Deformable Image Registration Accuracy Research Articles

A novel framework for elucidating the effect of mechanical loading on the geometry of ovariectomized mouse tibiae using principal component analysis

IntroductionMurine models are used to test the effect of anti-osteoporosis treatments as they replicate some of the bone phenotypes observed in osteoporotic (OP) patients. The effect of disease and treatment is typically described as changes in bone geometry and microstructure over time. Conventional assessment of geometric changes relies on morphometric scalar parameters. However, being correlated with each other, these parameters do not describe separate fractions of variations and offer only a moderate insight into temporal changes.MethodsThe current study proposes a novel image-based framework that employs deformable image registration on in vivo longitudinal images of bones and Principal Component Analysis (PCA) for improved quantification of geometric effects of OP treatments. This PCA-based model and a novel post-processing of score changes provide orthogonal modes of shape variations temporally induced by a course of treatment (specifically in vivo mechanical loading).Results and DiscussionErrors associated with the proposed framework are rigorously quantified and it is shown that the accuracy of deformable image registration in capturing the bone shapes (∼1 voxel = 10.4 μm) is of the same order of magnitude as the relevant state-of-the-art evaluation studies. Applying the framework to longitudinal image data from the midshaft section of ovariectomized mouse tibia, two mutually orthogonal mode shapes are reliably identified to be an effect of treatment. The mode shapes captured changes of the tibia geometry due to the treatment at the anterior crest (maximum of 0.103 mm) and across the tibia midshaft section and the posterior (0.030 mm) and medial (0.024 mm) aspects. These changes agree with those reported previously but are now described in a compact fashion, as a vector field of displacements on the bone surface. The proposed framework enables a more detailed investigation of the effect of disease and treatment on bones in preclinical studies and boosts the precision of such assessments.

Geometric evaluation and quantifying dosimetric impact of diverse deformable image registration algorithms on abdomen images with biomechanically modeled deformations.

Deformable image registration (DIR) has been increasingly used in radiation therapy (RT). The accuracy of DIR algorithms and how it impacts on the RT plan dosimetrically were examined in our study for abdominal sites using biomechanically modeled deformations. Five pancreatic cancer patients were enrolled in this study. Following the guidelines of AAPM TG-132, a patient-specific quality assurance (QA) workflow was developed to evaluate DIR for the abdomen using the TG-132 recommended virtual simulation software ImSimQA (Shrewsbury, UK). First, the planning CT was deformed to simulate respiratory motion using the embedded biomechanical model in ImSimQA. Additionally, 5mm translational motion was added to the stomach, duodenum, and small bowel. The original planning CT and the deformed CT were then imported into Eclipse and MIM to perform DIR. The output displacement vector fields (DVFs) were compared with the ground truth from ImSimQA. Furthermore, the original treatment plan was recalculated on the ground-truth deformed CT and the deformed CT (with Eclipse and MIM DVF). The dose errors were calculated on a voxel-to-voxel basis. Data analysis comparing DVF from Eclipse versus MIM show the average mean DVF magnitude errors of 2.8±1.0 versus 1.1±0.7mm for stomach and duodenum, 5.2±4.0 versus 2.5±1.0mm for small bowel, and 4.8±4.1 versus 2.7±1.1mm for the gross tumor volume (GTV), respectively, across all patients. The mean dose error on stomach+duodenum and small bowel were 2.3±0.6% for Eclipse, and 1.0±0.3% for MIM. As the DIR magnitude error increases, the dose error range increase, for both Eclipse and MIM. In our study, an initial assessment was conducted to evaluate the accuracy of DIR and its dosimetric impact on radiotherapy. A patient-specific DIR QA workflow was developed for pancreatic cancer patients. This workflow exhibits promising potential for future implementation as a clinical workflow.

Retrospective Comparison of Geometrical Accuracy among Atlas-based Auto-segmentation, Deep Learning Auto-segmentation, and Deformable Image Registration in the Treatment Replanning for Adaptive Radiotherapy of Head-and-Neck Cancer

Aims: This study aimed to evaluate the geometrical accuracy of atlas-based auto-segmentation (ABAS), deformable image registration (DIR), and deep learning auto-segmentation (DLAS) in adaptive radiotherapy (ART) for head-and-neck cancer (HNC). Subjects and Methods: Seventeen patients who underwent replanning for ART were retrospectively studied, and delineated contours on their replanning computed tomography (CT2) images were delineated. For DIR, the planning CT image (CT1) of the evaluated patients was utilized. In contrast, ABAS was performed using an atlas dataset comprising 30 patients who were not part of the evaluated group. DLAS was trained with 143 patients from different patients from the evaluated patients. The ABAS model was improved, and a modified ABAS (mABAS) was created by adding the evaluated patients’ own CT1 to the atlas datasets of ABAS (number of patients of the atlas dataset, 31). The geometrical accuracy of DIR, DLAS, ABAS, and mABAS was evaluated. Results: The Dice similarity coefficient in DIR was the highest, at >0.8 at all organs at risk. The mABAS was delineated slightly more accurately than the standard ABAS. There was no significant difference between ABAS and DLAS in delineation accuracy. DIR had the lowest Hausdorff distance (HD) value (within 10 mm). The HD values in ABAS, mABAS, and DLAS were within 16 mm. Conclusions: DIR delineation is the most geometrically accurate ART for HNC.

