Registration-derived estimates of local lung expansion as surrogates for regional ventilation

Direct estimation of regional lung volume change from paired and single CT images using residual regression neural network

BACKGROUND

Chest computed tomography (CT) enables characterization of pulmonary diseases by producing high-resolution and high-contrast images of the intricate lung structures. Deformable image registration is used to align chest CT scans at different lung volumes, yielding estimates of local tissue expansion and contraction.

PURPOSE

We investigated the utility of deep generative models for directly predicting local tissue volume change from lung CT images, bypassing computationally expensive iterative image registration and providing a method that can be utilized in scenarios where either one or two CT scans are available.

METHODS

A residual regression convolutional neural network, called Reg3DNet+, is proposed for directly regressing high-resolution images of local tissue volume change (i.e., Jacobian) from CT images. Image registration was performed between lung volumes at total lung capacity (TLC) and functional residual capacity (FRC) using a tissue mass- and structure-preserving registration algorithm. The Jacobian image was calculated from the registration-derived displacement field and used as the ground truth for local tissue volume change. Four separate Reg3DNet+ models were trained to predict Jacobian images using a multifactorial study design to compare the effects of network input (i.e., single image vs. paired images) and output space (i.e., FRC vs. TLC). The models were trained and evaluated on image datasets from the COPDGene study. Models were evaluated against the registration-derived Jacobian images using local, regional, and global evaluation metrics.

RESULTS

Statistical analysis revealed that both factors - network input and output space - were significant determinants for change in evaluation metrics. Paired-input models performed better than single-input models, and model performance was better in the output space of FRC rather than TLC. Mean structural similarity index for paired-input models was 0.959 and 0.956 for FRC and TLC output spaces, respectively, and for single-input models was 0.951 and 0.937. Global evaluation metrics demonstrated correlation between registration-derived Jacobian mean and predicted Jacobian mean: coefficient of determination (r2 ) for paired-input models was 0.974 and 0.938 for FRC and TLC output spaces, respectively, and for single-input models was 0.598 and 0.346. After correcting for effort, registration-derived lobar volume change was strongly correlated with the predicted lobar volume change: for paired-input models r2 was 0.899 for both FRC and TLC output spaces, and for single-input models r2 was 0.803 and 0.862, respectively.

CONCLUSIONS

Convolutional neural networks can be used to directly predict local tissue mechanics, eliminating the need for computationally expensive image registration. Networks that use paired CT images acquired at TLC and FRC allow for more accurate prediction of local tissue expansion compared to networks that use a single image. Networks that only require a single input image still show promising results, particularly after correcting for effort, and allow for local tissue expansion estimation in cases where multiple CT scans are not available. For single-input networks, the FRC image is more predictive of local tissue volume change compared to the TLC image.

deepPERFECT: Novel Deep Learning CT Synthesis Method for Expeditious Pancreatic Cancer Radiotherapy

Major sources of delay in the standard of care RT workflow are the need for multiple appointments and separate image acquisition. In this work, we addressed the question of how we can expedite the workflow by synthesizing planning CT from diagnostic CT. This idea is based on the theory that diagnostic CT can be used for RT planning, but in practice, due to the differences in patient setup and acquisition techniques, separate planning CT is required. We developed a generative deep learning model, deepPERFECT, that is trained to capture these differences and generate deformation vector fields to transform diagnostic CT into preliminary planning CT. We performed detailed analysis both from an image quality and a dosimetric point of view, and showed that deepPERFECT enabled the preliminary RT planning to be used for preliminary and early plan dosimetric assessment and evaluation.

