Deformable Image Registration Research Articles

Deformable anthropomorphic pelvis phantom for dose accumulation verification

Objective. The validation of deformable image registration (DIR) for contour propagation is often done using contour-based metrics. Meanwhile, dose accumulation requires evaluation of voxel mapping accuracy, which might not be accurately represented by contour-based metrics. By fabricating a deformable anthropomorphic pelvis phantom, we aim to (1) quantify the voxel mapping accuracy for various deformation scenarios, in high- and low-contrast regions, and (2) identify any correlation between dice similarity coefficient (DSC), a commonly used contour-based metric, and the voxel mapping accuracy for each organ. Approach. Four organs, i.e. pelvic bone, prostate, bladder and rectum (PBR), were 3D printed using PLA and a Polyjet digital material, and assembled. The latter three were implanted with glass bead and CT markers within or on their surfaces. Four deformation scenarios were simulated by varying the bladder and rectum volumes. For each scenario, nine DIRs with different parameters were performed on RayStation v10B. The voxel mapping accuracy was quantified by finding the discrepancy between true and mapped marker positions, termed the target registration error (TRE). Pearson correlation test was done between the DSC and mean TRE for each organ. Main results. For the first time, we fabricated a deformable phantom purely from 3D printing, which successfully reproduced realistic anatomical deformations. Overall, the voxel mapping accuracy dropped with increasing deformation magnitude, but improved when more organs were used to guide the DIR or limit the registration region. DSC was found to be a good indicator of voxel mapping accuracy for prostate and rectum, but a comparatively poorer one for bladder. DSC > 0.85/0.90 was established as the threshold of mean TRE ⩽ 0.3 cm for rectum/prostate. For bladder, extra metrics in addition to DSC should be considered. Significance. This work presented a 3D printed phantom, which enabled quantification of voxel mapping accuracy and evaluation of correlation between DSC and voxel mapping accuracy.

Diffeomorphic transformer-based abdomen MRI-CT deformable image registration.

Stereotactic body radiotherapy (SBRT) is a well-established treatment modality for liver metastases in patients unsuitable for surgery. Both CT and MRI are useful during treatment planning for accurate target delineation and to reduce potential organs-at-risk (OAR) toxicity from radiation. MRI-CT deformable image registration (DIR) is required to propagate the contours defined on high-contrast MRI to CT images. An accurate DIR method could lead to more precisely defined treatment volumes and superior OAR sparing on the treatment plan. Therefore, it is beneficial to develop an accurate MRI-CT DIR for liver SBRT. To create a new deep learning model that can estimate the deformation vector field (DVF) for directly registering abdominal MRI-CT images. The proposed method assumed a diffeomorphic deformation. By using topology-preserved deformation features extracted from the probabilistic diffeomorphic registration model, abdominal motion can be accurately obtained and utilized for DVF estimation. The model integrated Swin transformers, which have demonstrated superior performance in motion tracking, into the convolutional neural network (CNN) for deformation feature extraction. The model was optimized using a cross-modality image similarity loss and a surface matching loss. To compute the image loss, a modality-independent neighborhood descriptor (MIND) was used between the deformed MRI and CT images. The surface matching loss was determined by measuring the distance between the warped coordinates of the surfaces of contoured structures on the MRI and CT images. To evaluate the performance of the model, a retrospective study was carried out on a group of 50 liver cases that underwent rigid registration of MRI and CT scans. The deformed MRI image was assessed against the CT image using the target registration error (TRE), Dice similarity coefficient (DSC), and mean surface distance (MSD) between the deformed contours of the MRI image and manual contours of the CT image. When compared to only rigid registration, DIR with the proposed method resulted in an increase of the mean DSC values of the liver and portal vein from 0.850±0.102 and 0.628±0.129 to 0.903±0.044 and 0.763±0.073, a decrease of the mean MSD of the liver from 7.216±4.513mm to 3.232±1.483mm, and a decrease of the TRE from 26.238±2.769mm to 8.492±1.058mm. The proposed DIR method based on a diffeomorphic transformer provides an effective and efficient way to generate an accurate DVF from an MRI-CT image pair of the abdomen. It could be utilized in the current treatment planning workflow for liver SBRT.

