Intensity-based Registration Algorithm Research Articles

The Effect of Low-Dose CT Protocols on Shoulder Model-Based Tracking accuracy Using Biplane Videoradiography.

Model-based tracking is being increasingly used to quantify shoulder kinematics and typically employs computed tomography (CT) to create the 3D bone volumes, which adds to the total radiation exposure. Lower-dose CT protocols may be possible given the contrast between bone and the surrounding soft tissues. The purpose of this study was to describe the dose-accuracy tradeoff between low-dose CT scans and the kinematic tracking accuracy of the humerus, scapula, and clavicle when tracked using an intensity-based registration algorithm. Three fresh-frozen cadavers consisting of the torso and bilateral shoulders were tested. The CT protocols investigated included a full-dose protocol and 4 experimental low-dose protocols that modulated x-raytube current and peak voltage. Bead-based tracking (i.e., radiostereometric analysis) served as the reference standard to which model-based tracking results were compared. Accuracy was described in terms of both segmental (humerus, scapula, and clavicle) and joint (glenohumeral, acromioclavicular) kinematics using root-mean-square (RMSE), bias, precision, and worst-case errors. The low-dose CT scans resulted in an average dose reduction of 70.6-92.8%. RMSEs tended to increase as CT dose decreased with average glenohumeral errors increasing from 0.5° and 0.6 mm to 0.6° and 0.6 mm between the highest and lowest-dose protocols, and average acromioclavicular errors increasing from 0.6° and 0.8 mm to 0.7° and 0.9 mm. However, the difference in joint kinematic errors between the highest and lowest-dose CT scanning protocols was generally small (≤0.3°, ≤ 0.1 mm). It is possible to substantially reduce the CT dose associated with shoulder motion analysis using biplane videoradiography without significantly impacting data fidelity.

Unsupervised deep learning enables real-time image registration of fast-scanning optical-resolution photoacoustic microscopy

A fast scanner of optical-resolution photoacoustic microscopy is inherently vulnerable to perturbation, leading to severe image distortion and significant misalignment among multiple 2D or 3D images. Restoration and registration of these images is critical for accurately quantifying dynamic information in long-term imaging. However, traditional registration algorithms face a great challenge in computational throughput. Here, we develop an unsupervised deep learning based registration network to achieve real-time image restoration and registration. This method can correct artifacts from B-scan distortion and remove misalignment among adjacent and repetitive images in real time. Compared with conventional intensity based registration algorithms, the throughput of the developed algorithm is improved by 50 times. After training, the new deep learning method performs better than conventional feature based image registration algorithms. The results show that the proposed method can accurately restore and register the images of fast-scanning photoacoustic microscopy in real time, offering a powerful tool to extract dynamic vascular structural and functional information.

InTEn-LOAM: Intensity and Temporal Enhanced LiDAR Odometry and Mapping

Traditional LiDAR odometry (LO) systems mainly leverage geometric information obtained from the traversed surroundings to register lazer scans and estimate LiDAR ego-motion, while they may be unreliable in dynamic or degraded environments. This paper proposes InTEn-LOAM, a low-drift and robust LiDAR odometry and mapping method that fully exploits implicit information of lazer sweeps (i.e., geometric, intensity and temporal characteristics). The specific content of this work includes method innovation and experimental verification. With respect to method innovation, we propose the cylindrical-image-based feature extraction scheme, which makes use of the characteristic of uniform spatial distribution of lazer points to boost the adaptive extraction of various types of features, i.e., ground, beam, facade and reflector. We propose a novel intensity-based point registration algorithm and incorporate it into the LiDAR odometry, enabling the LO system to jointly estimate the LiDAR ego-motion using both geometric and intensity feature points. To eliminate the interference of dynamic objects, we propose a temporal-based dynamic object removal approach to filter them out in the resulting points map. Moreover, the local map is organized and downsampled using a temporal-related voxel grid filter to maintain the similarity between the current scan and the static local map. With respect to experimental verification, extensive tests are conducted on both simulated and real-world datasets. The results show that the proposed method achieves similar or better accuracy with respect to the state-of-the-art in normal driving scenarios and outperforms geometric-based LO in unstructured environments.