Innovations in thoracic imaging: CT, radiomics, AI and x-ray velocimetry

In recent years, pulmonary imaging has seen enormous progress, with the introduction, validation and implementation of new hardware and software. There is a general trend from mere visual evaluation of radiological images to quantification of abnormalities and biomarkers, and assessment of ‘non visual’ markers that contribute to establishing diagnosis or prognosis. Important catalysts to these developments in thoracic imaging include new indications (like computed tomography [CT] lung cancer screening) and the COVID‐19 pandemic. This review focuses on developments in CT, radiomics, artificial intelligence (AI) and x‐ray velocimetry for imaging of the lungs. Recent developments in CT include the potential for ultra‐low‐dose CT imaging for lung nodules, and the advent of a new generation of CT systems based on photon‐counting detector technology. Radiomics has demonstrated potential towards predictive and prognostic tasks particularly in lung cancer, previously not achievable by visual inspection by radiologists, exploiting high dimensional patterns (mostly texture related) on medical imaging data. Deep learning technology has revolutionized the field of AI and as a result, performance of AI algorithms is approaching human performance for an increasing number of specific tasks. X‐ray velocimetry integrates x‐ray (fluoroscopic) imaging with unique image processing to produce quantitative four dimensional measurement of lung tissue motion, and accurate calculations of lung ventilation.

See relatedEditorial

Origins of and lessons from quantitative functional X-ray computed tomography of the lung

Functional CT of the lung has emerged from quantitative CT (qCT). Structural details extracted at multiple lung volumes offer indices of function. Additionally, single volumetric images, if acquired at standardized lung volumes and body posture, can be used to model function by employing such engineering techniques as computational fluid dynamics. With the emergence of multispectral CT imaging including dual energy from energy integrating CT scanners and multienergy binning using the newly released photon counting CT technology, function is tagged via use of contrast agents. Lung disease phenotypes have previously been lumped together by the limitations of spirometry and plethysmography. QCT and its functional embodiment have been imbedded into studies seeking to characterize chronic obstructive pulmonary disease, severe asthma, interstitial lung disease and more. Reductions in radiation dose by an order of magnitude or more have been achieved. At the same time, we have seen significant increases in spatial and density resolution along with methodologic validations of extracted metrics. Together, these have allowed attention to turn towards more mild forms of disease and younger populations. In early applications, clinical CT offered anatomic details of the lung. Functional CT offers regional measures of lung mechanics, the assessment of functional small airways disease, as well as regional ventilation-perfusion matching (V/Q) and more. This paper will focus on the use of quantitative/functional CT for the non-invasive exploration of dynamic three-dimensional functioning of the breathing lung and beating heart within the unique negative pressure intrathoracic environment of the closed chest.

Quantitative CT-based image registration metrics provide different ventilation and lung motion patterns in prone and supine positions in healthy subjects

Background

Previous studies suggested that the prone position (PP) improves oxygenation and reduces mortality among patients with acute respiratory distress syndrome (ARDS). However, the mechanism of this clinical benefit of PP is not completely understood. The aim of the present study was to quantitatively compare regional characteristics of lung functions in the PP with those in the supine position (SP) using inspiratory and expiratory computed tomography (CT) scans.

Methods

Ninety subjects with normal pulmonary function and inspiration and expiration CT images were included in the study. Thirty-four subjects were scanned in PP, and 56 subjects were scanned in SP. Non-rigid image registration-based inspiratory-expiratory image matching assessment was used for regional lung function analysis. Tissue fractions (TF) were computed based on the CT density and compared on a lobar basis. Three registration-derived functional variables, relative regional air volume change (RRAVC), volumetric expansion ratio (J), and three-dimensional relative regional displacement (s*) were used to evaluate regional ventilation and deformation characteristics.

Results

J was greater in PP than in SP in the right middle lobe (P = 0 .025), and RRAVC was increased in the upper and right middle lobes (P < 0.001). The ratio of the TF on inspiratory and expiratory scans, J, and RRAVC at the upper lobes to those at the middle and lower lobes and that ratio at the upper and middle lobes to those at the lower lobes of were all near unity in PP, and significantly higher than those in SP (0.98–1.06 vs 0.61–0.94, P < 0.001).

Conclusion

We visually and quantitatively observed that PP not only induced more uniform contributions of regional lung ventilation along the ventral-dorsal axis but also minimized the lobar differences of lung functions in comparison with SP. This may help in the clinician’s search for an understanding of the benefits of the application of PP to the patients with ARDS or other gravitationally dependent pathologic lung diseases.

Trial registration

Retrospectively registered.