The effects of mega-voltage CT scan parameters on offline adaptive radiation therapy.

TomoTherapy involves image-guided radiation therapy (IGRT) using Mega-voltage CT (MVCT) for each treatment session. The acquired MVCT images can be utilized for the retrospective assessment of dose distribution. The TomoTherapy provides 18 distinct imaging conditions that can be selected based on a combination of algorithms, acquisition pitch, and slice interval. We investigated the accuracy of dose calculation and deformable image registration (DIR) depending on MVCT scan parameters and their effects on adaptive radiation therapy (ART). We acquired image values for density calibration tables (IVDTs) under 18 different MVCT conditions and compared them. The planning CT (pCT) was performed using a thoracic phantom, and an esophageal intensity-modulated radiation therapy (IMRT) plan was created. MVCT images of the thoracic phantom were acquired under each of the 18 conditions, and dose recalculation was performed. DIR was performed on the MVCT images acquired under each condition. The accuracy of DIR, depending on the MVCT scan parameters, was compared using the mean distance to agreement (MDA) and Dice similarity coefficient (DSC). The dose distribution calculated on the MVCT images was deformed using deformed vector fields (DVF). No significant differences were observed in the results of the 18 IVDTs. The esophageal IMRT plan also showed a small dose difference. Regarding verifying the DIR accuracy, the MDA increased, and the DSC decreased as the acquisition pitch and slice interval increased. The difference between the dose distributions after dose mapping was comparable to that before DIR. The MVCT scan parameters had little effect on ART.

Deformable image registration for composite planned doses during adaptive radiation therapy

IntroductionSome patients have significant anatomic changes during radiotherapy, necessitating an adaptive repeat CT-simulation and re-planning. This yields two unique planning datasets that introduce uncertainty into total dose records. This study explored the impact of using deformable image registration (DIR) to spatially align repeat CT-simulation images and calculate total planned dose distributions. Materials & methodsData from 5 head-and-neck, 5 lung, and 5 sarcoma patients who had unanticipated re-planning during radiotherapy were analyzed in a treatment planning system (RayStation v6.1 RaySearch Laboratories). Total planned doses to normal tissues were calculated using two methods and the previously generated manual contours defined on each CT. The first method, termed ‘parameter addition’, simply sums the relevant DVH metrics from the initial and re-planned distributions without spatially registering the CTs. The second, termed ‘dose accumulation’, uses a validated hybrid contour/intensity-based DIR algorithm to deform initial CT and dose distribution onto the repeat CT and re-planning dose distribution. DVH metrics from the summed distribution on the repeat CT are then calculated. Dose differences for organs-at-risk between parameter addition and dose accumulation ≥100 cGy were assumed to be clinically relevant. To elucidate whether relevant differences were due to registration accuracy or contouring variability between CTs, the analysis was repeated using contours on the first CT and the same contours deformed to the repeat CT with DIR. ResultsFor all patients, high overall DIR accuracy was verified visually (qualitatively) and numerically (quantitatively) using image similarity and contour-based metrics. All head-and-neck and lung patients, and one sarcoma patient (11 of 15 total) had dose differences between parameter addition and dose accumulation ≥100 cGy, with absolute mean differences of 160 cGy (range 101–436 cGy) seen in 41 of 205 total DVH criteria. In 22 of these 41 criteria, these differences were attributed to contouring variability between CTs. After correcting for contouring variations using DIR, the mean absolute differences in 7 of these 22 criteria with a relevant result (across 6 patients) was 146 cGy (range 100–502 cGy). In only 4 DVH criteria, the DIR mapped contours had higher variations than the original contours. One lung patient had a DVH criteria exceeding the clinical dose constraint by 125 cGy with parameter addition, and with accurate DIR and dose accumulation, the criteria was actually 97 cGy lower than the constraint. ConclusionsThe use of DIR to generate total planned dose records revealed substantial dose differences in most cases compared to commonly used clinical methods (i.e. parameter addition), and altered the planned acceptance criteria in a minority. DIR is recommended to be used for future adaptive re-plans to generate total planned dose records and facilitate accurate re-contouring. More accurate dose records may also improve our understanding of clinical outcomes.