Uncertainty estimation and evaluation of deformation image registration based convolutional neural networks

Objective. Fast and accurate deformable image registration (DIR), including DIR uncertainty estimation, is essential for safe and reliable clinical deployment. While recent deep learning models have shown promise in predicting DIR with its uncertainty, challenges persist in proper uncertainty evaluation and hyperparameter optimization for these methods. This work aims to develop and evaluate a model that can perform fast DIR and predict its uncertainty in seconds. Approach. This study introduces a novel probabilistic multi-resolution image registration model utilizing convolutional neural networks to estimate a multivariate normal distributed dense displacement field (DDF) in a multimodal image registration problem. To assess the quality of the DDF distribution predicted by the model, we propose a new metric based on the Kullback–Leibler divergence. The performance of our approach was evaluated against three other DIR algorithms (VoxelMorph, Monte Carlo dropout, and Monte Carlo B-spline) capable of predicting uncertainty. The evaluation of the models included not only the quality of the deformation but also the reliability of the estimated uncertainty. Our application investigated the registration of a treatment planning computed tomography (CT) to follow-up cone beam CT for daily adaptive radiotherapy. Main results. The hyperparameter tuning of the models showed a trade-off between the estimated uncertainty’s reliability and the deformation’s accuracy. In the optimal trade-off, our model excelled in contour propagation and uncertainty estimation (p <0.05) compared to existing uncertainty estimation models. We obtained an average dice similarity coefficient of 0.89 and a KL-divergence of 0.15. Significance. By addressing challenges in DIR uncertainty estimation and evaluation, our work showed that both the DIR and its uncertainty can be reliably predicted, paving the way for safe deployment in a clinical environment.

Pure large kernel convolutional neural network transformer for medical image registration

Deformable medical image registration is a fundamental and critical task in medical image analysis. Recently, deep learning-based methods have rapidly developed and have shown impressive results in deformable image registration. However, existing approaches still suffer from limitations in registration accuracy or generalization performance. To address these challenges, in this paper, we propose a pure convolutional neural network module (CVTF) to implement hierarchical transformers and enhance the registration performance of medical images. CVTF has a larger convolutional kernel, providing a larger global effective receptive field, which can improve the network’s ability to capture long-range dependencies. In addition, we introduce the spatial interaction attention (SIA) module to compute the interrelationship between the target feature pixel points and all other points in the feature map. This helps to improve the semantic understanding of the model by emphasizing important features and suppressing irrelevant ones. Based on the proposed CVTF and SIA, we construct a novel registration framework named PCTNet. We applied PCTNet to generate displacement fields and register medical images, and we conducted extensive experiments and validation on two public datasets, OASIS and LPBA40. The experimental results demonstrate the effectiveness and generality of our method, showing significant improvements in registration accuracy and generalization performance compared to existing methods. Our code has been available at https://github.com/fz852/PCTNet.

A light-weight rectangular decomposition large kernel convolution network for deformable medical image registration

The performance and speed of medical image registration have been greatly boosted by advanced deep-learning based methods. However, most current methods are challenged by large deformations between input images, which necessitate a compromise in computational cost to enhance the model’s receptive field and its ability to model long-range spatial relationships for improving registration performance. In order to enhance the performance of registration for images with large deformations at a lower computational cost, in this paper, we propose a light-weight registration model with the ability to model large receptive fields and long-range spatial relationships, named LL-Net. The core components of LL-Net consist of a Rectangular Decomposition Large Kernel Attention (RD-LKA) layer and a Spatial and Channel Fusion Attention (SC-Fusion) layer. The RD-LKA layer utilizes anisotropic depth-wise large kernel convolutions to capture large receptive fields with an extremely low parameter count while modeling long-range spatial relationships. Moreover, the SC-Fusion layer enhances the model’s feature fusion capability and strengthens feature representations at critical locations. Our LL-Net exhibits state-of-the-art performance across multiple datasets. Specifically, it achieves a Dice score of 76.7% and an HD95 of 2.983 mm on the IXI dataset, and a Dice score of 87.8% and an HD95 of 1.042 mm on the OASIS dataset. Experimental results substantiate the efficacy of LL-Net in capturing large receptive fields and modeling long-range spatial relationships. The code for LL-Net is available at https://github.com/BoyOfChu/LL_Net.