Imaging the Injured Lung: Mechanisms of Action and Clinical Use

Acute respiratory distress syndrome (ARDS) consists of acute hypoxemic respiratory failure characterized by massive and heterogeneously distributed loss of lung aeration caused by diffuse inflammation and edema present in interstitial and alveolar spaces. It is defined by consensus criteria, which include diffuse infiltrates on chest imaging-either plain radiography or computed tomography. This review will summarize how imaging sciences can inform modern respiratory management of ARDS and continue to increase the understanding of the acutely injured lung. This review also describes newer imaging methodologies that are likely to inform future clinical decision-making and potentially improve outcome. For each imaging modality, this review systematically describes the underlying principles, technology involved, measurements obtained, insights gained by the technique, emerging approaches, limitations, and future developments. Finally, integrated approaches are considered whereby multimodal imaging may impact management of ARDS.

Imaging Advances in Chronic Obstructive Pulmonary Disease. Insights from the Genetic Epidemiology of Chronic Obstructive Pulmonary Disease (COPDGene) Study

The Genetic Epidemiology of Chronic Obstructive Pulmonary Disease (COPDGene) study, which began in 2007, is an ongoing multicenter observational cohort study of more than 10,000 current and former smokers. The study is aimed at understanding the etiology, progression, and heterogeneity of chronic obstructive pulmonary disease (COPD). In addition to genetic analysis, the participants have been extensively characterized by clinical questionnaires, spirometry, volumetric inspiratory and expiratory computed tomography, and longitudinal follow-up, including follow-up computed tomography at 5 years after enrollment. The purpose of this state-of-the-art review is to summarize the major advances in our understanding of COPD resulting from the imaging findings in the COPDGene study. Imaging features that are associated with adverse clinical outcomes include early interstitial lung abnormalities, visual presence and pattern of emphysema, the ratio of pulmonary artery to ascending aortic diameter, quantitative evaluation of emphysema, airway wall thickness, and expiratory gas trapping. COPD is characterized by the early involvement of the small conducting airways, and the addition of expiratory scans has enabled measurement of small airway disease. Computational advances have enabled indirect measurement of nonemphysematous gas trapping. These metrics have provided insights into the pathogenesis and prognosis of COPD and have aided early identification of disease. Important quantifiable extrapulmonary findings include coronary artery calcification, cardiac morphology, intrathoracic and extrathoracic fat, and osteoporosis. Current active research includes identification of novel quantitative measures for emphysema and airway disease, evaluation of dose reduction techniques, and use of deep learning for phenotyping COPD.

Influence of Inspiratory/Expiratory CT Registration on Quantitative Air Trapping

RATIONALE AND OBJECTIVES

The aim of this study was to assess variability in quantitative air trapping (QAT) measurements derived from spatially aligned expiration CT scans.

MATERIALS AND METHODS

Sixty-four paired CT examinations, from 16 school-age cystic fibrosis subjects examined at four separate time intervals, were used in this study. For each pair, visually inspected lobe segmentation maps were generated and expiration CT data were registered to the inspiration CT frame. Measurements of QAT, the percentage of voxels on the expiration CT scan below a set threshold were calculated for each lobe and whole-lung from the registered expiration CT and compared to the true values from the unregistered data.

RESULTS

A mathematical model, which simulates the effect of variable regions of lung deformation on QAT values calculated from aligned to those from unaligned data, showed the potential for large bias. Assessment of experimental QAT measurements using Bland-Altman plots corroborated the model simulations, demonstrating biases greater than 5% when QAT was approximately 40% of lung volume. These biases were removed when calculating QAT from aligned expiration CT data using the determinant of the Jacobian matrix. We found, by Dice coefficient analysis, good agreement between aligned expiration and inspiration segmentation maps for the whole-lung and all but one lobe (Dice coefficient > 0.9), with only the lingula generating a value below 0.9 (mean and standard deviation of 0.85 ± 0.06).

CONCLUSION

The subtle and predictable variability in corrected QAT observed in this study suggests that image registration is reliable in preserving the accuracy of the quantitative metrics.

Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration

We present a novel algorithm for the registration of pulmonary CT scans. Our method is designed for large respiratory motion by integrating sparse keypoint correspondences into a dense continuous optimization framework. The detection of keypoint correspondences enables robustness against large deformations by jointly optimizing over a large number of potential discrete displacements, whereas the dense continuous registration achieves subvoxel alignment with smooth transformations. Both steps are driven by the same normalized gradient fields data term. We employ curvature regularization and a volume change control mechanism to prevent foldings of the deformation grid and restrict the determinant of the Jacobian to physiologically meaningful values. Keypoint correspondences are integrated into the dense registration by a quadratic penalty with adaptively determined weight. Using a parallel matrix-free derivative calculation scheme, a runtime of about 5 min was realized on a standard PC. The proposed algorithm ranks first in the EMPIRE10 challenge on pulmonary image registration. Moreover, it achieves an average landmark distance of 0.82 mm on the DIR-Lab COPD database, thereby improving upon the state of the art in accuracy by 15%. Our algorithm is the first to reach the inter-observer variability in landmark annotation on this dataset.

Evaluation of the ΔV 4D CT ventilation calculation method using in vivo xenon CT ventilation data and comparison to other methods

Ventilation distribution calculation using 4D CT has shown promising potential in several clinical applications. This study evaluated the direct geometric ventilation calculation method, namely the ΔV method, with xenon-enhanced CT (XeCT) ventilation data from four sheep, and compared it with two other published meth-ods, the Jacobian and the Hounsfield unit (HU) methods. Spearman correlation coefficient (SCC) and Dice similarity coefficient (DSC) were used for the evaluation and comparison. The average SCC with one standard deviation was 0.44 ± 0.13 with a range between 0.29 and 0.61 between the XeCT and ΔV ventilation distributions. The average DSC value for lower 30% ventilation volumes between the XeCT and ΔV ventilation distributions was 0.55 ± 0.07 with a range between 0.48 and 0.63. Ventilation difference introduced by deformable image registration errors improved with smoothing. In conclusion, ventilation distributions generated using ΔV-4D CT and deformable image registration are in reasonably agreement with the in vivo XeCT measured ventilation distribution.

Dependence of ventilation image derived from 4D CT on deformable image registration and ventilation algorithms

Ventilation imaging using 4D CT is a convenient and low-cost functional imaging methodology which might be of value in radiotherapy treatment planning to spare functional lung volumes. Deformable image registration (DIR) is needed to calculate ventilation imaging from 4D CT. This study investigates the dependence of calculated ventilation on DIR methods and ventilation algorithms. DIR of the normal end expiration and normal end inspiration phases of the 4D CT images was used to correlate the voxels between the two respiratory phases. Three different DIR algorithms, optical flow (OF), diffeomorphic demons (DD), and diffeomorphic morphons (DM) were retrospectively applied to ten esophagus and ten lung cancer cases with 4D CT image sets that encompassed the entire lung volume. The three ventilation extraction methods were used based on either the Jacobian, the change in volume of the voxel, or directly calculated from Hounsfield units. The ventilation calculation algorithms used are the Jacobian, ΔV, and HU method. They were compared using the Dice similarity coefficient (DSC) index and Bland-Altman plots. Dependence of ventilation images on the DIR was greater for the ΔV and the Jacobian methods than for the HU method. The DSC index for 20% of low-ventilation volume for ΔV was 0.33 ± 0.03 (1 SD) between OF and DM, 0.44 ± 0.05 between OF and DD, and 0.51 ± 0.04 between DM and DD. The similarity comparisons for Jacobian were 0.32 ± 0.03, 0.44 ± 0.05, and 0.51 ± 0.04, respectively, and for HU they were 0.53 ± 0.03, 0.56 ± 0.03, and 0.76 ± 0.04, respectively. Dependence of extracted ventilation on the ventilation algorithm used showed good agreement between the ΔV and Jacobian methods, but differed significantly for the HU method. DSC index for using OF as DIR was 0.86 ± 0.01 between ΔV and Jacobian, 0.28 ± 0.04 between ΔV and HU, and 0.28 ± 0.04 between Jacobian and HU, respectively. When using DM or DD as DIR, similar values were obtained when comparing the different ventilation calculation methods. The similarity values for the 20% high-ventilation volume were close to those found for the 20% low-ventilation volume. The results obtained with DSC index were confirmed when using the Bland-Altman plots for comparing the ventilation images. Our data suggest that ventilation calculated from 4D CT depends on the DIR algorithm employed. Similarities between ΔV and Jacobian are higher than between ΔV and HU, and Jacobian and HU.