A transformer-based hierarchical registration framework for multimodality deformable image registration.

Deformable image registration (DIR) between daily and reference images is fundamentally important for adaptive radiotherapy. In the last decade, deep learning-based image registration methods have been developed with faster computation time and improved robustness compared to traditional methods. However, the registration performance is often degraded in extra-cranial sites with large volume containing multiple anatomic regions, such as Computed Tomography (CT)/Magnetic Resonance (MR) images used in head and neck (HN) radiotherapy. In this study, we developed a hierarchical deformable image registration (DIR) framework, Patch-based Registration Network (Patch-RegNet), to improve the accuracy and speed of CT-MR and MR-MR registration for head-and-neck MR-Linac treatments. Patch-RegNet includes three steps: a whole volume global registration, a patch-based local registration, and a patch-based deformable registration. Following a whole-volume rigid registration, the input images were divided into overlapping patches. Then a patch-based rigid registration was applied to achieve accurate local alignment for subsequent DIR. We developed a ViT-Morph model, a combination of a convolutional neural network (CNN) and the Vision Transformer (ViT), for the patch-based DIR. A modality independent neighborhood descriptor was adopted in our model as the similarity metric to account for both inter-modality and intra-modality registration. The CT-MR and MR-MR DIR models were trained with 242 CT-MR and 213 MR-MR image pairs from 36 patients, respectively, and both tested with 24 image pairs (CT-MR and MR-MR) from 6 other patients. The registration performance was evaluated with 7 manually contoured organs (brainstem, spinal cord, mandible, left/right parotids, left/right submandibular glands) by comparing with the traditional registration methods in Monaco treatment planning system and the popular deep learning-based DIR framework, Voxelmorph. Evaluation results show that our method outperformed VoxelMorph by 6 % for CT-MR registration, and 4 % for MR-MR registration based on DSC measurements. Our hierarchical registration framework has been demonstrated achieving significantly improved DIR accuracy of both CT-MR and MR-MR registration for head-and-neck MR-guided adaptive radiotherapy.

Quantifying the Effect of 4-Dimensional Computed Tomography–Based Deformable Dose Accumulation on Representing Radiation Damage for Patients with Locally Advanced Non-Small Cell Lung Cancer Treated with Standard-Fractionated Intensity-Modulated Radiation Therapy

The aim of this study was to investigate the dosimetric and clinical effects of 4-dimensional computed tomography (4DCT)-based longitudinal dose accumulation in patients with locally advanced non-small cell lung cancer treated with standard-fractionated intensity-modulated radiation therapy (IMRT). Sixty-seven patients were retrospectively selected from a randomized clinical trial. Their original IMRT plan, planning and verification 4DCTs, and ∼4-month posttreatment follow-up CTs were imported into a commercial treatment planning system. Two deformable image registration algorithms were implemented for dose accumulation, and their accuracies were assessed. The planned and accumulated doses computed using average-intensity images or phase images were compared. At the organ level, mean lung dose and normal-tissue complication probability (NTCP) for grade ≥2 radiation pneumonitis were compared. At the region level, mean dose in lung subsections and the volumetric overlap between isodose intervals were compared. At the voxel level, the accuracy in estimating the delivered dose was compared by evaluating the fit of a dose versus radiographic image density change (IDC) model. The dose-IDC model fit was also compared for subcohorts based on the magnitude of NTCP difference (|ΔNTCP|) between planned and accumulated doses. Deformable image registration accuracy was quantified, and the uncertainty was considered for the voxel-level analysis. Compared with planned doses, accumulated doses on average resulted in <1-Gy lung dose increase and <2% NTCP increase (up to 8.2 Gy and 18.8% for a patient, respectively). Volumetric overlap of isodose intervals between the planned and accumulated dose distributions ranged from 0.01 to 0.93. Voxel-level dose-IDC models demonstrated a fit improvement from planned dose to accumulated dose (pseudo-R2 increased 0.0023) and a further improvement for patients with ≥2% |ΔNTCP| versus for patients with <2% |ΔNTCP|. With a relatively large cohort, robust image registrations, multilevel metric comparisons, and radiographic image-based evidence, we demonstrated that dose accumulation more accurately represents the delivered dose and can be especially beneficial for patients with greater longitudinal response.

Impact of CT scan parameters on deformable image registration accuracy using deformable thorax phantom.

