Deformable Image Registration Research Articles

Influence of learned landmark correspondences on lung CT registration.

Disease or injury may cause a change in the biomechanical properties of the lungs, which can alter lung function. Image registration can be used to measure lung ventilation and quantify volume change, which can be a useful diagnostic aid. However, lung registration is a challenging problem because of the variation in deformation along the lungs, sliding motion of the lungs along the ribs, and change indensity. Landmark correspondences have been used to make deformable image registration robust to largedisplacements. To tackle the challenging task of intra-patient lung computed tomography (CT) registration, we extend the landmark correspondence prediction model deep convolutional neural network-Match by introducing a soft mask loss term to encourage landmark correspondences in specific regions and avoid the use of a mask during inference. To produce realistic deformations to train the landmark correspondence model, we use data-driven synthetic transformations. We study the influence of these learned landmark correspondences on lung CT registration by integrating them into intensity-based registration as a distance-basedpenalty. Our results on the public thoracic CT dataset COPDgene show that using learned landmark correspondences as a soft constraint can reduce median registration error from approximately 5.46 to 4.08mm compared to standard intensity-based registration, in the absence of lungmasks. We show that using landmark correspondences results in minor improvements in local alignment, while significantly improving globalalignment.

Abstract PO5-22-04: Genomic analysis of local recurrences following risk adapted breast radiotherapy in the IMPORT trials defines 'true recurrences' and 'new primaries'

Abstract Background: Most ipsilateral breast tumor recurrences (IBTR) following breast conserving surgery occur near the tumor bed (Veronisi et al, Ann Oncol 2001) and are considered to represent ‘true recurrence’ (derived from residual malignant cells of the index cancer). A smaller number occur elsewhere in the breast and are thought to be ‘new primaries’ (independently occurring cancer). The IMPORT LOW (Coles et al, The Lancet 2017) and IMPORT HIGH (Coles et al, The Lancet 2023) trials investigated adaptation of radiotherapy dose-volume to this spatially varying risk, testing partial breast irradiation and simultaneous integrated boost in patients with tumors at low and high risk of IBTR respectively. We analysed genomic relationships between index cancers and recurrences in these trials, to ascertain the frequency of true recurrences and unrelated new primaries, and their spatial distribution. Methodology: FFPE blocks were obtained from 137 patients who developed subsequent ipsi- or contralateral breast cancer: 66 from IMPORT HIGH and 71 from IMPORT LOW (4 with bilateral second cancers). DNA extracted from index and subsequent cancers underwent shallow whole genome sequencing (sWGS) using the Illumina NovaSeq 6000 system. Copy number profiles were derived from sWGS data using the R package QDNAseq(Scheinin et al, Genome Res 2014); those that failed QC criteria were removed. Relatedness of tumor pairs was determined using the R package Breakclone (Lips et al, Nat Genet 2022). This approach uses individual copy number aberration breakpoint position rather than events at chromosomal arm level. The p value cutoff for relatedness was 0.01; values between 0.01 and 0.05 were considered ambiguous. Researchers were blinded to clinical information prior to results. Results: In 80/137 tumor pairs both copy number profiles met QC criteria and clonal relationship could be ascertained. In total 26/80 were considered related, 20/80 ambiguous and 34/40 non-related (Table 1). 16/26 ipsilateral subsequent cancers in IMPORT HIGH were clonally related to the primary tumor and could be considered true recurrences. In 5/26 it was impossible to accurately call clonality as pairs shared only common copy number changes such as 1q or 8q gain and 16q loss. 5/26 were considered new primaries. In the lower risk IMPORT LOW cohort, subsequent cancers appear to have similar chances of being related or independent. As expected, most contralateral tumors in IMPORT LOW showed no evidence of a clonal relationship to the index tumors. In both trials an ambiguous subgroup of pairs shared some common copy number changes suggesting similar phenotype.5/14 contralateral tumors in IMPORT HIGH, in which some women were also at high risk of systemic relapse, shared very similar copy number profiles to the index tumor and may be metastases rather than new primaries. Discussion: A considerable number of tumors classed as IBTR appear genomically unrelated to the index cancer particularly in low risk cancer; this biology is relevant to clinical management both initially and at ‘recurrence’. The finding that 5/14 contralateral cancers in the high risk group appear to be clonally related suggests that some may be metastases. Results are being confirmed by targeted sequencing and will be correlated with recorded spatial and clinicopathological data and patient outcome. Future work will analyse spatial relationships more precisely using deformable image registration. *From the 77 patients with baseline circulating tumor DNA samples, 2 patients were excluded because their samples failed during assay quality control. Table. PIK3CA and ESR1 alterations detected in circulating tumor DNA at baseline and post abemaciclib treatment Citation Format: Sara Lightowlers, Maria Roman-Escorza, Elena Provenzano, Judith Bliss, Jason Carroll, H Y Charlie Chan, Clare Griffin, Joanne Haviland, Monica Jefford, Anna Kirby, Navita Somaiah, Mark Sydenham, Jenny Titley, John Yarnold, Charlotte Coles, Elinor Sawyer. Genomic analysis of local recurrences following risk adapted breast radiotherapy in the IMPORT trials defines 'true recurrences' and 'new primaries' [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO5-22-04.