Estimating the accumulative dose uncertainty for intracavitary and interstitial brachytherapy

BackgroundImage-guided adaptive brachytherapy shows the ability to deliver high doses to tumors while sparing normal tissues. However, interfraction dose delivery introduces uncertainties to high dose estimation, which relates to normal tissue toxicity. The purpose of this study was to investigate the high-dose regions of two applicator approaches in brachytherapy.MethodFor 32 cervical cancer patients, the CT images from each fraction were wrapped to a reference image, and the displacement vector field (DVF) was calculated with a hybrid intensity-based deformable registration algorithm. The fractional dose was then accumulated to calculate the position and the overlap of high dose (D2cc) during multiple fractions.ResultThe overall Dice similarity coefficient (DSC) of the deformation algorithm for the bladder and the rectum was (0.97 and 0.91). No significant difference was observed between the two applicators. However, the location of the intracavitary brachytherapy (ICBT) high-dose region was relatively concentrated. The overlap volume of bladder and rectum D2cc was 0.42 and 0.71, respectively, which was higher than that of interstitial brachytherapy (ISBT) (0.26 and 0.31). The cumulative dose was overestimated in ISBT cases when using the GEC-recommended method. The ratio of bladder and rectum D2cc to the GEC method was 0.99 and 1, respectively, which was higher than that of the ISBT method (0.96 and 0.94).ConclusionHigh-dose regions for brachytherapy based on different applicator types were different. The 3D-printed ICBT has better high-dose region consistency than freehand ISBT and hence is more predictable.

Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dose radiation treatment of pancreatic cancer.

Accurate deformable registration between computed tomography (CT) and cone-beam CT (CBCT) images of pancreatic cancer patients treated with high biologically effective radiation doses is essential to assess changes in organ-at-risk (OAR) locations and shapes and to compute delivered dose. This study describes the development and evaluation of a deep-learning (DL) registration model to predict OAR segmentations on the CBCT derived from segmentations on the planning CT. The DL model is trained with CT-CBCT image pairs of the same patient, on which OAR segmentations of the small bowel, stomach, and duodenum have been manually drawn. A transformation map is obtained, which serves to warp the CT image and segmentations. In addition to a regularity loss and an image similarity loss, an OAR segmentation similarity loss is also used during training, which penalizes the mismatch between warped CT segmentations and manually drawn CBCT segmentations. At test time, CBCT segmentations are not required as they are instead obtained from the warped CT segmentations. In an IRB-approved retrospective study, a dataset consisting of 40 patients, each with one planning CT and two CBCT scans, was used in a fivefold cross-validation to train and evaluate the model, using physician-drawn segmentations as reference. Images were preprocessed to remove gas pockets. Network performance was compared to two intensity-based deformable registration algorithms (large deformation diffeomorphic metric mapping [LDDMM] and multimodality free-form [MMFF]) as baseline. Evaluated metrics were Dice similarity coefficient (DSC), change in OAR volume within a volume of interest (enclosing the low-dose PTV plus 1cm margin) from planning CT to CBCT, and maximum dose to 5 cm3 of the OAR [D(5cc)]. Processing time for one CT-CBCT registration with the DL model at test time was less than 5seconds on a GPU-based system, compared to an average of 30minutes for LDDMM optimization. For both small bowel and stomach/duodenum, the DL model yielded larger median DSC and smaller interquartile variation than either MMFF (paired t-test P<10-4 for both type of OARs) or LDDMM (P<10-3 and P=0.03 respectively). Root-mean-square deviation (RMSD) of DL-predicted change in small bowel volume relative to reference was 22% less than for MMFF (P=0.007). RMSD of DL-predicted stomach/duodenum volume change was 28% less than for LDDMM (P=0.0001). RMSD of DL-predicted D(5cc) in small bowel was 39% less than for MMFF (P=0.001); in stomach/duodenum, RMSD of DL-predicted D(5cc) was 18% less than for LDDMM (P<10-3 ). The proposed deep network CT-to-CBCT deformable registration model shows improved segmentation accuracy compared to intensity-based algorithms and achieves an order-of-magnitude reduction in processing time.

HeadLocNet: Deep convolutional neural networks for accurate classification and multi-landmark localization of head CTs.