The purpose of this study was to evaluate the deformable image registration (DIR) accuracy using various CT scan parameters with deformable thorax phantom. Our developed deformable thorax phantom (Dephan, Chiyoda Technol Corp, Tokyo, Japan) was used. The phantom consists of a base phantom, an inner phantom, and a motor-derived piston. The base phantom is an acrylic cylinder phantom with a diameter of 180mm, which simulates the chest wall. The inner phantom consists of deformable, 20mm thick disk-shaped sponges with 48 Lucite beads and 48 nylon cross-wires which simulate the vascular and bronchial bifurcations of the lung. Peak-exhale and peak-inhale images of the deformable phantom were acquired using a CT scanner (Aquilion LB, TOSHIBA). To evaluate the impact of CT scan parameters on DIR accuracy, we used the four tube voltages (80, 100, 120, and 135kV) and six reconstruction algorithms (FC11, FC13, FC15, FC41, FC44, and FC52). Intensity-based DIR was performed between the two images using MIM Maestro (MIM software, Cleveland, USA). Fiducial markers (beads and cross-wires) based target registration error (TRE) was used for quantitative evaluation of DIR. In case with different tube voltages, the range of average TRE were 4.44-5.69mm (reconstruction algorithm: FC13). In case with different reconstruction algorithms, the range of average TRE were 4.26-4.59mm (tube voltage: 120kV). The TRE were differed by up to 3.0mm (3.96-6.96mm) depending on the combination of tube voltage and reconstruction algorithm. Our result indicated that CT scan parameters had moderate impact of TRE, especially for reconstruction algorithms for the deformable thorax phantom.

Applying Multi-Metric Deformable Image Registration for Dose Accumulation in Combined Cervical Cancer Radiotherapy

(1) Purpose: Challenges remain in dose accumulation for cervical cancer radiotherapy combined with external beam radiotherapy (EBRT) and brachytherapy (BT) as there are many large and complex organ deformations between different treatments. This study aims to improve deformable image registration (DIR) accuracy with the introduction of multi-metric objectives for dose accumulation of EBRT and BT. (2) Materials and methods: Twenty cervical cancer patients treated with EBRT (45-50 Gy/25 fractions) and high-dose-rate BT (≥20 Gy in 4 fractions) were included for DIR. The multi-metric DIR algorithm included an intensity-based metric, three contour-based metrics, and a penalty term. Nonrigid B-spine transformation was used to transform the planning CT images from EBRT to the first BT, with a six-level resolution registration strategy. To evaluate its performance, the multi-metric DIR was compared with a hybrid DIR provided by commercial software. The DIR accuracy was measured by the Dice similarity coefficient (DSC) and Hausdorff distance (HD) between deformed and reference organ contours. The accumulated maximum dose of 2 cc (D2cc) of the bladder and rectum was calculated and compared to simply addition of D2cc from EBRT and BT (ΔD2cc). (3) Results: The mean DSC of all organ contours for the multi-metric DIR were significantly higher than those for the hybrid DIR (p ≤ 0.011). In total, 70% of patients had DSC > 0.8 using the multi-metric DIR, while 15% of patients had DSC > 0.8 using the commercial hybrid DIR. The mean ΔD2cc of the bladder and rectum for the multi-metric DIR were 3.25 ± 2.29 and 3.54 ± 2.02 GyEQD2, respectively, whereas those for the hybrid DIR were 2.68 ± 2.56 and 2.32 ± 3.25 GyEQD2, respectively. The multi-metric DIR resulted in a much lower proportion of unrealistic D2cc than the hybrid DIR (2.5% vs. 17.5%). (4) Conclusions: Compared with the commercial hybrid DIR, the introduced multi-metric DIR significantly improved the registration accuracy and resulted in a more reasonable accumulated dose distribution.

Dosimetric impact of deformable image registration using radiophotoluminescent glass dosimeters with a physical geometric phantom.

To study the dosimetry impact of deformable image registration (DIR) using radiophotoluminescent glass dosimeter (RPLD) and custom developed phantom with various inserts. The phantom was developed to facilitate simultaneous evaluation of geometric and dosimetric accuracy of DIR. Four computed tomography (CT) images of the phantom were acquired with four different configurations. Four volumetric modulated arc therapy (VMAT) plans were computed for different phantom. Two different patterns were applied to combination of four phantom configurations. RPLD dose measurement was combined between corresponding two phantom configurations. DIR-based dose accumulation was calculated between corresponding two CT images with two commercial DIR software and various DIR parameter settings, and an open source software. Accumulated dose calculated using DIR was then compared with measured dose using RPLD. The mean±standard deviation (SD) of dose difference was 2.71±0.23% (range, 2.22%-3.01%) for tumor-proxy and 3.74±0.79% (range, 1.56%-4.83%) for rectum-proxy. The mean±SD of target registration error (TRE) was 1.66±1.36mm (range, 0.03-4.43mm) for tumor-proxy and 6.87±5.49mm (range, 0.54-17.47mm) for rectum-proxy. These results suggested that DIR accuracy had wide range among DIR parameter setting. The dose difference observed in our study was 3% for tumor-proxy and within 5% for rectum-proxy. The custom developed physical phantom with inserts showed potential for accurate evaluation of DIR-based dose accumulation. The prospect of simultaneous evaluation of geometric and dosimetric DIR accuracy in a single phantom may be useful for validation of DIR for clinical use.