Broad-UNet-diff: Diffeomorphic Deformable Medical Image Registration based on Multi-scale Feature Learning

Introduction: To propose a medical image registration method with significant performance improvement. The spatial transformation obtained by the traditional deformable image registration technology is not smooth enough, and the calculation amount is too large to solve the optimization parameters. The network model proposed based on deep learning medical image registration technology has some limitations, which cannot guarantee the registration of topological structures, resulting in the loss of spatial features. It makes the model have topological conservation and transform reversibility, has the ability to learn more multi-scale features and complex image structures, and captures finer changes while clearly encoding global correlation. Method: Based on the core UNet model, a deformable image registration method with a new architecture Broad-UNet-diff is proposed. The model is equipped with asymmetric parallel convolution and uses diffeomorphism mapping. Result: Compared with the seven classical registration methods under the brain MRI datasets, the proposed method has significantly improved the registration performance. In particular, compared with the advanced TransMorph-diff registration method, the Dice score can be improved by 12 %, but only the 1/10 parameters are needed. Conclusion: This method confirms its convincing effectiveness and accuracy.

Uncertain prediction of deformable image registration on lung CT using multi-category features and supervised learning.

The assessment of deformable registration uncertainty is an important task for the safety and reliability of registration methods in clinical applications. However, it is typically done by a manual and time-consuming procedure. We propose a novel automatic method to predict registration uncertainty based on multi-category features and supervised learning. Three types of features, including deformation field statistical features, deformation field physiologically realistic features, and image similarity features, are introduced and calculated to train the random forest regressor for local registration uncertain prediction. Deformation field statistical features represent the numerical stability of registration optimization, which are correlated to the uncertainty of deformation fields; deformation field physiologically realistic features represent the biomechanical properties of organ motions, which mathematically reflect the physiological reality of deformation; image similarity features reflect the similarity between the warped image and fixed image. The multi-category features comprehensively reflect the registration uncertainty. The strategy of spatial adaptive random perturbations is also introduced to accurately simulate spatial distribution of registration uncertainty, which makes deformation field statistical features more discriminative to the uncertainty of deformation fields. Experiments were conducted on three publicly available thoracic CT image datasets. Seventeen randomly selected image pairs are used to train the random forest model, and 9 image pairs are used to evaluate the prediction model. The quantitative experiments on lung CT images show that the proposed method outperforms the baseline method for uncertain prediction of classical iterative optimization-based registration and deep learning-based registration with different registration qualities. The proposed method achieves good performance for registration uncertain prediction, which has great potential in improving the accuracy of registration uncertain prediction.

New full-counts phase-matched data-driven gated (DDG) PET/CT.

