Deformable Image Research Articles

The mechanics of congenital heart disease: from a morphological trait to the functional echocardiographic evaluation.

Advances in pediatric cardiac surgery have resulted in a recent growing epidemic of children and young adults with congenital heart diseases (CHDs). In these patients, congenital defects themselves, surgical operations and remaining lesions may alter cardiac anatomy and impact the mechanical performance of both ventricles. Cardiac function significantly influences outcomes in CHDs, necessitating regular patient follow-up to detect clinical changes and relevant risk factors. Echocardiography remains the primary imaging method for CHDs, but clinicians must understand patients' unique anatomies as different CHDs exhibit distinct anatomical characteristics affecting cardiac mechanics. Additionally, the use of myocardial deformation imaging and 3D echocardiography has gained popularity for enhanced assessment of cardiac function and anatomy. This paper discusses the role of echocardiography in evaluating cardiac mechanics in most significant CHDs, particularly its ability to accommodate and interpret the inherent anatomical substrate in these conditions.

Unsupervised Multi-parametric MRI Registration Using Neural Optimal Transport.

Precise deformable image registration of multi-parametric MRI sequences is necessary for radiologists in order to identify abnormalities and diagnose diseases, such as prostate cancer and lymphoma. Despite recent advances in unsupervised learning-based registration, volumetric medical image registration that requires considering the variety of data distributions is still challenging. To address the problem of multi-parametric MRI sequence data registration, we propose an unsupervised domain-transported registration method, called OTMorph by employing neural optimal transport that learns an optimal transport plan to map different data distributions. We have designed a novel framework composed of a transport module and a registration module: the former transports data distribution from the moving source domain to the fixed target domain, and the latter takes the transported data and provides the deformed moving volume that is aligned with the fixed volume. Through end-to-end learning, our proposed method can effectively learn deformable registration for the volumes in different distributions. Experimental results with abdominal multi-parametric MRI sequence data show that our method has superior performance over around 67-85% in deforming the MRI volumes compared to the existing learning-based methods. Our method is generic in nature and can be used to register inter-/intra-modality images by mapping the different data distributions in network training.

Prognostic significance of echocardiographic deformation imaging in adult congenital heart disease.

Due to medical and surgical advancements, the population of adult patients with congenital heart disease (ACHD) is growing. Despite successful therapy, ACHD patients face structural sequalae, placing them at increased risk for heart failure and arrhythmias. Left and right ventricular function are important predictors for adverse clinical outcomes. In acquired heart disease it has been shown that echocardiographic deformation imaging is of superior prognostic value as compared to conventional parameters as ejection fraction. However, in adult congenital heart disease, the clinical significance of deformation imaging has not been systematically assessed and remains unclear. According to the Preferred Reporting Items for Systematic Reviews checklist, this systematic review included studies that reported on the prognostic value of echocardiographic left and/or right ventricular strain by 2-dimensional speckle tracking for hard clinical end-points (death, heart failure hospitalization, arrhythmias) in the most frequent forms of adult congenital heart disease. In total, 19 contemporary studies were included. Current data shows that left ventricular and right ventricular global longitudinal strain (GLS) predict heart failure, transplantation, ventricular arrhythmias and mortality in patients with Ebstein's disease and tetralogy of Fallot, and that GLS of the systemic right ventricle predicts heart failure and mortality in patients post atrial switch operation or with a congenitally corrected transposition of the great arteries. Deformation imaging can potentially impact the clinical decision making in ACHD patients. Further studies are needed to establish disease-specific reference strain values and ranges of impaired strain that would indicate the need for medical or structural intervention.

Performance Evaluation of Deformable Image Registration Systems - SmartAdapt® and Velocity™.