CMAN: Cascaded Multi-scale Spatial Channel Attention-guided Network for large 3D deformable registration of liver CT images

Deformable image registration is an essential component of medical image analysis and plays an irreplaceable role in clinical practice. In recent years, deep learning-based registration methods have demonstrated significant improvements in convenience, robustness and execution time compared to traditional algorithms. However, registering images with large displacements, such as those of the liver organ, remains underexplored and challenging. In this study, we present a novel convolutional neural network (CNN)-based unsupervised learning registration method, Cascaded Multi-scale Spatial-Channel Attention-guided Network (CMAN), which addresses the challenge of large deformation fields using a double coarse-to-fine registration approach. The main contributions of CMAN include: (i) local coarse-to-fine registration in the base network, which generates the displacement field for each resolution and progressively propagates these local deformations as auxiliary information for the final deformation field; (ii) global coarse-to-fine registration, which stacks multiple base networks for sequential warping, thereby incorporating richer multi-layer contextual details into the final deformation field; (iii) integration of the spatial-channel attention module in the decoder stage, which better highlights important features and improves the quality of feature maps. The proposed network was trained using two public datasets and evaluated on another public dataset as well as a private dataset across several experimental scenarios. We compared CMAN with four state-of-the-art CNN-based registration methods and two well-known traditional algorithms. The results show that the proposed double coarse-to-fine registration strategy outperforms other methods in most registration evaluation metrics. In conclusion, CMAN can effectively handle the large-deformation registration problem and show potential for application in clinical practice. The source code is made publicly available at https://github.com/LocPham263/CMAN.git.

Pre-operative lung ablation prediction using deep learning.

Microwave lung ablation (MWA) is a minimally invasive and inexpensive alternative cancer treatment for patients who are not candidates for surgery/radiotherapy. However, a major challenge for MWA is its relatively high tumor recurrence rates, due to incomplete treatment as a result of inaccurate planning. We introduce a patient-specific, deep-learning model to accurately predict post-treatment ablation zones toaidplanning and enable effective treatments. Our IRB-approved retrospective study consisted of ablations with a single applicator/burn/vendor between 01/2015 and 01/2019. The input data included pre-procedure computerized tomography (CT), ablation power/time, and applicator position. The ground truth ablation zone was segmented from follow-up CT post-treatment. Novel deformable image registration optimized for ablation scans and an applicator-centric co-ordinate system for data analysis were applied. Our prediction model was based on the U-net architecture. The registrations were evaluated using target registration error (TRE) and predictions using Bland-Altman plots, Dice co-efficient, precision, and recall, compared against the applicator vendor's estimates. The data included 113 unique ablations from 72 patients (median age 57, interquartile range (IQR) (49-67); 41 women). We obtained a TRE ≤ 2 mm on 52 ablations. Our prediction had no bias from ground truth ablation volumes (p = 0.169) unlike the vendor's estimate (p < 0.001) and had smaller limits of agreement (p < 0.001). An 11% improvement was achieved in the Dice score. The ability to account for patient-specific in-vivo anatomical effects due to vessels, chest wall, heart, lung boundaries, and fissures was shown. We demonstrated a patient-specific deep-learning model to predict the ablation treatment effect prior to the procedure, with the potential for improved planning, achievingcomplete treatments, and reduce tumor recurrence. Our method addresses the current lack of reliable tools to estimate ablation extents, required for ensuring successful ablation treatments. The potential clinical implications include improved treatment planning, ensuring complete treatments, and reducing tumor recurrence.

Enhancing voxel-based dosimetry accuracy with an unsupervised deep learning approach for hybrid medical image registration.