Data-driven gated (DDG) PET has gained clinical acceptance and has been shown to match or outperform external-device gated (EDG) PET. However, in most clinical applications, DDG PET is matched with helical CT acquired in free breathing (FB) at a random respiratory phase, leaving registration, and optimal attenuation correction (AC) to chance. Furthermore, DDG PET requires additional scan time to reduce image noise as it only preserves 35%-50% of the PET data at or near the end-expiratory phase of the breathing cycle. A new full-counts, phase-matched (FCPM) DDG PET/CT was developed based on a low-dose cine CT to improve registration between DDG PET and DDG CT, to reduce image noise, and to avoid increasing acquisition times in DDG PET. A new DDG CT was developed for three respiratory phases of CT images from a low dose cine CT acquisition of 1.35mSv for a coverage of about 15.4cm: end-inspiration (EI), average (AVG), and end-expiration (EE) to match with the three corresponding phases of DDG PET data: -10% to 15%; 15% to 30%, and 80% to 90%; and 30% to 80%, respectively. The EI and EE phases of DDG CT were selected based on the physiological changes in lung density and body outlines reflected in the dynamic cine CT images. The AVG phase was derived from averaging of all phases of the cine CT images. The cine CT was acquired over the lower lungs and/or upper abdomen for correction of misregistration between PET and FB CT as well as DDG PET and FB CT. The three phases of DDG CT were used for AC of the corresponding phases of PET. After phase-matched AC of each PET dataset, the EI and AVG PET data were registered to the EE PET data with deformable image registration. The final result was FCPM DDG PET/CT which accounts for all PET data registered at the EE phase. We applied this approach to 14 18F-FDG lung cancer patient studies acquired at 2min/bed position on the GE Discovery MI (25-cm axial FOV) and evaluated its efficacy in improved quantification and noise reduction. Relative to static PET/CT, the SUVmax increases for the EI, AVG, EE, and FCPM DDG PET/CT were 1.67±0.40, 1.50±0.28, 1.64±0.36, and 1.49±0.28, respectively. There were 10.8% and 9.1% average decreases in SUVmax from EI and EE to FCPM DDG PET/CT, respectively. EI, AVG, and EE DDG PET/CT all maintained increased image noise relative to static PET/CT. However, the noise levels of FCPM and static PET were statistically equivalent, suggesting the inclusion of all counts was able to decrease the image noise relative to EI and EE DDG PET/CT. A new FCPM DDG PET/CT has been developed to account for 100% of collected PET data in DDG PET applications. Image noise in FCPM is comparable to static PET, while small decreases in SUVmax were also observed in FCPM when compared to either EI or EE DDG PET/CT.

Evaluation and mitigation of deformable image registration uncertainties for MRI-guided adaptive radiotherapy.

We evaluate the performance of a deformable image registration (DIR) software package in registering abdominal magnetic resonance images (MRIs) and then develop a mechanical modeling method to mitigate detected DIR uncertainties. Three evaluation metrics, namely mean displacement to agreement (MDA), DICE similarity coefficient (DSC), and standard deviation of Jacobian determinants (STD-JD), are used to assess the multi-modality (MM), contour-consistency (CC), and image-intensity (II)-based DIR algorithms in the MIM software package, as well as an in-house developed, contour matching-based finite element method (CM-FEM). Furthermore, we develop a hybrid FEM registration technique to modify the displacement vector field of each MIM registration. The MIM and FEM registrations were evaluated on MRIs obtained from 10 abdominal cancer patients. One-tailed Wilcoxon-Mann-Whitney (WMW) tests were conducted to compare the MIM registrations with their FEM modifications. For the registrations performed with the MIM-CC, MIM-MM, MIM-II, and CM-FEM algorithms, their average MDAs are 0.62±0.27, 2.39±1.30, 3.07±2.42, 1.04±0.72mm, and average DSCs are 0.94±0.03, 0.80±0.12, 0.77±0.15, 0.90±0.11, respectively. The p-values of the WMW tests between the MIM registrations and their FEM modifications are less than 0.0084 for STD-JDs and greater than 0.87 for MDA and DSC. Among the three MIM DIR algorithms, MIM-CC shows the smallest errors in terms of MDA and DSC but exhibits significant Jacobian uncertainties in the interior regions of abdominal organs. The hybrid FEM technique effectively mitigates the Jacobian uncertainties in these regions.