Multiscale imaging and registration-driven model for pulmonary acinar mechanics in the mouse

A registration-based multiscale method to obtain a deforming geometric model of mouse acinus is presented. An intact mouse lung was fixed by means of vascular perfusion at a hydrostatic inflation pressure of 20 cmH(2)O. Microcomputed tomography (μCT) scans were obtained at multiple resolutions. Substructural morphometric analysis of a complete acinus was performed by computing a surface-to-volume (S/V) ratio directly from the 3D reconstruction of the acinar geometry. A geometric similarity is observed to exist in the acinus where S/V is approximately preserved anywhere in the model. Using multiscale registration, the shape of the acinus at an elevated inflation pressure of 25 cmH(2)O is estimated. Changes in the alveolar geometry suggest that the deformation within the acinus is not isotropic. In particular, the expansion of the acinus (from 20 to 25 cmH(2)O) is accompanied by an increase in both surface area and volume in such a way that the S/V ratio is not significantly altered. The developed method forms a useful tool in registration-driven fluid and solid mechanics studies as displacement of the alveolar wall becomes available in a discrete sense.

Validation of three deformable image registration algorithms for the thorax

Deformable image registration (DIR) has been proposed for lung ventilation calculation using 4D CT. Spatial accuracy of DIR can be evaluated using expert landmark correspondences. Additionally, image differences between the deformed and the target images give a degree of accuracy of DIR algorithms for the same image modality registration. DIR of the normal end-expiration (50%), end-inspiration (0%), midexpiration (30%), and midinspiration image (70%) phases of the 4D CT images was used to correlate the voxels between the respiratory phases. Three DIR algorithms, optical flow (OF), diffeomorphic morphons (DM), and diffeomorphic demons (DD) were validated using a 4D thorax model, consisting of a 4D CT image dataset, along with associated landmarks delineated by a radiologist. Image differences between the deformed and the target images were used to evaluate the degree of registration accuracy of the three DIR algorithms. In the validation of the DIR algorithms, the average target registration error (TRE) for normal end-expiration-to-end-inspiration registration with one standard deviation (SD) for the DIR algorithms was 1.6 ± 0.9 mm (maximum 3.1 mm) for OF, 1.4 ± 0.6 mm (maximum 3.3 mm) for DM, and 1.4 ± 0.7 mm (maximum 3.3 mm) for DD, indicating registration errors were within two voxels. As a reference, the median value of TRE between 0 and 50% phases with rigid registration only was 5.0 mm with one SD of 2.5 mm and the maximum value of 12.0 mm. For the OF algorithm, 81% of voxels were within a difference of 50 HU, and 93% of the voxels were within 100 HU. For the DM algorithm, 69% of voxels were within 50 HU, and 87% within 100 HU. For the DD algorithm, 71% of the voxels were within 50 HU, and 87% within a difference of 100 HU. These data suggest that the three DIR methods perform accurate registrations in the thorax region. The mean TRE for all three DIR methods was less than two voxels suggesting that the registration performed by all methods are equally accurate in the thorax.

Three-dimensional characterization of regional lung deformation

The deformation of the lung during inspiration and expiration involves regional variations in volume change and orientational preferences. Studies have reported techniques for measuring the displacement field in the lung based on imaging or image registration. However, means of interpreting all the information in the displacement field in a physiologically relevant manner is lacking. We propose three indices of lung deformation that are determinable from the displacement field: the Jacobian--a measure of volume change, the anisotropic deformation index--a measure of the magnitude of directional preference in volume change and a slab-rod index--a measure of the nature of directional preference in volume change. To demonstrate the utility of these indices, they were determined for six human subjects using deformable image registration on static CT images, registered from FRC to TLC. Volume change was elevated in the inferior-dorsal region as should be expected for breathing in the supine position. The anisotropic deformation index was elevated in the inferior region owing to proximity to the diaphragm and in the lobar fissures owing to sliding. Vessel regions in the lung had a significantly rod-like deformation compared to the whole lung. Compared to upper lobes, lower lobes exhibited significantly greater volume change (19.4% and 21.3% greater in the right and left lungs on average; p<0.005) and anisotropy in deformation (26.3% and 21.8% greater in the right and left lungs on average; p<0.05) with remarkable consistency across subjects. The developed deformation indices lend themselves to exhaustive and physiologically intuitive interpretations of the displacement fields in the lung determined through image-registration techniques or finite element simulations.