To commission and validate commercial deformable image registration (DIR) systems (SmartAdapt® and Velocity™) using task group 132 (TG-132) digital phantom datasets. Additionally, the study compares and verifies the DIR algorithms of the two systems. TG-132 digital phantoms were obtained from the American Association of Physicists in Medicine website and imported into SmartAdapt® and Velocity™ systems for commissioning and validation. The registration results were compared with known shifts using rigid registrations and deformable registrations. Virtual head and neck phantoms obtained online (DIR Evaluation Project) and some selected clinical data sets from the department were imported into the two DIR systems. For both of these datasets, DIR was carried out between the source and target images, and the contours were then propagated from the source to the target image data set. The dice similarity coefficient (DSC), mean distance to agreement (MDA), and Jacobian determinant measures were utilised to evaluate the registration results. The recommended criteria for commissioning and validation of DIR system from TG-132 was error <0.5*voxel dimension (vd). Translation only registration: Both systems met TG-132 recommendations except computed tomography (CT)-positron emission tomography registration in both systems (Velocity ~1.1*vd, SmartAdapt ~1.6*vd). Translational and rotational registration: Both systems failed the criteria for all modalities (For velocity, error ranged from 0.6*vd [CT-CT registration] to 3.4*vd [CT-cone-beam CT (CBCT) registration]. For SmartAdapt® the range was 0.6*vd [CT-CBCT] to 3.6*vd [CT-CT]). Mean ± standard deviation for DSC, MDA and Jacobian metrics were used to compare the DIR results between SmartAdapt® and Velocity™. The DIR algorithms of SmartAdapt® and Velocity™ were commissioned and their deformation results were compared. Both systems can be used for clinical purpose. While there were only minimal differences between the two systems, Velocity™ provided lower values for parotids, bladder, rectum, and prostate (soft tissue) compared to SmartAdapt. However, for mandible, spinal cord, and femoral heads (rigid structures), both systems showed nearly identical results.

HGCMorph: joint discontinuity-preserving and pose-learning via GNN and capsule networks for deformable medical images registration

Objective. This study aims to enhance medical image registration by addressing the limitations of existing approaches that rely on spatial transformations through U-Net, ConvNets, or Transformers. The objective is to develop a novel architecture that combines ConvNets, graph neural networks (GNNs), and capsule networks to improve the accuracy and efficiency of medical image registration, which can also deal with the problem of rotating registration. Approach. We propose an deep learning-based approach which can be utilized in both unsupervised and semi-supervised manners, named as HGCMorph. It leverages a hybrid framework that integrates ConvNets and GNNs to capture lower-level features, specifically short-range attention, while also utilizing capsule networks (CapsNets) to model abstract higher-level features, including entity properties such as position, size, orientation, deformation, and texture. This hybrid framework aims to provide a comprehensive representation of anatomical structures and their spatial relationships in medical images. Main results. The results demonstrate the superiority of HGCMorph over existing state-of-the-art deep learning-based methods in both qualitative and quantitative evaluations. In unsupervised training process, our model outperforms the recent SOTA method TransMorph by achieving 7%/38% increase on Dice score coefficient (DSC), and 2%/7% improvement on negative jacobian determinant for OASIS and LPBA40 datasets, respectively. Furthermore, HGCMorph achieves improved registration accuracy in semi-supervised training process. In addition, when dealing with complex 3D rotations and secondary randomly deformations, our method still achieves the best performance. We also tested our methods on lung datasets, such as Japanese Society of Radiology, Montgoermy and Shenzhen. Significance. The significance lies in its innovative design to medical image registration. HGCMorph offers a novel framework that overcomes the limitations of existing methods by efficiently capturing both local and abstract features, leading to enhanced registration accuracy, discontinuity-preserving, and pose-learning abilities. The incorporation of capsule networks introduces valuable improvements, making the proposed method a valuable contribution to the field of medical image analysis. HGCMorph not only advances the SOTA methods but also has the potential to improve various medical applications that rely on accurate image registration.

A prior-information-based automatic segmentation method for the clinical target volume in adaptive radiotherapy of cervical cancer.