On Finite Difference Jacobian Computation in Deformable Image  Registration

AbstractProducing spatial transformations that are diffeomorphic is a key goal in deformable image registration. As a diffeomorphic transformation should have positive Jacobian determinant $$\vert J\vert $$ | J | everywhere, the number of pixels (2D) or voxels (3D) with $$\vert J\vert <0$$ | J | < 0 has been used to test for diffeomorphism and also to measure the irregularity of the transformation. For digital transformations, $$\vert J\vert $$ | J | is commonly approximated using a central difference, but this strategy can yield positive $$\vert J\vert $$ | J | ’s for transformations that are clearly not diffeomorphic—even at the pixel or voxel resolution level. To show this, we first investigate the geometric meaning of different finite difference approximations of $$\vert J\vert $$ | J | . We show that to determine if a deformation is diffeomorphic for digital images, the use of any individual finite difference approximation of $$\vert J\vert $$ | J | is insufficient. We further demonstrate that for a 2D transformation, four unique finite difference approximations of $$\vert J\vert $$ | J | ’s must be positive to ensure that the entire domain is invertible and free of folding at the pixel level. For a 3D transformation, ten unique finite differences approximations of $$\vert J\vert $$ | J | ’s are required to be positive. Our proposed digital diffeomorphism criteria solves several errors inherent in the central difference approximation of $$\vert J\vert $$ | J | and accurately detects non-diffeomorphic digital transformations. The source code of this work is available at https://github.com/yihao6/digital_diffeomorphism.

Improving hybrid image and structure-based deformable image registration for large internal deformations

Objective. Deformable image registration (DIR) is a widely used technique in radiotherapy. Complex deformations, resulting from large anatomical changes, are a regular challenge. DIR algorithms generally seek a balance between capturing large deformations and preserving a smooth deformation vector field (DVF). We propose a novel structure-based term that can enhance the registration efficacy while ensuring a smooth DVF. Approach. The proposed novel similarity metric for controlling structures was introduced as a new term into a commercially available algorithm. Its performance was compared to the original algorithm using a dataset of 46 patients who received pelvic re-irradiation, many of which exhibited complex deformations. Main results. The mean Dice Similarity Coefficient (DSC) under the improved algorithm was 0.96, 0.94, 0.76, and 0.91 for bladder, rectum, colon, and bone respectively, compared to 0.69, 0.89, 0.62, and 0.88 for the original algorithm. The improvement was more pronounced for complex deformations. Significance. With this work, we have demonstrated that the proposed term is able to improve registration accuracy for complex cases while maintaining realistic deformations.

Clinical feasibility of deep learning-based synthetic CT images from T2-weighted MR images for cervical cancer patients compared to MRCAT

This work aims to investigate the clinical feasibility of deep learning-based synthetic CT images for cervix cancer, comparing them to MR for calculating attenuation (MRCAT). Patient cohort with 50 pairs of T2-weighted MR and CT images from cervical cancer patients was split into 40 for training and 10 for testing phases. We conducted deformable image registration and Nyul intensity normalization for MR images to maximize the similarity between MR and CT images as a preprocessing step. The processed images were plugged into a deep learning model, generative adversarial network. To prove clinical feasibility, we assessed the accuracy of synthetic CT images in image similarity using structural similarity (SSIM) and mean-absolute-error (MAE) and dosimetry similarity using gamma passing rate (GPR). Dose calculation was performed on the true and synthetic CT images with a commercial Monte Carlo algorithm. Synthetic CT images generated by deep learning outperformed MRCAT images in image similarity by 1.5% in SSIM, and 18.5 HU in MAE. In dosimetry, the DL-based synthetic CT images achieved 98.71% and 96.39% in the GPR at 1% and 1 mm criterion with 10% and 60% cut-off values of the prescription dose, which were 0.9% and 5.1% greater GPRs over MRCAT images.

A three-dimensional left atrial motion estimation from retrospective gated computed tomography: application in heart failure patients with atrial fibrillation.