Cochlear implants (CIs) are used to treat subjects with hearing loss. In a CI surgery, an electrode array is inserted into the cochlea to stimulate auditory nerves. After surgery, CIs need to be programmed. Studies have shown that the cochlea-electrode spatial relationship derived from medical images can guide CI programming and lead to significant improvement in hearing outcomes. We have developed a series of algorithms to segment the inner ear anatomy and localize the electrodes. But, because clinical head CT images are acquired with different protocols, the field of view and orientation of the image volumes vary greatly. As a consequence, visual inspection and manual image registration to an atlas image are needed to document their content and to initialize intensity-based registration algorithms used in our processing pipeline. For large-scale evaluation and deployment of our methods these steps need to be automated. In this article we propose to achieve this with a deep convolutional neural network (CNN) that can be trained end-to-end to classify a head CT image in terms of its content and to localize landmarks. The detected landmarks can then be used to estimate a point-based registration with the atlas image in which the same landmark set's positions are known. We achieve 99.5% classification accuracy and an average localization error of 3.45 mm for 7 landmarks located around each inner ear. This is better than what was achieved with earlier methods we have proposed for the same tasks.

Registration with probabilistic correspondences — Accurate and robust registration for pathological and inhomogeneous medical data

The registration of two medical images is usually based on the assumption that corresponding regions exist in both images. If this assumption is violated by e.g. pathologies most approaches encounter problems. The registration approach proposed is based on probabilistic correspondences of sparse image representations and enables a robust handling of potentially missing correspondences. A maximum a-posteriori framework is used to derive an optimization criterion with respect to deformation parameters that aim to reduce the shape and appearance differences between the registered images. A multi-resolution approach speeds up the optimization and increases the robustness of the registration. The computed probabilistic correspondences enable the approach to deal with missing correspondences in the images. Furthermore, they provide additional information about the quality of fit and potentially non-corresponding/pathological image regions. The approach is compared to two state-of-the-art registration methods using MR brain and cardiac images: a variational intensity-based registration algorithm and a feature-based registration approach using a discrete optimization scheme. The comprehensive quantitative evaluation using additional simulated stroke lesions shows a significantly higher accuracy and robustness of the proposed approach. Furthermore, the correspondence probability maps were used to characterize pathological regions in the MRI brain data.

Motion correction of chemical exchange saturation transfer MRI series using robust principal component analysis (RPCA) and PCA.

Chemical exchange saturation transfer (CEST) MRI requires the acquisition of multiple saturation-weighted images and can last several minutes. Misalignments among these images, which are often due to the inevitable motion of the subject, will corrupt CEST contrast maps and result in large quantification errors. Therefore, the registration of the CEST series is critical. However, registration is challenging since common intensity-based registration algorithms may fail to differentiate CEST signals from motion artifacts. Herein, we studied how different patterns of motion affect CEST quantification and proposed a cascaded two-step registration scheme by utilizing features extracted from the entire Z-spectral image series instead of direct registration to a single image. The proposed approach is conducted in two stages: during the first coarse registration, the Z-spectral image series is decomposed by robust principal component analysis (RPCA) to separate CEST contrast from motion. The recomposed image series using only the low-rank component, which contains minimized motion, are averaged to generate a reference for the alignment of the image series. To further remove residual misalignments, the coarse registration is followed by a refinement stage, which uses PCA iteratively to generate motionless synthetic reference series with the first few principal components (PCs) that correspond to CEST contrast. In the end, the quality check is performed to exclude the images with unsuccessful registration. The proposed registration scheme (RPCA + PCA_R) was assessed by both phantom experiments and in vivo data of tumor-bearing mouse brain, with simulated random rigid motion in different patterns applied to the acquired static Z-spectral image series. For comparison, previous correction schemes using an explicit image [either S0 or Ssat(∆ω)] as registration reference were also performed, named as S0_R and Ssat_R respectively. To illustrate the advantage of combination of RPCA and PCA, registration was also exploited using either only the RPCA-based method (RPCA_R) or only the PCA-based one (PCA_R). Compared with the above four methods, RPCA + PCA_R allowed for more accurate correction of the corrupted Z-spectral images, exhibiting smaller MTRasym(∆ω) error maps and lower residual Z-spectra referring to the static data. Among all the five correction methods, the corrected Z-spectral image series by RPCA + PCA_R and the resulting MTRasym(∆ω) maps achieved the highest correlation coefficients (CC) with respect to the static ones. The registration scheme of RPCA + PCA_R provides robust motion correction between two specific Z-spectral images and among an entire image series, through extraction of the static component from the entire Z-spectra set and inclusion of a PCA-based refinement step. Therefore, this method can help improve CEST acquisition and quantification.

