching 0.874 ± 0.096 , 0.814 ± 0.055 , and 0.758 ± 0.101 for bladder, rectum, and prostate, respectively. This was about 10% better than conventional approaches based on deformable image registration between planning CT and treatment CBCT scans, except for prostate. Interestingly, adding 74 CT scans to the CBCT training set allowed maintaining high DSCs, while halving the number of CBCT scans. Hence, our work showed that although CBCT scans included artifacts, cross-domain augmentation of the training set was effective and could rely on large datasets available for planning CT scans.

Optimizing planning CT using past CT images for prostate cancer volumetric modulated arc therapy

This study aimed to evaluate a new method to optimize planning computed tomography (CT) using three-dimensional (3D) displacement error between the planning and diagnosed past CT scans. Thirty-two patients undergoing volumetric modulated arc therapy for prostate cancer were evaluated for a 3D displacement error between bone- and prostate-matching spatial coordinates using multiple acquisition planning CT (MPCT) scans. Each MPCT image and a past CT image were used to perform rigid image registration (RIR) and deformable image registration (DIR), and the 3D displacement error was calculated. Correlations of the 3D displacement error in each MPCT scan and between the MPCT and past CT were evaluated based on RIR and DIR, respectively. The 3D displacement error in the MPCT images exhibited moderate correlation with the 3D displacement error between MPCT and past CT for both RIR (adjusted r² = 0.495) and DIR (adjusted r² = 0.398). In the correlation analysis between MPCT and past CT, image pairs with 3D displacement errors ≥ 6 mm were significantly different from those with errors < 6 mm (p < 0.0001). Past CT images were different from the planning CT images, which can be attributed to setup tools, flat-top plates, and physical differences due to the presence or absence of urine as well as prescription effects. The relationship between bone and prostate exhibited small deviations between the planning and past CT regardless of pretreatment. The prostate, which only has a slight effect on the displacement between it and bladder volume, was covered with a stiff pelvic bone. As a result, MPCT images exhibited correlations with past CT images of various difference states such as body positions. Finally, large 3D displacement errors in prostate position were caused by pelvic tension and stress, which can be detected using diagnosed past CT images instead of requiring MPCT scans. By comparing past and planning CT images, the random displacement error in the planning CT scan can be avoided by evaluating 3D displacement errors. The new method using the past CT images can estimate the displacement error of the prostate during the treatment period with 1 plan CT scan only, and it helps improve the treatment accuracy.

[Improvement Prediction on Contour Deformation Accuracy Using Deformable Image Registration Results Compared to Rigid Image Registration Results]

PURPOSE

The aim of this study was to analyze improvement prediction on contour deformation accuracy using deformable image registration (DIR) results compared to rigid image registration (RIR) results.

METHOD

Radiotherapy plans for 31 cases (seven head and neck cases, 10 chest cases, six abdomen cases and eight female pelvis cases) from the privately open database for DIR were used. These cases used at least two radiotherapy plans, and registration was performed using two plans, not only for one case but also for different cases. The DIR and RIR were performed using the DIR software MIM Maestro (MIM software Inc., Cleveland, USA). The registration results for the following organs were analyzed: eye balls, optic nerves, brain stem, spinal cord and right and left parotid glands for head and neck; right and left lungs for chest; liver and right and left kidneys for abdomen; and rectum and bladder for pelvis. Dice similarity coefficient (DSC) for the organs was calculated from the results of RIR and DIR. The improvement in the DSC was observed.

RESULTS AND DISCUSSION

DIR improved the DSC values by more than 0.2 for simple shapes, well-defined boundaries and large volumes such as eye balls, brain stem, lungs and liver. The minimum DSC for these organs was approximately 0.7. The improvement in DSC for the organs eye balls, brain stem, lungs and liver had ceiling values 0.95, 0.90, 1.0 and 1.0, respectively. DSC for the spinal cord, parotid gland, bladder and kidney also improved by DIR compared to RIR; however, DIR could not improve the DSC value for rectum compared to RIR because of a large difference in the position, shape and size due to stool and gas.