A reduced left atrial (LA) strain correlates with the presence of atrial fibrillation (AF). Conventional atrial strain analysis uses two-dimensional (2D) imaging, which is, however, limited by atrial foreshortening and an underestimation of through-plane motion. Retrospective gated computed tomography (RGCT) produces high-fidelity three-dimensional (3D) images of the cardiac anatomy throughout the cardiac cycle that can be used for estimating 3D mechanics. Its feasibility for LA strain measurement, however, is understudied. The aim of this study is to develop and apply a novel workflow to estimate 3D LA motion and calculate the strain from RGCT imaging. The utility of global and regional strains to separate heart failure in patients with reduced ejection fraction (HFrEF) with and without AF is investigated. A cohort of 30 HFrEF patients with (n = 9) and without (n = 21) AF underwent RGCT prior to cardiac resynchronisation therapy. The temporal sparse free form deformation image registration method was optimised for LA feature tracking in RGCT images and used to estimate 3D LA endocardial motion. The area and fibre reservoir strains were calculated over the LA body. Universal atrial coordinates and a human atrial fibre atlas enabled the regional strain calculation and the fibre strain calculation along the local myofibre orientation, respectively. It was found that global reservoir strains were significantly reduced in the HFrEF + AF group patients compared with the HFrEF-only group patients (area strain: 11.2 ± 4.8% vs. 25.3 ± 12.6%, P = 0.001; fibre strain: 4.5 ± 2.0% vs. 15.2 ± 8.8%, P = 0.001), with HFrEF + AF patients having a greater regional reservoir strain dyssynchrony. All regional reservoir strains were reduced in the HFrEF + AF patient group, in whom the inferior wall strains exhibited the most significant differences. The global reservoir fibre strain and LA volume + posterior wall reservoir fibre strain exceeded LA volume alone and 2D global longitudinal strain (GLS) for AF classification (area-under-the-curve: global reservoir fibre strain: 0.94 ± 0.02, LA volume + posterior wall reservoir fibre strain: 0.95 ± 0.02, LA volume: 0.89 ± 0.03, 2D GLS: 0.90 ± 0.03). RGCT enables 3D LA motion estimation and strain calculation that outperforms 2D strain metrics and LA enlargement for AF classification. Differences in regional LA strain could reflect regional myocardial properties such as atrial fibrosis burden.

Repeatability and reproducibility of prostate apparent diffusion coefficient values on a 1.5 T magnetic resonance linear accelerator

Background and PurposeIntegrated magnetic resonance linear accelerator (MR-Linac) systems offer potential for biologically based adaptive radiation therapy using apparent diffusion coefficient (ADC). Accurate tracking of longitudinal ADC changes is key to establishing ADC-driven dose adaptation. Here, we report repeatability and reproducibility of intraprostatic ADC using deformable image registration (DIR) to correct for inter-fraction prostate changes. Materials and MethodsThe study included within-fraction repeat ADC measurements for three consecutive fractions for 20 patients with prostate cancer treated on a 1.5 T MR-Linac. We deformably registered successive fraction T2-weighted images and applied the deformation vector field to corresponding ADC maps to align to fraction 2. We delineated gross tumour volume (GTV), peripheral zone (PZ) and prostate clinical target volume (CTV) regions-of-interest (ROIs) on T2-weighted MRI and copied to ADC maps. We computed intraclass correlation coefficients (ICC) and percent repeatability coefficient (%RC) to determine within-fraction repeatability and between-fraction reproducibility for individual voxels, mean and 10th percentile ADC values per ROI. ResultsThe ICC between repeats and fractions was excellent for mean and 10th percentile ADC in all ROIs (ICC > 0.86), and moderate repeatability and reproducibility existed for individual voxels (ICC > 0.542). Similarly, low %RC within-fraction (4.2–17.9 %) mean and 10th percentile ADC existed, with greater %RC between fractions (10.2–36.8 %). Higher %RC existed for individual voxel within-fraction (21.7–30.6 %) and between-fraction (32.1–34.5 %) ADC. ConclusionsResults suggest excellent ADC repeatability and reproducibility in clinically relevant ROIs using DIR to correct between-fraction anatomical changes. We established the precision of voxel-level ADC tracking for future biologically based adaptation implementation.

A comprehensive lung CT landmark pair dataset for evaluating deformable image registration algorithms.