Evaluating Utility of 4D PET-CT Motion Freeze Imaging for Lung SABR

In Lung stereotactic ablative radiotherapy (SABR), 4D PET-CT gives an edge over static 3D PET-CT in target volume delineation given its ability to reduce motion artifacts. Motion Freeze (MF) PET imaging combines the quantitative benefits of 100% counts of 4D phase-matched PET-CT imaging into a single static image by collecting CT & PET data at each phase of the breathing cycle, then matching the data for attenuation consistency. This provides further robustness of biologic target volume delineation with reduced image noise. The authors evaluated the utility of 4D PET-CT MF imaging in lung SABR treatments & the consequent dosimetric impact when either motion inclusive (retrospective imaging) technique or gating technique were to be used. Five patients of lung SABR were included for purpose of this dosimetric study (1 Ca lung and 4 lung oligo-metastasis). All patients underwent 4D CT /PET scan with the RPM system on 16 slice PET-CT scanner. The 4D CT and 4D PET data were binned in 10 phases of respiratory cycle. The Motion match software was utilized to create a MF image of all the 10 PET bins (MF-10) and 3 bins corresponding to end expiratory phase 40%,50%,60% (MF-3) in which tumor position was relatively stable. For study purpose we analyzed 3 clinical scenarios for target delineation (a) target volume generated using 4D CT alone (b) 4D CT all bins deformably registered with MF-10 (c) 4D-CT 3 bins deformably registered with corresponding MF-3, using gradient based intensity based registration algorithm. Three VMAT 6 MV FFF plans were generated for all the above all 3 volumes. The dosimetric parameters analysed included Target volume coverage, dose spillage (high, intermediate and low dose) & OAR doses as per RTOG protocol. Statistical comparison was done using paired sample t test in statistical analysis software. The target volume was reduced using 4D PET MF 10 & MF 3 as compared to 4D CT alone though the values were statistically insignificant [P=0.75(MF10), P=0.68 (MF3)]. There was statistically insignificant difference in target volume coverage parameters i.e. Conformity index, Heterogeneity index, dose spillage (high, intermediate and low dose) among all the plans. However the trend towards reduced OAR doses was seen in MF 10 plan & MF 3 plan as compared to 4D CT plan {Lungs V20 [P=0.06(MF10), P=0.08(MF3)], Heart Dmax [P=0.02(MF10), P=0.03(MF3)], Spinal cord Dmax [P=0.08(MF10), P=0.07(MF3)], Chest wall Dmax [P=0.001(MF10), P=0.037(MF3)], Great Vessel Dmax [P=0.03(MF10), P=0.045 (MF3)]}. Inclusion of 4D PET-CT MF scan 10 bins (non gated delivery) or 3 bins (gated delivery) can improvise the robustness of Lung SABR in terms of better target volume delineation, OAR doses & estimation of SUV values helping in better treatment response evaluation in follow up. While this study, first of its kind for Lung SABR, gives proof-of-concept & integration into workflow, a larger sample size evaluating 4D PET-CT MF would address the target delineation issue.

Intra-Fraction Motion Analysis for Frameless Linac-Based Stereotactic Radiosurgery with Three-Dimension (3D) Optical Surface Imaging for Intra-Fractional Motion Management