Dosimetric comparison of deformable image registration and synthetic CT generation based on CBCT images for organs at risk in cervical cancer radiotherapy

ObjectiveAnatomical variations existing in cervical cancer radiotherapy treatment can be monitored by cone-beam computed tomography (CBCT) images. Deformable image registration (DIR) from planning CT (pCT) to CBCT images and synthetic CT (sCT) image generation based on CBCT are two methods for improving the quality of CBCT images. This study aims to compare the accuracy of these two approaches geometrically and dosimetrically in cervical cancer radiotherapy.MethodsIn this study, 40 paired pCT-CBCT images were collected to evaluate the accuracy of DIR and sCT generation. The DIR method was based on a 3D multistage registration network that was trained with 150 paired pCT-CBCT images, and the sCT generation method was performed based on a 2D cycle-consistent adversarial network (CycleGAN) with 6000 paired pCT-CBCT slices for training. Then, the doses were recalculated with the CBCT, pCT, deformed pCT (dpCT) and sCT images by a GPU-based Monte Carlo dose code, ArcherQA, to obtain DoseCBCT, DosepCT, DosedpCT and DosesCT. Organs at risk (OARs) included small intestine, rectum, bladder, spinal cord, femoral heads and bone marrow, CBCT and pCT contours were delineated manually, dpCT contours were propagated through deformation vector fields, sCT contours were auto-segmented and corrected manually.ResultsThe global gamma pass rate of DosesCT and DosedpCT was 99.66% ± 0.34%, while that of DoseCBCT and DosedpCT was 85.92% ± 7.56% at the 1%/1 mm criterion and a low-dose threshold of 10%. Based on DosedpCT as uniform dose distribution, there were comparable errors in femoral heads and bone marrow for the dpCT and sCT contours compared with CBCT contours, while sCT contours had lower errors in small intestine, rectum, bladder and spinal cord, especially for those with large volume difference of pCT and CBCT.ConclusionsFor cervical cancer radiotherapy, the DIR method and sCT generation could produce similar precise dose distributions, but sCT contours had higher accuracy when the difference in planning CT and CBCT was large.

Evaluating the accumulated dose distribution of organs at risk in combined radiotherapy for cervical carcinoma based on deformable image registration

ObjectiveTo evaluate the feasibility and value of deformable image registration (DIR) in calculating the cumulative doses of organs at risk (OARs) in the combined radiotherapy of cervical cancer. Patients and methodsThirty cervical cancer patients treated with external beam radiotherapy (EBRT) combined with intracavitary brachytherapy (ICBT) were reviewed. The simulation CT images of EBRT and ICBT were imported into Varian Velocity 4.1 for the DIR-based dose accumulation. Cumulative dose-volume parameters of D2cc for rectum and bladder were compared between the direct addition (DA) and DIR methods. The quantitative parameters were measured to evaluate the accuracy of DIR. ResultsThe three-dimensional cumulative dose distribution of the tumor and OARs were graphically well illustrated by composite isodose lines. In combined EBRT and ICBT, the mean cumulative bladder D2cc calculated by DIR and DA was 86.13 Gy and 86.27 Gy, respectively. The mean cumulative rectal D2cc calculated by DIR and DA was 72.97 Gy and 73.90 Gy, respectively. No significant differences were noted between these two methods (p > 0.05). As to the parameters used to evaluate the DIR accuracy, the mean DSC, Jacobian, MDA (mm) and Hausdorff distance (mm) were 0.79, 1.0, 3.84, and 22.01 respectively for the bladder and 0.53, 1.2, 7.31, and 29.58 respectively for the rectum. In this study, the DSC seemed to be slightly lower compared with previous studies. ConclusionDose accumulation based on DIR might be an alternative method to illustrate and evaluate the cumulative doses of the OARs in combined radiotherapy for cervical cancer. However, DIR should be used with caution before overcoming the relevant limitations.