Deformable image registration (DIR) is a key enabling technology in many diagnostic and therapeutic tasks, but often does not meet the required robustness and accuracy for supporting clinical tasks. This is in large part due to a lack of high-quality benchmark datasets by which new DIR algorithms can be evaluated. Our team was supported by the National Institute of Biomedical Imaging and Bioengineering to develop DIR benchmark dataset libraries for multiple anatomical sites, comprising of large numbers of highly accurate landmark pairs on matching blood vessel bifurcations. Here we introduce our lung CT DIR benchmark dataset library, which was developed to improve upon the number and distribution of landmark pairs in current public lung CT benchmark datasets. Thirty CT image pairs were acquired from several publicly available repositories as well as authors' institution with IRB approval. The data processing workflow included multiple steps: (1) The images were denoised. (2) Lungs, airways, and blood vessels were automatically segmented. (3) Bifurcations were directly detected on the skeleton of the segmented vessel tree. (4) Falsely identified bifurcations were filtered out using manually defined rules. (5) A DIR was used to project landmarks detected on the first image onto the second image of the image pair to form landmark pairs. (6) Landmark pairs were manually verified. This workflow resulted in an average of 1262 landmark pairs per image pair. Estimates of the landmark pair target registration error (TRE) using digital phantoms were 0.4mm±0.3mm. The data is published in Zenodo at https://doi.org/10.5281/zenodo.8200423. Instructions for use can be found at https://github.com/deshanyang/Lung-DIR-QA. The dataset library generated in this work is the largest of its kind to date and will provide researchers with a new and improved set of ground truth benchmarks for quantitatively validating DIR algorithms within the lung.

Evaluation of the availability of single-position treatment with a rotating gantry and the validity of deformable image registration dose assessment for pancreatic cancer carbon-ion radiotherapy.

This study aimed to evaluate the clinical acceptability of rotational gantry-based single-position carbon-ion radiotherapy (CIRT) to reduce the gastrointestinal (GI) dose in pancreatic cancer. We also evaluated the usefulness of the deformable image registration (DIR)-based dosimetry method for CIRT. Fifteen patients with pancreatic cancer were analyzed. The treatment plans were developed for four beam angles in the supine (SP plan) and prone (PR plan) positions. In the case of using multiple positions, the treatment plan was created with two angles for each of the supine and prone position (SP + PR plan). Dose evaluation for multiple positions was performed in two ways: by directly adding the values of the DVH parameters for each position treatment plan (DVH sum), and by calculating the DVH parameters from the accumulative dose distribution created using DIR (DIR sum). The D2cc and D6cc of the stomach and duodenum were recorded for each treatment plan and dosimetry method and compared. There were no significant differences among any of the treatment planning and dosimetry methods (p>0.05). The DVH parameters for the stomach and duodenum were higher in the PR plan and SP plan, respectively, and DVH sum tended to be between the SP and PR plans. DVH sum and DIR sum, DVH sum tended to be higher for D2cc and DIR sum tended to be higher for D6cc . There were no significant differences in the GI dose, which suggests that treatment with a simple workflow performed in one position should be clinically acceptable. In CIRT, DIR-based dosimetry should be carefully considered because of the potential for increased uncertainty due to the steep dose distributions.

Deformable registration of preoperative MR and intraoperative long-length tomosynthesis images for guidance of spine surgery via image synthesis

PurposeImproved integration and use of preoperative imaging during surgery hold significant potential for enhancing treatment planning and instrument guidance through surgical navigation. Despite its prevalent use in diagnostic settings, MR imaging is rarely used for navigation in spine surgery. This study aims to leverage MR imaging for intraoperative visualization of spine anatomy, particularly in cases where CT imaging is unavailable or when minimizing radiation exposure is essential, such as in pediatric surgery. MethodsThis work presents a method for deformable 3D-2D registration of preoperative MR images with a novel intraoperative long-length tomosynthesis imaging modality (viz., Long-Film [LF]). A conditional generative adversarial network is used to translate MR images to an intermediate bone image suitable for registration, followed by a model-based 3D-2D registration algorithm to deformably map the synthesized images to LF images. The algorithm’s performance was evaluated on cadaveric specimens with implanted markers and controlled deformation, and in clinical images of patients undergoing spine surgery as part of a large-scale clinical study on LF imaging. ResultsThe proposed method yielded a median 2D projection distance error of 2.0 mm (interquartile range [IQR]: 1.1–3.3 mm) and a 3D target registration error of 1.5 mm (IQR: 0.8–2.1 mm) in cadaver studies. Notably, the multi-scale approach exhibited significantly higher accuracy compared to rigid solutions and effectively managed the challenges posed by piecewise rigid spine deformation. The robustness and consistency of the method were evaluated on clinical images, yielding no outliers on vertebrae without surgical instrumentation and 3% outliers on vertebrae with instrumentation. ConclusionsThis work constitutes the first reported approach for deformable MR to LF registration based on deep image synthesis. The proposed framework provides access to the preoperative annotations and planning information during surgery and enables surgical navigation within the context of MR images and/or dual-plane LF images.