There has been a rapid increase in the use of frameless SRS in place of the frame-based SRS for treatment of brain metastases (BM). Compared to the frame-based SRS, intra-fraction motion management is a major challenge for the frameless SRS. With advanced immobilization and patient monitoring technologies, intra-fraction motion can be reduced. The purpose of this study is to analyze intra-fraction motion with LINAC-based SRS using a frameless radiosurgery platform that uses an integrated 3D optical surface monitoring system for intra-fraction motion management. This retrospective study includes 97 LINAC-SRS treatments delivered to 60 patients of BM with an integrated 3D surface imaging software for intra-fraction monitoring. Every treatment was delivered with a 6MV FFF beam at a dose-rate of 1400MU/min. Each treatment had at least 3 non-coplanar arcs with a minimum of 3 couch rotations. The patients were immobilized using an open-faced rigid SRS-thermoplastic mask with an opening encompassing the eyes, nose, and part of their forehead. Each patient was first aligned using a high-quality cone-beam CT (CBCT) with 1mm slice thickness and positioned using a 6 degrees of freedom couch. The patient’s face was monitored during treatment delivery through the surface monitoring system. During delivery, beam holds occurred if patient motion exceeded pre-defined tolerance (1mm translation/1° rotation) for > 5 seconds. An additional CBCT was performed following the delivering of two arcs to assess for any intra-fraction motion. Each CBCT was then registered to the planning CT using the automated intensity-based registration algorithm, followed by confirmation with a manual check. The intra-fraction shifts (RL, AP, and SI) and rotation (yaw, roll, and pitch) data were retrospectively recorded and analyzed. The total magnitude of the patient intra-fraction motion for all ninety-seven SRS treatments as recorded through shifts were 0.4 mm (mean) ± 0.3 mm (stv). Translational shifts were 0.0±0.3 mm in RL, 0.0±0.3 mm in AP, 0.0±0.3 mm in SI, while the rotational variations were 0.0±0.4° in yaw, 0.0±0.2° in roll, and 0.0±0.2° in pitch. In total, 93.8%(n=91/97) delivered treatments had intra-fraction motion that was ≤1mm and ≤1 degree. Minimal intra-fraction motion was observed during frameless-based LINAC-SRS treatments when using an integrated 3D surface image tracking; Only 6% percent of treatments experienced motion that was >1mm or >1 degree. A planning target margin of ≤1 mm may be considered adequate during the planning process to account for intra-fraction motion in the majority of all cases.

A comparative analysis of intensity-based 2D-3D registration for intraoperative use in pedicle screw insertion surgeries.

Although multiple algorithms have been reported that focus on improving the accuracy of 2D-3D registration techniques, there has been relatively little attention paid to quantifying their capture range. In this paper, we analyze the capture range for a number of variant formulations of the 2D-3D registration problem in the context of pedicle screw insertion surgery. We tested twelve 2D-3D registration techniques for capture range under different clinically realistic conditions. A registration was considered as successful if its error was less than 2mm and 2° in 95% of the cases. We assessed the sensitivity of capture range to a variety of clinically realistic parameters including: X-ray contrast, number and configuration of X-rays, presence or absence of implants in the image, inter-subject variability, intervertebral motion and single-level vs multi-level registration. Gradient correlation + Powell optimizer had the widest capture range and the least sensitivity to X-ray contrast. The combination of 4 AP + lateral X-rays had the widest capture range (725mm2). The presence of implant projections significantly reduced the registration capture range (up to 84%). Different spine shapes resulted in minor variations in registration capture range (SD 78mm2). Intervertebral angulations of less than 1.5° had modest effects on the capture range. This paper assessed capture range of a number of variants of intensity-based 2D-3D registration algorithms in clinically realistic situations (for the use in pedicle screw insertion surgery). We conclude that a registration approach based on the gradient correlation similarity and the Powell's optimization algorithm, using a minimum of two C-arm images, is likely sufficiently robust for the proposed application.

Breast MRI and X-ray mammography registration using gradient values.

Breast magnetic resonance imaging (MRI) and X-ray mammography are two image modalities widely used for early detection and diagnosis of breast diseases in women. The combination of these modalities, traditionally done using intensity-based registration algorithms, leads to a more accurate diagnosis and treatment, due to the capability of co-localizing lesions and susceptibles areas between the two image modalities. In this work, we present the first attempt to register breast MRI and X-ray mammographic images using intensity gradients as the similarity measure. Specifically, a patient-specific biomechanical model of the breast, extracted from the MRI image, is used to mimic the mammographic acquisition. The intensity gradients of the glandular tissue are directly projected from the 3D MRI volume to the 2D mammographic space, and two different gradient-based metrics are tested to lead the registration, the normalized cross-correlation of the scalar gradient values and the gradient correlation of the vectoral gradients. We compare these two approaches to an intensity-based algorithm, where the MRI volume is transformed to a synthetic computed tomography (pseudo-CT) image using the partial volume effect obtained by the glandular tissue segmentation performed by means of an Expectation-Maximization algorithm. This allows us to obtain the digitally reconstructed radiographies by a direct intensity projection. The best results are obtained using the scalar gradient approach along with a transversal isotropic material model, obtaining a target registration error (TRE), in millimeters, of 5.65 ± 2.76 for CC- and of 7.83 ± 3.04 for MLO-mammograms, while the TRE is 7.33 ± 3.62 in the 3D MRI. We also evaluate the effect of the glandularity of the breast as well as the landmark position on the TRE, obtaining moderated correlation values (0.65 and 0.77 respectively), concluding that these aspects need to be considered to increase the accuracy in further approaches.