Geometric Analysis and Dosimetric Evaluation of Various Deformable Image Registration (DIR) Algorithms for Abdominal Images with 3D Biomechanically Modelled Deformation

<h3>Purpose/Objective(s)</h3> The accuracy of DIR algorithms available on commercial radiotherapy planning platforms were examined and their clinical applicability geometrically and dosimetrically for abdominal sites were evaluated using biomechanically modelled deformation. <h3>Materials/Methods</h3> 5 pancreatic patients' planning CT were used in this study. Following the guideline of AAPM TG-132, a patient-specific QA workflow was developed and implemented to evaluate DIR for abdomen using digital phantoms, created with a commercial virtual phantom software (VPS). First, the planning CT images were deformed in superior-inferior direction to simulation respiratory motion in lung and abdomen, using the biomechanical model embedded in VPS. In addition, 5 mm motion in both anterior-posterior and lateral directions were added to region of interest (ROI), including stomach and duodenum, and small bowel. The added ROI deformations are consistent with the abdomen data observed in daily CBCT. The resulting 3D deformation vector field (DVF) and the corresponding deformed CT was then obtained, serving as ground truth. Second, the original planning CT and the deformed CT were imported to two commercial DIR systems (DS1 and DS2), to perform DIR with intensity-based algorithms, and derive DVFs. Quantitative differences between ground truth DVF and DS1 or DS2's DVFs, such as mean, max, and the distribution of DIR errors were tabulated. Then the original plan was re-calculated on the deformed CT, which was generated based on DS1 or DS2's DVF. The dose errors were then calculated on a pixel-to-pixel basis. The relationship between the DIR errors and the dose error ranges (25%-75% on the dose error distribution histogram) were investigated. As a pilot study, comprehensive reports were generated to show the DIR performances as patient specific QA records. <h3>Results</h3> The displacements on the ground truth DVF range from 0 to 37 mm. Geometric analysis showed DIR errors as tabulated below. Dosimetrically, as the DIR error increases, the dose error range also increase, for both DS1 and DS2. Dosimetric evaluation of the dose errors for ROIs were tabulated as below. <h3>Conclusion</h3> Preliminary evaluation of geometric and dosimetric accuracy of DIR on DS1 and DS2 were performed, with a realistic biomechanical model derived DVF serving as ground truth. A patient specific DIR QA workflow was developed for a pancreatic patient cohort, and it has potential to be implemented as a clinical workflow.

Evaluating a Personalized Deep-Learning-Based Auto-Segmentation Method for CBCT-Based Adaptive Radiotherapy

<h3>Purpose/Objective(s)</h3> Online adaptive radiotherapy (ART) requires accurate and efficient auto-segmentation of target volumes and organs-at-risk (OARs) in mostly cone-beam computed tomography (CBCT) images. Propagating expert-drawn contours from the pre-treatment planning CT (pCT) through traditional or deep learning (DL) based deformable image registration (DIR) can achieve improved results in many situations. Typical DL-based DIR models are population based, that is, trained with a dataset for a population of patients, so they tend to average their result to the data distribution rather than individualizing to a single patient. We previously proposed a method, test-time optimization (TTO), that can individualize DL-based DIR model to each patient to improve DIR accuracy. In this work, we evaluated the accuracy and efficiency of auto-segmentation results from our proposed DIR method. <h3>Materials/Methods</h3> We used 39 patients with head and neck squamous cell carcinoma for evaluation. Each patient has a pCT with manual contours and two fractions of CBCT with manual contours. 17 structures that are either critical OARs or have large anatomical changes during radiotherapy courses were selected. These structures were: left brachial plexus, right brachial plexus, brainstem, oral cavity, constrictor, esophagus, nodal gross tumor volume, larynx, mandible, left masseter, right masseter, posterior arytenoid-cricoid space, left parotid gland, right parotid gland, left submandibular gland, right submandibular gland, and spinal cord. Dice similarity coefficient (DSC) and 95% Hausdorff Distance (HD95) were calculated between auto-segmentation and manual segmentation for each structure. All the auto-segmentation methods tested in this experiment are based on DIR methods including our proposed individualized DIR models and traditional DIR models. To get individualized DIR model for each patient, TTO was applied where a pre-trained population DIR model was fine-tuned on each patient separately. The auto-segmentation accuracy and the time cost for DIR model individualization were studied. <h3>Results</h3> The average DSC and HD95 of the auto-segmentation by individualized DIR models is 0.85 and 2.33mm respectively over 17 selected OARs and a target of 39 patients, which performs better than traditional DIR methods. The average time for deriving the individualized DIR model is approximately 3.6 minutes. <h3>Conclusion</h3> The proposed TTO method is well-suited for online ART and can boost segmentation accuracy for DL-based DIR models, especially for outlier patients where traditional DIR methods fail.

CT and cone-beam CT of ablative radiation therapy for pancreatic cancer with expert organ-at-risk contours

We describe a dataset from patients who received ablative radiation therapy for locally advanced pancreatic cancer (LAPC), consisting of computed tomography (CT) and cone-beam CT (CBCT) images with physician-drawn organ-at-risk (OAR) contours. The image datasets (one CT for treatment planning and two CBCT scans at the time of treatment per patient) were collected from 40 patients. All scans were acquired with the patient in the treatment position and in a deep inspiration breath-hold state. Six radiation oncologists delineated the gastrointestinal OARs consisting of small bowel, stomach and duodenum, such that the same physician delineated all image sets belonging to the same patient. Two trained medical physicists further edited the contours to ensure adherence to delineation guidelines. The image and contour files are available in DICOM format and are publicly available from The Cancer Imaging Archive (https://doi.org/10.7937/TCIA.ESHQ-4D90, Version 2). The dataset can serve as a criterion standard for evaluating the accuracy and reliability of deformable image registration and auto-segmentation algorithms, as well as a training set for deep-learning-based methods.