Deformable registration is required to generate a time-integrated activity (TIA) map which is essential for voxel-based dosimetry. The conventional iterative registration algorithm using anatomical images (e.g., computed tomography (CT)) could result in registration errors in functional images (e.g., single photon emission computed tomography (SPECT) or positron emission tomography (PET)). Various deep learning-based registration tools have been proposed, but studies specifically focused on the registration of serial hybrid images were not found. In this study, we introduce CoRX-NET, a novel unsupervised deep learning network designed for deformable registration of hybrid medical images. The CoRX-NET structure is based on the Swin-transformer (ST), allowing for the representation of complex spatial connections in images. Its self-attention mechanism aids in the effective exchange and integration of information across diverse image regions. To augment the amalgamation of SPECT and CT features, cross-stitch layers have been integrated into the network. Two different 177 Lu DOTATATE SPECT/CT datasets were acquired at different medical centers. 22 sets from Seoul National University and 14 sets from Sunway Medical Centre are used for training/internal validation and external validation respectively. The CoRX-NET architecture builds upon the ST, enabling the modeling of intricate spatial relationships within images. To further enhance the fusion of SPECT and CT features, cross-stitch layers have been incorporated within the network. The network takes a pair of SPECT/CT images (e.g., fixed and moving images) and generates a deformed SPECT/CT image. The performance of the network was compared with Elastix and TransMorph using L1 loss and structural similarity index measure (SSIM) of CT, SSIM of normalized SPECT, and local normalized cross correlation (LNCC) of SPECT as metrics. The voxel-wise root mean square errors (RMSE) of TIA were compared among the different methods. The ablation study revealed that cross-stitch layers improved SPECT/CT registration performance. The cross-stitch layers notably enhance SSIM (internal validation: 0.9614vs. 0.9653, external validation: 0.9159vs. 0.9189) and LNCC of normalized SPECT images (internal validation: 0.7512vs. 0.7670, external validation: 0.8027vs. 0.8027). CoRX-NET with the cross-stitch layer achieved superior performance metrics compared to Elastix and TransMorph, except for CT SSIM in the external dataset. When qualitatively analyzed for both internal and external validation cases, CoRX-NET consistently demonstrated superior SPECT registration results. In addition, CoRX-NET accomplished SPECT/CT image registration in less than 6s, whereas Elastix required approximately 50s using the same PC's CPU. When employing CoRX-NET, it was observed that the voxel-wise RMSE values for TIA were approximately 27% lower for the kidney and 33% lower for the tumor, compared to when Elastix was used. This study represents a major advancement in achieving precise SPECT/CT registration using an unsupervised deep learning network. It outperforms conventional methods like Elastix and TransMorph, reducing uncertainties in TIA maps for more accurate dose assessments.

Deformable registration of magnetic resonance images using unsupervised deep learning in neuro-/radiation oncology

PurposeAccurate deformable registration of magnetic resonance imaging (MRI) scans containing pathologies is challenging due to changes in tissue appearance. In this paper, we developed a novel automated three-dimensional (3D) convolutional U-Net based deformable image registration (ConvUNet-DIR) method using unsupervised learning to establish correspondence between baseline pre-operative and follow-up MRI scans of patients with brain glioma.MethodsThis study involved multi-parametric brain MRI scans (T1, T1-contrast enhanced, T2, FLAIR) acquired at pre-operative and follow-up time for 160 patients diagnosed with glioma, representing the BraTS-Reg 2022 challenge dataset. ConvUNet-DIR, a deep learning-based deformable registration workflow using 3D U-Net style architecture as a core, was developed to establish correspondence between the MRI scans. The workflow consists of three components: (1) the U-Net learns features from pairs of MRI scans and estimates a mapping between them, (2) the grid generator computes the sampling grid based on the derived transformation parameters, and (3) the spatial transformation layer generates a warped image by applying the sampling operation using interpolation. A similarity measure was used as a loss function for the network with a regularization parameter limiting the deformation. The model was trained via unsupervised learning using pairs of MRI scans on a training data set (n = 102) and validated on a validation data set (n = 26) to assess its generalizability. Its performance was evaluated on a test set (n = 32) by computing the Dice score and structural similarity index (SSIM) quantitative metrics. The model’s performance also was compared with the baseline state-of-the-art VoxelMorph (VM1 and VM2) learning-based algorithms.ResultsThe ConvUNet-DIR model showed promising competency in performing accurate 3D deformable registration. It achieved a mean Dice score of 0.975 ± 0.003 and SSIM of 0.908 ± 0.011 on the test set (n = 32). Experimental results also demonstrated that ConvUNet-DIR outperformed the VoxelMorph algorithms concerning Dice (VM1: 0.969 ± 0.006 and VM2: 0.957 ± 0.008) and SSIM (VM1: 0.893 ± 0.012 and VM2: 0.857 ± 0.017) metrics. The time required to perform a registration for a pair of MRI scans is about 1 s on the CPU.ConclusionsThe developed deep learning-based model can perform an end-to-end deformable registration of a pair of 3D MRI scans for glioma patients without human intervention. The model could provide accurate, efficient, and robust deformable registration without needing pre-alignment and labeling. It outperformed the state-of-the-art VoxelMorph learning-based deformable registration algorithms and other supervised/unsupervised deep learning-based methods reported in the literature.