Adaptive radiotherapy for NSCLC patients: utilizing the principle of energy conservation to evaluate dose mapping operations

Tumor regression during the course of fractionated radiotherapy confounds the ability to accurately estimate the total dose delivered to tumor targets. Here we present a new criterion to improve the accuracy of image intensity-based dose mapping operations for adaptive radiotherapy for patients with non-small cell lung cancer (NSCLC). Six NSCLC patients were retrospectively investigated in this study. An image intensity-based B-spline registration algorithm was used for deformable image registration (DIR) of weekly CBCT images to a reference image. The resultant displacement vector fields were employed to map the doses calculated on weekly images to the reference image. The concept of energy conservation was introduced as a criterion to evaluate the accuracy of the dose mapping operations. A finite element method (FEM)-based mechanical model was implemented to improve the performance of the B-Spline-based registration algorithm in regions involving tumor regression. For the six patients, deformed tumor volumes changed by 21.2 ± 15.0% and 4.1 ± 3.7% on average for the B-Spline and the FEM-based registrations performed from fraction 1 to fraction 21, respectively. The energy deposited in the gross tumor volume (GTV) was 0.66 Joules (J) per fraction on average. The energy derived from the fractional dose reconstructed by the B-spline and FEM-based DIR algorithms in the deformed GTV’s was 0.51 J and 0.64 J, respectively. Based on landmark comparisons for the 6 patients, mean error for the FEM-based DIR algorithm was 2.5 ± 1.9 mm. The cross-correlation coefficient between the landmark-measured displacement error and the loss of radiation energy was −0.16 for the FEM-based algorithm. To avoid uncertainties in measuring distorted landmarks, the B-Spline-based registrations were compared to the FEM registrations, and their displacement differences equal 4.2 ± 4.7 mm on average. The displacement differences were correlated to their relative loss of radiation energy with a cross-correlation coefficient equal to 0.68. Based on the principle of energy conservation, the FEM-based mechanical model has a better performance than the B-Spline-based DIR algorithm. It is recommended that the principle of energy conservation be incorporated into a comprehensive QA protocol for adaptive radiotherapy.

A hybrid patient-specific biomechanical model based image registration method for the motion estimation of lungs.

This paper presents a new hybrid biomechanical model-based non-rigid image registration method for lung motion estimation. In the proposed method, a patient-specific biomechanical modelling process captures major physically realistic deformations with explicit physical modelling of sliding motion, whilst a subsequent non-rigid image registration process compensates for small residuals. The proposed algorithm was evaluated with 10 4D CT datasets of lung cancer patients. The target registration error (TRE), defined as the Euclidean distance of landmark pairs, was significantly lower with the proposed method (TRE=1.37mm) than with biomechanical modelling (TRE=3.81mm) and intensity-based image registration without specific considerations for sliding motion (TRE=4.57mm). The proposed method achieved a comparable accuracy as several recently developed intensity-based registration algorithms with sliding handling on the same datasets. A detailed comparison on the distributions of TREs with three non-rigid intensity-based algorithms showed that the proposed method performed especially well on estimating the displacement field of lung surface regions (mean TRE=1.33mm, maximum TRE=5.3mm). The effects of biomechanical model parameters (such as Poisson's ratio, friction and tissue heterogeneity) on displacement estimation were investigated. The potential of the algorithm in optimising biomechanical models of lungs through analysing the pattern of displacement compensation from the image registration process has also been demonstrated.