Dual attention network for unsupervised medical image registration based on VoxelMorph

An accurate medical image registration is crucial in a variety of neuroscience and clinical studies. In this paper, we proposed a new unsupervised learning network, DAVoxelMorph to improve the accuracy of 3D deformable medical image registration. Based on the VoxelMorph model, our network presented two modifications, one is adding a dual attention architecture, specifically, we model semantic correlation on spatial and coordinate dimensions respectively, and the location attention module selectively aggregates the features of each location by weighting the features of all locations. The coordinate attention module further puts the location information into the channel attention. The other is introducing the bending penalty as regularization in the loss function to penalize the bending in the deformation field. Experimental results show that DAVoxelMorph achieved better registration performance including average Dice scores (0.714) and percentage of locations with non-positive Jacobian (0.345) compare with VoxelMorph (0.703, 0.355), CycleMorph (0.705, 0.133), ANTs SyN (0.707, 0.137) and NiftyReg (0.694, 0.549). Our model increases both model sensitivity and registration accuracy.

Accuracy and consistency of intensity-based deformable image registration in 4DCT for tumor motion estimation in liver radiotherapy planning.

We investigate the accuracy of intensity-based deformable image registration (DIR) for tumor localization in liver stereotactic body radiotherapy (SBRT). We included 4DCT scans to capture the breathing motion of eight patients receiving SBRT for liver metastases within a retrospective clinical study. Each patient had three fiducial markers implanted. The liver and the tumor were delineated in the mid-ventilation phase, and their positions in the other phases were estimated with deformable image registration. We tested referenced and sequential registrations strategies. The fiducial markers were the gold standard to evaluate registration accuracy. The registration errors related to measured versus estimated fiducial markers showed a mean value less than 1.6mm. The positions of some fiducial markers appeared not stable on the 4DCT throughout the respiratory phases. Markers’ center of mass tends to be a more reliable measurement. Distance errors of tumor location based on registration versus markers center of mass were less than 2mm. There were no statistically significant differences between the reference and the sequential registration, i.e., consistency and errors were comparable to resolution errors. We demonstrated that intensity-based DIR is accurate up to resolution level for locating the tumor in the liver during breathing motion.

Deriving Pulmonary Ventilation Images From Clinical 4D-CBCT Using a Deep Learning-Based Model.

PurposeThe current algorithms for measuring ventilation images from 4D cone-beam computed tomography (CBCT) are affected by the accuracy of deformable image registration (DIR). This study proposes a new deep learning (DL) method that does not rely on DIR to derive ventilation images from 4D-CBCT (CBCT-VI), which was validated with the gold-standard single-photon emission-computed tomography ventilation image (SPECT-VI).Materials and MethodsThis study consists of 4D-CBCT and 99mTc-Technegas SPECT/CT scans of 28 esophagus or lung cancer patients. The scans were rigidly registered for each patient. Using these data, CBCT-VI was derived using a deep learning-based model. Two types of model input data are studied, namely, (a) 10 phases of 4D-CBCT and (b) two phases of peak-exhalation and peak-inhalation of 4D-CBCT. A sevenfold cross-validation was applied to train and evaluate the model. The DIR-dependent methods (density-change-based and Jacobian-based methods) were used to measure the CBCT-VIs for comparison. The correlation was calculated between each CBCT-VI and SPECT-VI using voxel-wise Spearman’s correlation. The ventilation images were divided into high, medium, and low functional lung regions. The similarity of different functional lung regions between SPECT-VI and each CBCT-VI was evaluated using the dice similarity coefficient (DSC). One-factor ANONA model was used for statistical analysis of the averaged DSC for the different methods of generating ventilation images.ResultsThe correlation values were 0.02 ± 0.10, 0.02 ± 0.09, and 0.65 ± 0.13/0.65 ± 0.15, and the averaged DSC values were 0.34 ± 0.04, 0.34 ± 0.03, and 0.59 ± 0.08/0.58 ± 0.09 for the density change, Jacobian, and deep learning methods, respectively. The strongest correlation and the highest similarity with SPECT-VI were observed for the deep learning method compared to the density change and Jacobian methods.ConclusionThe results showed that the deep learning method improved the accuracy of correlation and similarity significantly, and the derived CBCT-VIs have the potential to monitor the lung function dynamic changes during radiotherapy.