138 Beyond Rigid Registration: The Role of Deformable Image Registration for Rescans and Replans in H&N Cancer Radiotherapy

138 Beyond Rigid Registration: The Role of Deformable Image Registration for Rescans and Replans in H&N Cancer Radiotherapy

Incidental Ring-hyperenhancing Liver Micronodules at CT Hepatic Arteriography-guided Percutaneous Thermal Ablation of Colorectal Liver Metastases.

CT during hepatic arteriography (CTHA) is a highly sensitive imaging method for detecting colorectal liver metastases (CLMs), which supports its use during percutaneous thermal liver ablation. In contrast to its high sensitivity, its specificity for incidental small CLMs not detected at preablation cross-sectional imaging is believed to be low given the absence of specific imaging signatures and the common presence of pseudolesions. In this retrospective study of 22 patients (mean age, 55 years ± 10.6 [SD]; 63.6% male, 36.4% female) with CLMs undergoing CTHA-guided microwave percutaneous thermal ablation between November 2017 and October 2022, the authors provided a definition of incidental ring-hyperenhancing liver micronodules (RHLMs) and investigated whether there is a correlation of RHLMs with histologic analysis or intrahepatic tumor progression at imaging follow-up after applying a biomechanical deformable image registration method. The analysis revealed 25 incidental RHLMs in 41.7% (10 of 24) of the CTHA images from the respective guided ablation sessions. Of those, four RHLMs were ablated. Among the remaining 21 RHLMs, 71.4% (15 of 21) were confirmed to be CLM with either histology (n = 3) or imaging follow-up (n = 12). The remaining 28.6% (six of 21) of RHLMs were not observed at follow-up imaging. This suggests that RHLMs at CTHA may be an early indicator of incidental small CLMs. Keywords: Colorectal Neoplasms, Liver, Angiography, CT, Incidental Findings, Ablation Supplemental material is available for this article. © RSNA, 2024.

Pencil beam scanning proton therapy for mediastinal lymphomas in deep inspiration breath-hold: a retrospective assessment of plan robustness.

The aim of this study was to evaluate pencil beam scanning (PBS) proton therapy (PT) in deep inspiration breath-hold (DIBH) for mediastinal lymphoma patients, by retrospectively evaluating plan robustness to the clinical target volume (CTV) and organs at risk (OARs) on repeated CT images acquired throughout treatment. Methods: Sixteen mediastinal lymphoma patients treated with PBS-PT in DIBH were included. Treatment plans (TPs) were robustly optimized on the CTV (7 mm/4.5%). Repeated verification CTs (vCT) were acquired during the treatment course, resulting in 52 images for the entire patient cohort. The CTV and OARs were transferred from the planning CT to the vCTs with deformable image registration and the TPs were recalculated on the vCTs. Target coverage and OAR doses at the vCTs were compared to the nominal plan. Deviation in lung volume was also calculated. The TPs demonstrated high robust target coverage throughout treatment with D98%,CTV deviations within 2% for 14 patients and above the desired requirement of 95% for 49/52 vCTs. However, two patients did not achieve a robust dose to CTV due to poor DIBH reproducibility, with D98%,CTV at 78 and 93% respectively, and replanning was performed for one patient. Adequate OAR sparing was achieved for all patients. Total lung volume variation was below 10% for 39/52 vCTs. PBS PT in DIBH is generally a robust technique for treatment of mediastinal lymphomas. However, closely monitoring the DIBH-reproducibility during treatment is important to avoid underdosing CTV and achieve sufficient dose-sparing of the OARs.

Impact of radiation dose distribution on nutritional supplementation needs in head and neck cancer radiotherapy: a voxel-based machine learning approach.