Adaptive planning to accommodate anatomic changes during treatment often requires repeated segmentation. In this study, prior patient-specific data was integrateda into a registration-guided multi-channel multi-path (Rg-MCMP) segmentation framework to improve the accuracy of repeated clinical target volume (CTV) segmentation. This study was based on CT image datasets for a total of 90 cervical cancer patients who received two courses of radiotherapy. A total of 15 patients were selected randomly as the test set. In the Rg-MCMP segmentation framework, the first-course CT images (CT1) were registered to second-course CT images (CT2) to yield aligned CT images (aCT1), and the CTV in the first course (CTV1) was propagated to yield aligned CTV contours (aCTV1). Then, aCT1, aCTV1, and CT2 were combined as the inputs for 3D U-Net consisting of a channel-based multi-path feature extraction network. The performance of the Rg-MCMP segmentation framework was evaluated and compared with the single-channel single-path model (SCSP), the standalone registration methods, and the registration-guided multi-channel single-path (Rg-MCSP) model. The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) were used as the metrics. The average DSC of CTV for the deformable image DIR-MCMP model was found to be 0.892, greater than that of the standalone DIR (0.856), SCSP (0.837), and DIR-MCSP (0.877), which were improvements of 4.2%, 6.6%, and 1.7%, respectively. Similarly, the rigid body DIR-MCMP model yielded an average DSC of 0.875, which exceeded standalone RB (0.787), SCSP (0.837), and registration-guided multi-channel single-path (0.848), which were improvements of 11.2%, 4.5%, and 3.2%, respectively. These improvements in DSC were statistically significant (p<0.05). The proposed Rg-MCMP framework achieved excellent accuracy in CTV segmentation as part of the adaptive radiotherapy workflow.

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.

Image Processing in L1-Norm-Based Discrete Cartesian and Polar Coordinates

This paper proposes a radial image processing method performed in an L1-norm-based discrete polar coordinate system. For this purpose, we address the problem that polar coordinates based on the L2-norm cannot exist in discrete systems and then develop a method for converting Cartesian coordinates to L1-norm-based discrete polar coordinates. The proposed method greatly reduces the directional variance occurring in the Cartesian coordinate system and so processes radial directional images along the directions of the local image signal flows. To verify the usages of the proposed method, it was applied to the stabilization of mass-type breast cancer images, a segmentation of extremely deformable objects such as biomedical objects. In all cases, the proposed method produced superior results compared to the processing in the Cartesian coordinate systems. The proposed method is useful for processing or analyzing diffusing and deformable images such as bio-cell and smoke images.

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.

Development of a vision-based tactile sensor with micro suction cups

Tactile sensors capable of measuring contact force distribution are being actively developed for complex manipulation by robotic hands. In recent years, vision-based tactile sensors that estimate contact conditions by observing elastomer deformation with a camera from the backside and analyzing the images have attracted much attention. In the general marker displacement method using a single camera, it is difficult to estimate the contact force in the normal direction with high resolution. By applying a microstructure array (micro suction cup array) to the surface of the elastomer that is in contact with the object, the micro suction cups are deformed by the contact force. A device was fabricated that can estimate the normal contact force to each suction cup from this deformation images using machine learning. The device can vacuum a micro suction cup array and capture its deformation from the backside. The micro suction cup array (2×2) was fabricated by transferring a master mold fabricated on a high-resolution optical fabrication 3D printer onto polydimethylsiloxane. It was shown that UV nanoimprinting with soft molds can be used to fabricate large-area micro suction cup arrays relatively easily. A regression CNN model was created to estimate the normal force applied to each suction cup from the deformation image. An average error between the measured and estimated value was 21 mN, which was sufficient for the accuracy of the estimation.

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.

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.

Computer multimedia aided design and hand-drawn effect analysis based on grid resource sharing cooperative algorithm

Hand-drawn is one of the few visual descriptors that can directly represent visual content, and has significant research in the area of computer vision. Aiming at the problem of sparse features in the realm of hand-drawn image retrieval, hand-drawn images, and the easy deformation of hand-drawn images, this paper proposes a feature extraction method of grid resource sharing collaborative algorithm, which can be obtained utilizing precisely extracted semantic characteristics from hand-drawn images through computer multimedia-aided design Efficient and accurate retrieval results. First, the fundamental framework for obtaining semantic features is algorithm; then the attention model mechanism is the grid resource sharing collaborative introduced in the process of supervised training, and the attention structure block is introduced after the convolutional neural network’s bottom layer. To locate effective semantic features, In order to accomplish high-precision retrieval, the attention structure block combines channel attention structure and spatial attention structure to build the attention structure block. The last feature descriptor is then created by combining various semantic feature levels. The proposed strategy is practical and efficient, as demonstrated by the experimental findings on the comparison database Flickr15k. In addition, in the task of hand-drawn image classification, the proposed attention mechanism greatly improves the classification accuracy.