Evaluation of Accuracy of Deformable Image Registration with Newly Developed Treatment Planning Support Software for Thoracic Images

This study evaluated accuracy of deformable image registration (DIR) with twelve parameter settings for thoracic images. We used peak-inhale and peak-exhale images for ten patients provided by DIR-lab. We used a prototype version of iCView software (ITEM Corporation) with DIR to perform intensity, structure, and hybrid-based DIR with the twelve parameter settings. DIR accuracy was evaluated by a target registration error (TRE) using 300 bronchial bifurcations and the Dice similarity coefficient (DSC) of the lungs. For twelve parameter settings, TRE ranged from 2.83 mm to 5.27 mm, whereas DSC ranged from 0.96 to 0.98. These results demonstrated that DIR accuracy differed among parameter settings and show that appropriate parameter settings are required for clinical practice.

EQD2 Dose Accumulation Based on Deformable Image Registration of HR-CTV, Bladder, Rectum and Bowel for Combined External-Beam Radiotherapy and Brachytherapy for Cervical Cancer

<h3>Purpose/Objective(s)</h3> Evaluate the accuracy of DVH parameter summation between brachytherapy (BT) and external-beam radiotherapy (EBRT) for cervical cancer, by comparing deformable image registration (DIR) EQD2 dose accumulation. DVH summation of dosimetric parameters can overestimate cumulative organ at risk (OAR) doses due to daily variations in relative OAR position. <h3>Materials/Methods</h3> Ten patients were studied. Nine out of 10 patients received BT+EBRT. All women were treated with intracavitary tandem and ring BT. In phase I, CT simulation images from each BT fraction were rigidly fused with first fraction BT images, (BT1) focusing on the applicator and uterus. Hybrid-based DIR was then conducted using MIM software. Contours used for DIR were CTV_HR, bladder, rectum and bowel space. For phase II, EBRT and BT1 utero-cervix contours were rigidly fused, followed by contour-based DIR using utero-cervix, bladder and rectum. Each BT fraction and sum EBRT dose was accumulated onto BT1 and converted to EQD2 (Gy) via the linear quadratic equation with a/b of 10 for tumor and 3 for OARs. The absolute dose differences were reported for D0.1cc, D1cc and D2cc (OARs) and D90% (CTV_HR). The dice similarity coefficient (DSC) of all contours was reported. For phase I, the D2cc isodose level and OAR overlap structure was assessed for each BT fraction and the initial and deformed D2cc reported. The mean distance-to-agreement (MDA) and DSC of D2cc were reported for DIR accuracy assessment. <h3>Results</h3> For phase I, average DSC values for CTV_HR, bladder, rectum and bowel were 0.84 ± 0.07, 0.86 ± 0.08, 0.82 ± 0.05, 0.81 ± 0.07 and average DSC of initial vs. deformed D2cc were 0.88 ± 0.02, 0.89 ± 0.02, 0.88 ± 0.03 respectively. Average D2cc MDA values were 0.28 ± 0.04, 0.29 ± 0.05, 0.33 ± 0.06 for the bladder, rectum and bowel, respectively with absolute D2cc differences in Gy of 0.04 ± 0.04, 0.01 ± 0.01, and 0.03 ± 0.03. For CTV_HR, absolute D90 difference in EQD2 was 2.69 ± 1.98 Gy. For bladder, rectum and bowel, absolute EQD2 differences in Gy for D0.1cc were 5.57 ± 3.73, 2.78 ± 2.27, 5.10 ± 2.70 respectively. For D1cc, values in Gy were 3.27 ± 1.80, 1.62 ± 1.04, and 4.20 ± 2.51. For D2cc, 2.42 ± 0.80 Gy, 1.16 ± 0.72 Gy, and 2.83 ± 2.23 Gy. For phase II, average DSC values for utero-cervix, bladder and rectum were 0.82 ± 0.12, 0.80 ± 0.08, and 0.82 ± 0.17 respectively. Average absolute EQD2 difference in Gy for CTV_HR D90 was 7.43 ± 3.10 and 12.87 ± 6.84 and 6.02 ± 4.80 respectively for bladder and rectum D0.1cc. For D1cc and D2cc, absolute EQD2 differences in Gy were 10.46 ± 5.10 and 8.10 ± 4.48 respectively for bladder and 3.84 ± 2.95 and 3.21 ± 2.17 for rectum. <h3>Conclusion</h3> Arithmetic DVH addition over-estimated OAR D2cc in 7 of 10 patients. D2cc overestimation of bladder occurred in 6 of 9 patients and 7 of 9 patients for rectum. Our results show good estimation of accumulated dose with DVH parameter addition for both BT only and BT + EBRT.