Processing and fusion of passively acquired, millimeter and terahertz images of the human body

A passive, millimeter wave (MMW) and terahertz (THz) dual-band imaging system composed of 94 and 250 GHz single-element detectors was used to investigate preprocessing and fusion algorithms for dual-band images. Subsequently, an MMW and THz image preprocessing and fusion integrated algorithm (MMW-THz IPFIA) was developed. In the algorithm, a block-matching and three-dimensional filtering denoising algorithm is employed to filter noise, an adaptive histogram equalization algorithm to enhance images, an intensity-based registration algorithm to register images, and a wavelet-based image fusion algorithm to fuse the preprocessed images. The performance of the algorithm was analyzed by calculating the SNR and information entropy of the actual images. This algorithm effectively reduces the image noise and improves the level of detail in the images. Since the algorithm improves the performance of the investigated imaging system, it should support practical technological applications. Because the system responds to blackbody radiation, its improvement is quantified herein using the static performance parameter commonly employed for thermal imaging systems, namely, the minimum detectable temperature difference (MDTD). An experiment was conducted in which the system’s MDTD was measured before and after applying the MMW-THz IPFIA, verifying the improved performance that can be realized through its application.

Structure matching driven by joint-saliency-structure adaptive kernel regression

Matching outlier structures with missing correspondences and/or local large deformations is very difficult in image registration. In this paper, we define structure matching as an iterative local adaptive kernel regression which locally reconstructs moving image's dense deformation fields from the discrete displacement fields computed by multi-resolution block matching. First, a new joint saliency map (JSM) is proposed to match a structure-tensor-based local saliency distribution for each overlapping pixel pair and highlight the corresponding saliency structures (called joint saliency structures, JSSs) between the images. To explore the consistency of normal JSSs and their deformations around the outliers, we use JSM to guide the dense deformation reconstruction by emphasizing the JSSs’ discrete displacement vectors in kernel regression. The JSS adaptive kernel regression adapts anisotropic kernel's shape and orientation to reference image's structure and weights more contribution from JSS's displacement vectors for the iterative regression, whereby moving image's local deformations can be compliant with reference image's corresponding normal structures. The experimental results demonstrate that the proposed method achieves almost the best performance in structure matching of all challenging image pairs with outlier structures compared with other state-of-the-art intensity-based nonrigid registration algorithms.

Accelerated gradient-based free form deformable registration for online adaptive radiotherapy

The registration of planning fan-beam computed tomography (FBCT) and daily cone-beam CT (CBCT) is a crucial step in adaptive radiation therapy. The current intensity-based registration algorithms, such as Demons, may fail when they are used to register FBCT and CBCT, because the CT numbers in CBCT cannot exactly correspond to the electron densities. In this paper, we investigated the effects of CBCT intensity inaccuracy on the registration accuracy and developed an accurate gradient-based free form deformation algorithm (GFFD). GFFD distinguishes itself from other free form deformable registration algorithms by (a) measuring the similarity using the 3D gradient vector fields to avoid the effect of inconsistent intensities between the two modalities; (b) accommodating image sampling anisotropy using the local polynomial approximation-intersection of confidence intervals (LPA-ICI) algorithm to ensure a smooth and continuous displacement field; and (c) introducing a ‘bi-directional’ force along with an adaptive force strength adjustment to accelerate the convergence process. It is expected that such a strategy can decrease the effect of the inconsistent intensities between the two modalities, thus improving the registration accuracy and robustness. Moreover, for clinical application, the algorithm was implemented by graphics processing units (GPU) through OpenCL framework. The registration time of the GFFD algorithm for each set of CT data ranges from 8 to 13 s. The applications of on-line adaptive image-guided radiation therapy, including auto-propagation of contours, aperture-optimization and dose volume histogram (DVH) in the course of radiation therapy were also studied by in-house-developed software.