Multi-scale optical flow including normalized mutual information for planar deformable lung motion estimation from 4D CT

A novel energy function for computing planar optical flow from X-ray CT images was presented and reported in detail in [1]. The technique combines four terms: brightness constancy, gradient constancy, continuity equation based on mass conservation, and discontinuity-preserving spatio-temporal smoothness. Both qualitative and quantitative evaluation of the proposed method demonstrated that the method results in significantly better angular errors than previous well-known techniques for optical flow estimation. A multi-scale approach to motion field computation based on this framework is presented in this paper. The proposed approach significantly speeds up the calculations, realizing computational savings. Additionally, an approach to determination of optimum values of scalar weights in the energy function is herein proposed. Normalized mutual information measured between the first image warped with the estimated motion and the second image is used to determine the optimum value for weighting parameters.

Estimation of motion fields by non-linear registration for local lung motion analysis in 4D CT image data

PURPOSE

Motivated by radiotherapy of lung cancer non- linear registration is applied to estimate 3D motion fields for local lung motion analysis in thoracic 4D CT images. Reliability of analysis results depends on the registration accuracy. Therefore, our study consists of two parts: optimization and evaluation of a non-linear registration scheme for motion field estimation, followed by a registration-based analysis of lung motion patterns.

METHODS

The study is based on 4D CT data of 17 patients. Different distance measures and force terms for thoracic CT registration are implemented and compared: sum of squared differences versus a force term related to Thirion's demons registration; masked versus unmasked force computation. The most accurate approach is applied to local lung motion analysis.

RESULTS

Masked Thirion forces outperform the other force terms. The mean target registration error is 1.3 ± 0.2 mm, which is in the order of voxel size. Based on resulting motion fields and inter-patient normalization of inner lung coordinates and breathing depths a non-linear dependency between inner lung position and corresponding strength of motion is identified. The dependency is observed for all patients without or with only small tumors.

CONCLUSIONS

Quantitative evaluation of the estimated motion fields indicates high spatial registration accuracy. It allows for reliable registration-based local lung motion analysis. The large amount of information encoded in the motion fields makes it possible to draw detailed conclusions, e.g., to identify the dependency of inner lung localization and motion. Our examinations illustrate the potential of registration-based motion analysis.

Measurement of regional specific lung volume change using respiratory-gated PET of inhaled 13N-nitrogen

Regional specific lung volume change (sVol), defined as the regional tidal volume divided by the regional end-expiratory gas volume, is a key variable in lung mechanics and in the pathogenesis of ventilator-induced lung injury. Despite the usefulness of PET to study regional lung function, there is no established method to assess sVol with PET. We present a method to measure sVol from respiratory-gated PET images of inhaled (13)N-nitrogen ((13)NN), validate the method against regional specific ventilation (sV), and study the effect of region-of-interest (ROI) volume and orientation on the sVol-sV relationship.

METHODS

Four supine sheep were mechanically ventilated (tidal volume V(T) = 8 mL/kg, respiratory rate adjusted to normocapnia) at low (n = 2, positive end-expiratory pressure = 0) and high (n = 2, positive end-expiratory pressure adjusted to achieve a plateau pressure of 30 cm H(2)O) lung volumes. Respiratory-gated PET scans were obtained after inhaled (13)NN equilibration both at baseline and after a period of mechanical ventilation. We calculated sVol from (13)NN-derived regional fractional gas content at end-inspiration (F(EI)) and end-expiration (F(EE)) using the formula sVol = (F(EI) - F(EE))/(F(EE)[1 - F(EI)]). sV was computed as the inverse of the subsequent (13)NN washout curve time constant. ROIs were defined by dividing the lung field with equally spaced coronal, sagittal, and transverse planes, perpendicular to the ventrodorsal, laterolateral, and cephalocaudal axes, respectively.