Multi-centre evaluation of variation in cumulative dose assessment in reirradiation scenarios

Background and PurposeSafe reirradiation relies on assessment of cumulative doses to organs at risk (OARs) across multiple treatments. Different clinical pathways can result in inconsistent estimates. Here, we quantified the consistency of cumulative dose to OARs across multi-centre clinical pathways. Material and MethodsWe provided DICOM planning CT, structures and doses for two reirradiation cases: head & neck (HN) and lung. Participants followed their standard pathway to assess the cumulative physical and EQD2 doses (with provided α/β values), and submitted DVH metrics and a description of their pathways. Participants could also submit physical dose distributions from Course 1 mapped onto the CT of Course 2 using their best available tools. To assess isolated impact of image registrations, a single observer accumulated each submitted spatially mapped physical dose for every participating centre. ResultsCumulative dose assessment was performed by 24 participants. Pathways included rigid (n = 15), or deformable (n = 5) image registration-based 3D dose summation, visual inspection of isodose line contours (n = 1), or summation of dose metrics extracted from each course (n = 3). Largest variations were observed in near-maximum cumulative doses (25.4 – 41.8 Gy for HN, 2.4 – 33.8 Gy for lung OARs), with lower variations in volume/dose metrics to large organs. A standardised process involving spatial mapping of the first course dose to the second course CT followed by summation improved consistency for most near-maximum dose metrics in both cases. ConclusionLarge variations highlight the uncertainty in reporting cumulative doses in reirradiation scenarios, with implications for outcome analysis and understanding of published doses. Using a standardised workflow potentially including spatially mapped doses improves consistency in determination of accumulated dose in reirradiation scenarios.

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.

Recovery of the spatially-variant deformations in dual-panel PET reconstructions using deep-learning

Dual panel PET systems, such as Breast-PET (B-PET) scanner, exhibit strong asymmetric and anisotropic spatially-variant deformations in the reconstructed images due to the limited-angle data and strong depth of interaction effects for the oblique LORs inherent in such systems. In our previous work, we studied time-of-flight (TOF) effects and image-based spatially-variant PSF resolution models within dual-panel PET reconstruction to reduce these deformations. The application of PSF based models led to better and more uniform quantification of small lesions across the field of view (FOV). However, the ability of such a model to correct for PSF deformation is limited to small objects. On the other hand, large object deformations caused by the limited-angle reconstruction cannot be corrected with the PSF modeling alone. In this work, we investigate the ability of deep-learning (DL) networks to recover such strong spatially-variant image deformations using first simulated PSF deformations in image space of a generic dual panel PET system and then using simulated and acquired phantom reconstructions from dual panel B-PET system developed in our lab at University of Pennsylvania. For the studies using real B-PET data, the network was trained on the simulated synthetic data sets providing ground truth for objects resembling experimentally acquired phantoms on which the network deformation corrections were then tested. The synthetic and acquired limited-angle B-PET data were reconstructed using DIRECT-RAMLA reconstructions, which were then used as the network inputs. Our results demonstrate that DL approaches can significantly eliminate deformations of limited angle systems and improve their quantitative performance.

Research on image deformation monitoring algorithm based on binocular vision

Monitoring the deformation of critical structures such as tunnel、buildings and bridges is critical to ensure the safety of infrastructures. Non-contact deformation monitoring technology based on digital imagery has emerged as a prevalent and effective monitoring method, which enables cost-effective and efficient tracking of structural deformations. This paper aims to develop an automated deformation monitoring methodology using the binocular vision. First, standard preprocessing of digital images is performed through the integration of filtering algorithms and image enhancement techniques. Furthermore, by combining the Scale Invariant Feature Transform (SIFT) feature matching algorithm, the inverse compositional gauss–newton iterative algorithm, and interpolation methodologies, the planar displacement of the monitored targets can be calculated precisely, with sub-pixel precision being achieved. Subsequently, by adopting an enhanced Semi-Global Matching (SGM) algorithm, stereo matching of binocular images were accomplished. This process yields a disparity map, from which the depth map is computed. Then, precise measurement of the vertical displacement of the monitoring target can be obtained. This enables accurate measurement of three-dimensional displacements of the monitored targets. Finally, the developed methodology undergoes a comparative assessment against traditional measurement methods and existing algorithms to validate its measurement accuracy. The results prove that the deformation measurement technique based on binocular vision proposed in this paper captures structural deformation effectively. The accuracy surpasses that of existing measurement algorithms, and its efficiency outperforms traditional measurement methods.