Autosegmentation of the rectum on megavoltage image guidance scans

Autosegmentation of image guidance (IG) scans is crucial for streamlining and optimising delivered dose calculation in radiotherapy. By accounting for interfraction motion, daily delivered dose can be accumulated and incorporated into automated systems for adaptive radiotherapy. Autosegmentation of IG scans is challenging due to poorer image quality than typical planning kilovoltage computed tomography (kVCT) systems, and the resulting reduction of soft tissue contrast in regions such as the pelvis makes organ boundaries less distinguishable. Current autosegmentation solutions generally involve propagation of planning contours to the IG scan by deformable image registration (DIR). Here, we present a novel approach for primary autosegmentation of the rectum on megavoltage IG scans acquired during prostate radiotherapy, based on the Chan-Vese algorithm. Pre-processing steps such as Hounsfield unit/intensity scaling, identifying search regions, dealing with air, and handling the prostate, are detailed. Post-processing features include identification of implausible contours (nominally those affected by muscle or air), 3D self-checking, smoothing, and interpolation. In cases where the algorithm struggles, the best estimate on a given slice may revert to the propagated kVCT rectal contour. Algorithm parameters were optimised systematically for a training cohort of 26 scans, and tested on a validation cohort of 30 scans, from 10 patients. Manual intervention was not required. Comparing Chan-Vese autocontours with contours manually segmented by an experienced clinical oncologist achieved a mean Dice Similarity Coefficient of 0.78 (SE < 0.011). This was comparable with DIR methods for kVCT and CBCT published in the literature. The autosegmentation system was developed within the VoxTox Research Programme for accumulation of delivered dose to the rectum in prostate radiotherapy, but may have applicability to further anatomical sites and imaging modalities.

Evaluation of automatic contour propagation in T2-weighted 4DMRI for normal-tissue motion assessment using internal organ-at-risk volume (IRV)

Purpose

The purpose of this study was to evaluate the quality of automatically propagated contours of organs at risk (OARs) based on respiratory‐correlated navigator‐triggered four‐dimensional magnetic resonance imaging (RC‐4DMRI) for calculation of internal organ‐at‐risk volume (IRV) to account for intra‐fractional OAR motion.

Methods and Materials

T2‐weighted RC‐4DMRI images were of 10 volunteers acquired and reconstructed using an internal navigator‐echo surrogate and concurrent external bellows under an IRB‐approved protocol. Four major OARs (lungs, heart, liver, and stomach) were delineated in the 10‐phase 4DMRI. Two manual‐contour sets were delineated by two clinical personnel and two automatic‐contour sets were propagated using free‐form deformable image registration. The OAR volume variation within the 10‐phase cycle was assessed and the IRV was calculated as the union of all OAR contours. The OAR contour similarity between the navigator‐triggered and bellows‐rebinned 4DMRI was compared. A total of 2400 contours were compared to the most probable ground truth with a 95% confidence level (S95) in similarity, sensitivity, and specificity using the simultaneous truth and performance level estimation (STAPLE) algorithm.

Results

Visual inspection of automatically propagated contours finds that approximately 5–10% require manual correction. The similarity, sensitivity, and specificity between manual and automatic contours are indistinguishable (P > 0.05). The Jaccard similarity indexes are 0.92 ± 0.02 (lungs), 0.89 ± 0.03 (heart), 0.92 ± 0.02 (liver), and 0.83 ± 0.04 (stomach). Volume variations within the breathing cycle are small for the heart (2.6 ± 1.5%), liver (1.2 ± 0.6%), and stomach (2.6 ± 0.8%), whereas the IRV is much larger than the OAR volume by: 20.3 ± 8.6% (heart), 24.0 ± 8.6% (liver), and 47.6 ± 20.2% (stomach). The Jaccard index is higher in navigator‐triggered than bellows‐rebinned 4DMRI by 4% (P < 0.05), due to the higher image quality of navigator‐based 4DMRI.