RESULTS

sVol-sV linear regressions for ROIs based on the ventrodorsal axis yielded the highest R(2) (range, 0.71-0.92 for mean ROI volumes from 7 to 162 mL), the cephalocaudal axis the next highest (R(2) = 0.77-0.88 for mean ROI volumes from 38 to 162 mL), and the laterolateral axis the lowest (R(2) = 0.65-0.83 for mean ROI volumes from 8 to 162 mL). ROIs based on the ventrodorsal axis yielded lower standard errors of estimates of sVol from sV than those based on the laterolateral axis or the cephalocaudal axis.

CONCLUSION

sVol can be computed with PET using the proposed method and is highly correlated with sV. Errors in sVol are smaller for larger ROIs and for orientations based on the ventrodorsal axis.

Shape-correlated Deformation Statistics for Respiratory Motion Prediction in 4D Lung

4D image-guided radiation therapy (IGRT) for free-breathing lungs is challenging due to the complicated respiratory dynamics. Effective modeling of respiratory motion is crucial to account for the motion affects on the dose to tumors. We propose a shape-correlated statistical model on dense image deformations for patient-specic respiratory motion estimation in 4D lung IGRT. Using the shape deformations of the high-contrast lungs as the surrogate, the statistical model trained from the planning CTs can be used to predict the image deformation during delivery verication time, with the assumption that the respiratory motion at both times are similar for the same patient. Dense image deformation fields obtained by diffeomorphic image registrations characterize the respiratory motion within one breathing cycle. A point-based particle optimization algorithm is used to obtain the shape models of lungs with group-wise surface correspondences. Canonical correlation analysis (CCA) is adopted in training to maximize the linear correlation between the shape variations of the lungs and the corresponding dense image deformations. Both intra- and inter-session CT studies are carried out on a small group of lung cancer patients and evaluated in terms of the tumor location accuracies. The results suggest potential applications using the proposed method.

A SHAPE-NAVIGATED IMAGE DEFORMATION MODEL FOR 4D LUNG RESPIRATORY MOTION ESTIMATION

Intensity modulated radiation therapy (IMRT) for cancers in the lung remains challenging due to the complicated respiratory dynamics. We propose a shape-navigated dense image deformation model to estimate the patient-specific breathing motion using 4D respiratory correlated CT (RCCT) images. The idea is to use the shape change of the lungs, the major motion feature in the thorax image, as a surrogate to predict the corresponding dense image deformation from training.To build the statistical model, dense diffeomorphic deformations between images of all other time points to the image at end expiration are calculated, and the shapes of the lungs are automatically extracted. By correlating the shape variation with the temporally corresponding image deformation variation, a linear mapping function that maps a shape change to its corresponding image deformation is calculated from the training sample. Finally, given an extracted shape from the image at an arbitrary time point, its dense image deformation can be predicted from the pre-computed statistics.The method is carried out on two patients and evaluated in terms of the tumor and lung estimation accuracies. The result shows robustness of the model and suggests its potential for 4D lung radiation treatment planning.

Registration-based estimates of local lung tissue expansion compared to xenon CT measures of specific ventilation

The main function of the respiratory system is gas exchange. Since many disease or injury conditions can cause biomechanical or material property changes that can alter lung function, there is a great interest in measuring regional lung ventilation and regional specific volume change. We describe a registration-based technique for estimating local lung expansion from multiple respiratory-gated CT images of the thorax. The degree of regional lung expansion is measured using the Jacobian (a function of local partial derivatives) of the registration displacement field, which we show is directly related to specific volume change. We compare the ventral-dorsal patterns of lung expansion estimated across five pressure changes to a xenon CT based measure of specific ventilation in five anesthetized sheep studied in the supine orientation. Using 3D image registration to match images acquired at 10 cm H(2)O and 15 cm H(2)O airway pressures gave the best match between the average Jacobian and the xenon CT specific ventilation (linear regression, average r(2)=0.73).