A NOVEL FEATURE EXPANSION ALGORITHM FOR NONRIGID CT/MRI BRAIN IMAGE REGISTRATION

Image registration is one of the challenging tasks in medical image analysis. While coming to non rigid image registration there are mainly two issues to consider. They are i) intensity similarity and ii) gray level transformation. The issue with intensity similarity is it is not necessarily equivalent to anatomical similarity when the anatomical correspondences between source and target images are established. Another issue is choosing an appropriate registration algorithm. It should be robust against monotonic gray-level transformation when aligning anatomical structures in the presence of bias fields. Here new feature- intensity based registration method developed for nonrigid brain image registration to overcome the above stated issues named as Anatomical Region Descriptor (ARD). This method is developed on image feature, it encodes geometric properties of anatomical structures and pixel wise interaction details. It is efficient and theoretically monotonic gray level transformation invariant. This method is integrated with intensity based registration algorithm named as residual complexity for Registration purpose. This proposed method is compared with three other non rigid image registration algorithms. Experimental results of the proposed method show that it achieves the highest accuracy rate among the compared methods.

A simple and accurate method for computer-aided transapical aortic valve replacement

Background and purposeTransapical aortic valve replacement (TAVR) is a recent minimally invasive surgical treatment technique for elderly and high-risk patients with severe aortic stenosis. In this paper, a simple and accurate image-based method is introduced to aid the intra-operative guidance of TAVR procedure under 2-D X-ray fluoroscopy. MethodsThe proposed method fuses a 3-D aortic mesh model and anatomical valve landmarks with live 2-D fluoroscopic images. The 3-D aortic mesh model and landmarks are reconstructed from interventional X-ray C-arm CT system, and a target area for valve implantation is automatically estimated using these aortic mesh models.Based on template-based tracking approach, the overlay of visualized 3-D aortic mesh model, landmarks and target area of implantation is updated onto fluoroscopic images by approximating the aortic root motion from a pigtail catheter motion without contrast agent. Also, a rigid intensity-based registration algorithm is used to track continuously the aortic root motion in the presence of contrast agent. Furthermore, a sensorless tracking of the aortic valve prosthesis is provided to guide the physician to perform the appropriate placement of prosthesis into the estimated target area of implantation. ResultsRetrospective experiments were carried out on fifteen patient datasets from the clinical routine of the TAVR. The maximum displacement errors were less than 2.0mm for both the dynamic overlay of aortic mesh models and image-based tracking of the prosthesis, and within the clinically accepted ranges. Moreover, high success rates of the proposed method were obtained above 91.0% for all tested patient datasets. ConclusionThe results showed that the proposed method for computer-aided TAVR is potentially a helpful tool for physicians by automatically defining the accurate placement position of the prosthesis during the surgical procedure.

TU‐C‐141‐02: Development of a Hyrbid Biomechanical Model Based Deformable Image Registration; Application in Lung

Purpose: To investigate the reduction in maximum errors in 4D CT lung Deformable Image Registration (DIR) using a hybrid biomechanical model based algorithm with an intensity based registration refinement. Methods: Morfeus, a biomechanical modeling algorithm for deformable image registration was used to register 3D inhale to exhale images of the lungs acquired via 4DCT. The predicted exhale image was obtained by interpolation. An intensity based registration algorithm based on Sum of Absolute Differences (SAD) and BSpline free form deformations (drop3D, Munich, Germany) was then employed to refine the results by a second registration from the Morfeus predicted exhale to the actual exhale image. The BSpline grid point spacing for the refinement was set to 9mm. To measure the accuracy, Target Registration Error (TRE) was calculated based on the Euclidean distance of corresponding bifurcation points on both images. Improvements in the overall TRE as well as reduction in maximum errors were evaluated. Results: The hybrid method has been evaluated on 5 patients to date with 45 to 76 identified bifurcation points per patient. The Morfeus TRE ranged from 2.2±1.0 mm (mean±SD) to 3.6±1.9 mm. This was reduced to 1.4±0.8 mm up to 1.6±2.0 mm with the hybrid method. More importantly, the number of bifurcation points (% of total points) with an error greater than 5 mm was reduced from 54 (22%) points (across all patients, range 3 to 24 points per patient) with Morfeus to 10 (4%) points (range 0 to 4 points per patient) with the hybrid method. Conclusion: The proposed hybrid method combines the flexibility of the biomechanical model based algorithm, including the ability to model the sliding interface between the lungs and the chest wall, with the advantages of intensity based registration for the contrast rich lung images to provide a highly accurate DIR algorithm. This research is supported by the NIH 5RO1CA124714‐02. KK Brock has financial interest in the deformable registration technology through a licensing agreement with RaySearch Laboratories.