Conclusion

Automatic and manual OAR contours from Navigator‐triggered 4DMRI are not statistically distinguishable. The navigator‐triggered 4DMRI image provides higher contour quality than bellows‐rebinned 4DMRI. The IRVs are 20–50% larger than OAR volumes and should be considered in dose estimation.

A graphical approach to optimizing variable-kernel smoothing parameters for improved deformable registration of CT and cone beam CT images

A systematic method is presented for determining optimal parameters in variable-kernel deformable image registration of cone beam CT and CT images, in order to improve accuracy and convergence for potential use in online adaptive radiotherapy. Assessed conditions included the noise constant (symmetric force demons), the kernel reduction rate, the kernel reduction percentage, and the kernel adjustment criteria. Four such parameters were tested in conjunction with reductions of 5, 10, 15, 20, 30, and 40%. Noise constants ranged from 1.0 to 1.9 for pelvic images in ten prostate cancer patients. A total of 516 tests were performed and assessed using the structural similarity index. Registration accuracy was plotted as a function of iteration number and a least-squares regression line was calculated, which implied an average improvement of 0.0236% per iteration. This baseline was used to determine if a given set of parameters under- or over-performed. The most accurate parameters within this range were applied to contoured images. The mean Dice similarity coefficient was calculated for bladder, prostate, and rectum with mean values of 98.26%, 97.58%, and 96.73%, respectively; corresponding to improvements of 2.3%, 9.8%, and 1.2% over previously reported values for the same organ contours. This graphical approach to registration analysis could aid in determining optimal parameters for Demons-based algorithms. It also establishes expectation values for convergence rates and could serve as an indicator of non-physical warping, which often occurred in cases  >0.6% from the regression line.

Evaluation of the performance of deformable image registration between planning CT and CBCT images for the pelvic region: comparison between hybrid and intensity-based DIR

This study aimed to evaluate the performance of the hybrid deformable image registration (DIR) method in comparison with intensity-based DIR for pelvic cone-beam computed tomography (CBCT) images, using intensity and anatomical information. Ten prostate cancer patients treated with intensity-modulated radiation therapy (IMRT) were studied. Nine or ten CBCT scans were performed for each patient. First, rigid registration was performed between the planning CT and all CBCT images using gold fiducial markers, and then DIR was performed. The Dice similarity coefficient (DSC) and center of mass (COM) displacement were used to evaluate the quantitative DIR accuracy. The average DSCs for intensity-based DIR for the prostate, rectum, bladder, and seminal vesicles were 0.84 ± 0.05, 0.75 ± 0.05, 0.69 ± 0.07 and 0.65 ± 0.11, respectively, whereas those values for hybrid DIR were 0.98 ± 0.00, 0.97 ± 0.01, 0.98 ± 0.00 and 0.94 ± 0.03, respectively (P < 0.05). The average COM displacements for intensity-based DIR for the prostate, rectum, bladder, and seminal vesicles were 2.0 ± 1.5, 3.7 ± 1.4, 7.8 ± 2.2 and 3.6 ± 1.2 mm, whereas those values for hybrid DIR were 0.1 ± 0.0, 0.3 ± 0.2, 0.2 ± 0.1 and 0.6 ± 0.6 mm, respectively (P < 0.05). These results showed that the DSC for hybrid DIR had a higher DSC value and smaller COM displacement for all structures and all patients, compared with intensity-based DIR. Thus, the accumulative dose based on hybrid DIR might be trusted as a high-precision dose estimation method that takes into account organ movement during treatment radiotherapy.