C2FResMorph: A high-performance framework for unsupervised 2D medical image registration

Deformable medical image registration is an important precursor task for surgical automation, while enhancing the registration performance of 2D medical images remains a challenging work. Existing methods primarily minimize the similarity loss between image pairs as the main optimization objective, leading to limited registration accuracy and a lack of pixel matching. Moreover, the scarcity of informative features in 2D images often results in overfitting on the training set, hampering generalization. To address these issues, we propose C2FResMorph, a learning-based deformable registration algorithm specifically designed for 2D medical images. C2FResMorph employs a two-stage framework that improves registration accuracy and preserves topology during deformation in a coarse-to-fine manner. Inside the framework, by leveraging the convolutional neural network’s locality and the multi-head self-attention mechanism’s globality, a ResMorph registration network is designed. Additionally, the integration of residual image knowledge addresses deformation folding in 2D image registration, enhancing the preservation of local structures and improving generalization. Experimental evaluations on three datasets demonstrate that C2FResMorph outperforms existing learning-based methods in terms of accuracy, generalization ability for 2D medical image registration, and also retains the efficiency advantages.

Deformable vector fields warping for modelling of irregular breathing.

Purpose&#xD;4D computed tomography (4DCT) is the clinical standard to image organ motion in radiotherapy, although it is limited in imaging breathing variability. We propose a method to transfer breathing motion across longitudinal imaging datasets to include intra-patient variability and verify its performance in lung cancer patients. &#xD;Methods &#xD;Five repeated control 4DCTs for 6 non-small cell lung cancer patients were combined into multi-breath datasets (m4DCT) by merging stages of deformable image registration to isolate respiratory motion. The displacement of the centre of mass of the primary tumour and its volume changes were evaluated to quantify intra-patient differences. Internal target volumes defined on the m4DCT were compared with those conventionally drawn on the 4DCT.&#xD;Results &#xD;Motion analysis suggests no discontinuity at the junction between successive breaths, confirming the method's ability to merge repeated imaging into a continuum. Motion (variability) is primarily in superior-inferior direction and goes from 14.4 mm (8.7 mm) down to 0.1 mm (0.6 mm), respectively for tumours located in the lower lobes or most apical ones. On average, up to 65% and 74% of the tumour volume was subject to expansion or contraction in the inhalation and exhalation phases. These variations lead to an enlargement of the ITV up to 8% of its volume in our dataset.&#xD;Conclusion &#xD;4DCT can be extended to model variable breathing motion by adding synthetic phases from multiple time-resolved images. The inclusion of this improved knowledge of patients' breathing allows better definition of treatment volumes and their margins for radiation therapy.&#xD.

Dysphagia in Head and Neck Radiotherapy: The Influence of Pharyngeal Constrictor Anatomy and Dosimetry.