To investigate the relationship between nutritional supplementation and radiation dose to the pharyngeal constrictor muscles and larynx for head and neck (HN) cancer patients undergoing radiotherapy. We retrospectively analyzed radiotherapy (RT) dose for 231 HN cancer patients, focusing on the pharyngeal constrictors and larynx. We defined nutritional supplementation as feeding tube utilization or >10% weight loss from baseline within 90 days after radiotherapy completion. Using deformable image registration (DIR), we mapped each patient's anatomical structures to a reference coordinate system, and corresponding deformations were applied to dose matrices. Voxel doses were utilized as features for ridge logistic regression models, optimized through 5-fold cross-validation. Model performance was assessed with area under the curve of a receiver operating curve (AUC) and F1 score. We built and compared models using 1) pharyngeal constrictor voxels, 2) larynx voxels, 3) clinical factors and mean regional dose metrics, and 4) clinical factors and dose-volume histogram metrics. Test set AUCs were compared among the models, and feature importance was evaluated. DIR of the pharyngeal constrictors and larynx yielded mean Dice coefficients of 0.80 and 0.84, respectively. Pharyngeal constrictors voxels and larynx voxel models had AUC of 0.88 and 0.82, respectively. Voxel-based dose modeling identified the superior to middle regions of the pharyngeal constrictors and the superior region of larynx as most predictive of feeding tube use/weight loss. Univariate analysis found treatment setting, treatment laterality, chemotherapy, baseline dysphagia, weight, and socioeconomic status predictive of outcome. An aggregated model using mean doses of pharyngeal constrictors and larynx subregions had an AUC of 0.87 and the model using conventional DVH metrics had an AUC of 0.85 with p-value of 0.04. Feature importance calculations from the regional dose model indicated that mean doses to the superior-middle pharyngeal constrictor muscles followed by mean dose to the superior larynx were most predictive of nutritional supplementation. Machine learning modeling of voxel-level doses enables identification of subregions within organs that correlate with toxicity. For HN radiotherapy, doses to the superior-middle pharyngeal constrictors are most predictive of feeding tube use/weight loss followed by the doses to superior portion of the larynx.

PNMC: Four-dimensional conebeam CT reconstruction combining prior network and motion compensation

Four-dimensional conebeam computed tomography (4D CBCT) is an efficient technique to overcome motion artifacts caused by organ motion during breathing. 4D CBCT reconstruction in a single scan usually divides projections into different groups of sparsely sampled data based on the respiratory phases. The reconstructed images within each group present poor image quality due to the limited number of projections. To improve the image quality of 4D CBCT in a single scan, we propose a novel reconstruction scheme that combines prior knowledge with motion compensation. We apply the reconstructed images of the full projections within a single routine as prior knowledge, providing structural information for the network to enhance the restoration structure. The prior network (PN-Net) is proposed to extract features of prior knowledge and fuse them with the sparsely sampled data using an attention mechanism. The prior knowledge guides the reconstruction process to restore the approximate organ structure and alleviates severe streaking artifacts. The deformation vector field (DVF) extracted using deformable image registration among different phases is then applied in the motion-compensated ordered-subset simultaneous algebraic reconstruction algorithm to generate 4D CBCT images. Proposed method has been evaluated using simulated and clinical datasets and has shown promising results by comparative experiment. Compared with previous methods, our approach exhibits significant improvements across various evaluation metrics.

UDRSNet: An unsupervised deformable registration module based on image structure similarity.

Image registration is a challenging problem in many clinical tasks, but deep learning has made significant progress in this area over the past few years. Real-time and robust registration has been made possible by supervised transformation estimation. However, the quality of registrations using this framework depends on the quality of ground truth labels such as displacement field. To propose a simple and reliable method for registering medical images based on image structure similarity in a completely unsupervised manner. We proposed a deep cascade unsupervised deformable registration approach to align images without reliable clinical data labels. Our basic network was composed of a displacement estimation module (ResUnet) and a deformation module (spatial transformer layers). We adopted l2 -norm to regularize the deformation field instead of the traditional l1 -norm regularization. Additionally, we utilized structural similarity (ssim) estimation during the training stage to enhance the structural consistency between the deformed images and the reference images. Experiments results indicated that by incorporating ssim loss, our cascaded methods not only achieved higher dice score of 0.9873, ssim score of 0.9559, normalized cross-correlation (NCC) score of 0.9950, and lower relative sum of squared difference (SSD) error of 0.0313 on CT images, but also outperformed the comparative methods on ultrasound dataset. The statistical t-test results also proved that these improvements of our method have statisticalsignificance. In this study, the promising results based on diverse evaluation metrics have demonstrated that our model is simple and effective in deformable image registration (DIR). The generalization ability of the model was also verified through experiments on liver CT images and cardiac ultrasound images.