A multiple-image-based method to evaluate the performance of deformable image registration in the pelvis

Deformable image registration (DIR) is essential for adaptive radiotherapy (RT) for tumor sites subject to motion, changes in tumor volume, as well as changes in patient normal anatomy due to weight loss. Several methods have been published to evaluate DIR-related uncertainties but they are not widely adopted. The aim of this study was, therefore, to evaluate intra-patient DIR for two highly deformable organs-the bladder and the rectum-in prostate cancer RT using a quantitative metric based on multiple image registration, the distance discordance metric (DDM). Voxel-by-voxel DIR uncertainties of the bladder and rectum were evaluated using DDM on weekly CT scans of 38 subjects previously treated with RT for prostate cancer (six scans/subject). The DDM was obtained from group-wise B-spline registration of each patient's collection of repeat CT scans. For each structure, registration uncertainties were derived from DDM-related metrics. In addition, five other quantitative measures, including inverse consistency error (ICE), transitivity error (TE), Dice similarity (DSC) and volume ratios between corresponding structures from pre- and post- registered images were computed and compared with the DDM. The DDM varied across subjects and structures; DDMmean of the bladder ranged from 2 to 13 mm and from 1 to 11 mm for the rectum. There was a high correlation between DDMmean of the bladder and the rectum (Pearson's correlation coefficient, R p  =  0.62). The correlation between DDMmean and the volume ratios post-DIR was stronger (R p  =  0.51; 0.68) than the correlation with the TE (bladder: R p  =  0.46; rectum: R p  =  0.47), or the ICE (bladder: R p  =  0.34; rectum: R p  =  0.37). There was a negative correlation between DSC and DDMmean of both the bladder (R p  =  -0.23) and the rectum (R p  =  -0.63). The DDM uncertainty metric indicated considerable DIR variability across subjects and structures. Our results show a stronger correlation with volume ratios and with the DSC using DDM compared to using ICE and TE. The DDM has the potential to quantitatively identify regions of large DIR uncertainties and consequently identify anatomical/scan outliers. The DDM can, thus, be applied to improve the adaptive RT process for tumor sites subject to motion.

ART for head and neck patients: On the difference between VMAT and IMPT

Anatomical changes in the head-and-neck (H&N) region during the course of treatment can cause deteriorated dose distributions. Different replanning strategies were investigated for volumetric modulated arc therapy (VMAT) and intensity-modulated proton therapy (IMPT).

MATERIAL AND METHODS

For six H&N patients two repeated computed tomography (CT) and magnetic resonance (MR) (CT1/MR1 at week 2 and CT2/MR2 at week 4) scans were acquired additionally to the initial planning CT/MR. Organs-at-risk (OARs) and three targets (CTV70Gy, CTV63Gy, CTV56Gy) were delineated on MRs and transferred to respective CT data set. Simultaneously integrated boost plans were created using VMAT (two arcs) and IMPT (four beams). To assess the need of replanning the initial VMAT and IMPT plans were recalculated on repeated CTs. Furthermore, VMAT and IMPT plans were replanned on the repeated CTs. A Demon algorithm was used for deformable registration of the repeated CTs with the initial CT and utilized for dose accumulation. Total dose estimations were performed to compare ART versus standard treatment strategies.

RESULTS

Dosimetric evaluation of recalculated plans on CT1 and CT2 showed increasing OAR doses for both, VMAT and IMPT. The target coverage of recalculated VMAT plans was considered acceptable in three cases, while for all IMPT plans it dropped. Adaptation of the treatment reduced D2% for brainstem by 6.7 Gy for VMAT and by 8 Gy for IMPT, for particular patients. These D2% reductions were reaching 9 Gy and 14 Gy for the spinal cord. ART improved target dose homogeneity, especially for protons, i.e. D2% decreased by up to 8 Gy while D98% increased by 1.2 Gy.

CONCLUSION

ART showed benefits for both modalities. However, as IMPT is more conformal, the magnitude of dosimetric changes was more pronounced compared to VMAT. Large anatomic variations had a severe impact on treatment plan quality for both VMAT and IMPT. ART is justified in those cases irrespective of treatment modalities.