The goal of this study was to identify which anatomical and dosimetric changes correlated with late patient-reported dysphagia throughout the course of head and neck chemo-radiotherapy treatment. The patient cohort (n = 64) considered oropharyngeal and nasopharyngeal patients treated with curative intent, exhibiting no baseline dysphagia with a follow-up time greater than one year. Patients completed the MD Anderson Dysphagia Inventory during a follow-up visit. A composite score was measured ranging from 20 to 100, with a low score indicating a high symptom burden; a score ≤60 indicated patient-reported dysphagia. The pharyngeal (PCM) and cricopharyngeal constrictor muscles (CPM) were contoured on a planning CT image and adapted to weekly cone-beam CT anatomy using deformable image registration and dose was accumulated using weighted dose-volume histogram curves. The PCM and CPM were examined for volume, thickness, and dosimetric changes across treatment with the results correlated to symptom group. Anatomical evaluation indicated the PCM thickness increased more during treatment for patients with dysphagia, with base of C2 vertebrae (p = 0.04) and superior-inferior middle PCM (p = 0.01) thicknesses indicating a 1.0-1.5mm increase. The planned and delivered mean dose and DVH metrics to PCM and CPM were found to be within random error measured for the dose accumulation, indicating delivered and planned dose are equivalent. The PCM and CPM organs were found to lie approximately 5mm closer to high dose gradients in patients exhibiting dysphagia. The volume, thickness, and high dose gradient metrics may be useful metrics to identify patients at risk of late patient-reported dysphagia.

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.

Weighted window attention and recover feature resolution-based network for deformable abdominal image registration

The Swin Transformer has attracted attention in the field of medical image analysis since its introduction in 2021 owing to its computational efficiency and long-range modeling capabilities. Because of these characteristics, the Swin Transformer can establish distant relationships between corresponding voxels at distant locations for complex abdominal image registration tasks. Transformer-based registration methods model the features of multiple fused voxels and output coarse-grained features of the same size. To enable the Transformer to output fine-grained information and strengthen the contribution of the Transformer in the registration model, we propose the recover feature resolution network (RFRNet), which converts the features outputted by the Transformer into fine-grained spatial information. In addition, fixed-window partitioning restricts the Transformer from modeling the global connection of semantic information with uncertain distances. Therefore, we proposed a weighted window attenuation (WWA) mechanism to achieve automatic global-scale interaction of window information after a window partitioning operation. Based on these improvements, we proposed a single-modal unsupervised deformable abnormal image registration model called RFR-WWANet. Qualitative and quantitative results showed that RFR-WWANet achieved significant improvements compared with the current state-of-the-art methods. Ablation experiments demonstrated the effectiveness of the RFRNet and WWA designs. Our code is available at https://github.com/MingR-Ma/RFR-WWANet.

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.

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.

A multi-institutional comparison of retrospective deformable dose accumulation for online adaptive magnetic resonance-guided radiotherapy

Background and PurposeApplication of different deformable dose accumulation (DDA) solutions makes institutional comparisons after online-adaptive magnetic resonance-guided radiotherapy (OA-MRgRT) challenging. The aim of this multi-institutional study was to analyze accuracy and agreement of DDA-implementations in OA-MRgRT. Material and MethodsOne gold standard (GS) case deformed with a biomechanical-model and five clinical cases consisting of prostate (2x), cervix, liver, and lymph node cancer, treated with OA-MRgRT, were analyzed. Six centers conducted DDA using institutional implementations. Deformable image registration (DIR) and DDA results were compared using the contour metrics Dice Similarity Coefficient (DSC), surface-DSC, Hausdorff-distance (HD95%), and accumulated dose-volume histograms (DVHs) analyzed via intraclass correlation coefficient (ICC) and clinical dosimetric criteria (CDC). ResultsFor the GS, median DDA errors ranged from 0.0 to 2.8 Gy across contours and implementations. DIR of clinical cases resulted in DSC > 0.8 for up to 81.3% of contours and a variability of surface-DSC values depending on the implementation. Maximum HD95%=73.3 mm was found for duodenum in the liver case. Although DVH ICC > 0.90 was found after DDA for all but two contours, relevant absolute CDC differences were observed in clinical cases: Prostate I/II showed maximum differences in bladder V28Gy (10.2/7.6%), while for cervix, liver, and lymph node the highest differences were found for rectum D2cm3 (2.8 Gy), duodenum Dmax (7.1 Gy), and rectum D0.5cm3 (4.6 Gy). ConclusionOverall, high agreement was found between the different DIR and DDA implementations. Case- and algorithm-dependent differences were observed, leading to potentially clinically relevant results. Larger studies are needed to define future DDA-guidelines.

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.