Mutual Information Registration Research Articles

A Novel Approach for Position Verification and Dose Calculation through Local MVCT Reconstruction.

Traditional positioning verification using cone-beam computed tomography (CBCT) may incur errors due to potential misalignments between the isocenter of CBCT and the treatment beams in radiotherapy. This study introduces an innovative method for verifying patient positioning in radiotherapy. Initially, the transmission images from an electronic portal imaging device (EPID) are acquired from 10 distinct angles. Utilizing the ART-TV algorithm, a sparse reconstruction of local megavoltage computed tomography (MVCT) is performed. Subsequently, this MVCT is aligned with the planning CT via a three-dimensional mutual information registration technique, pinpointing any patient-positioning discrepancies and facilitating corrective adjustments to the treatment setup. Notably, this approach employs the same radiation source as used in treatment to obtain three-dimensional images, thereby circumventing errors stemming from misalignment between the isocenter of CBCT and the accelerator. The registration process requires only 10 EPID images, and the dose absorbed during this process is included in the total dose calculation. The results show that our method's reconstructed MVCT images fulfill the requirements for registration, and the registration algorithm accurately detects positioning errors, thus allowing for adjustments in the patient's treatment position and precise calculation of the absorbed dose.

Flexible 3D printing of the mitral valve apparatus and left coronary artery for patients with complex anatomical variations in mitral valve surgery

Abstract Funding Acknowledgements Type of funding sources: None. Introduction Injury to the left circumflex artery (LCA) occurs in an estimated 2.7% of patients undergoing mitral valve (MV) surgery. The average distance from the LCA to the MV varies substantially between patients but is on average 3.1 ± 1.3mm. In unfavorable anatomical variations, a 3D print of relevant anatomical structures could be helpful for a surgeon to be aware of the situation and determine a surgical strategy. In this case such a 3D print is made of a 66 year old patient with mitral valve regurgitation and a P2 prolapse assessed in the heart team for MVS. Purpose To create a flexible heart model using Computed tomography (CT) and Transesophageal echocardiography (TEE) scans of this patient that utilizes the synergistic information derived from both modalities and provides an improved method for surgical preparation in cases with unfavorable anatomical variations. Method CT and TEE scans of the heart and mitral valve are acquired and fused using Mutual information registration. Both modalities are used in the print as TEE is the gold standard for evaluating the MV prior to surgery while on CT the LCA can be visualized and the ventricle can be imaged with a higher spatial resolution. The combined reconstructions are hollowed and smoothed using Meshmixer and the Poisson disk sampling tool of Meshlab to make the reconstruction suitable for 3D printing, enhance visibility of the relevant anatomy and achieve the desired flexibility of the model. Results A flexible 3D model of the left side of the heart of a patient is created. The model consists of reconstructions of the left coronary artery (CT), the left side of the heart (CT), and the mitral valve (TEE). To expose the LCA, an indent in the tissue surrounding the LCA was made. At the apex of the heart and at the left lateral side a small window in the ventricle was created for visibility. A flexibility resembling the flexibility of tissue was created by hollowing a with walls of 1.2mm thickness and printing with Agilus 30 Clear (with a shore A value of 30) . Conclusion To our knowledge this is the first 3D print for the planning of mitral valve surgery in which CT and TEE scans are combined into one flexible print. The flexible 3D print with exposed coronary arteries allows for assessment of the mitral valve regurgitation deficit and determine a surgical strategy because of the flexibility of the model, and as the LCA is exposed in this model, the surgeon can adapt his surgical approach based on the location of the LCA.

Whole-Slide Imaging, Mutual Information Registration for Multiplex Immunohistochemistry and Immunofluorescence

Multiplex immunohistochemistry/immunofluorescence (mIHC/mIF) is a developing technology that facilitates the evaluation of multiple, simultaneous protein expressions at single-cell resolution while preserving tissue architecture. These approaches have shown great potential for biomarker discovery, yet many challenges remain. Importantly, streamlined cross-registration of multiplex immunofluorescence images with additional imaging modalities and immunohistochemistry (IHC) can help increase the plex and/or improve the quality of the data generated by potentiating downstream processes such as cell segmentation.To address this problem, a fully automated process was designed to perform a hierarchical, parallelizable, and deformable registration of multiplexed digital whole-slide images (WSIs). We generalized the calculation of mutual information as a registration criterion to an arbitrary number of dimensions, making it well suited for multiplexed imaging. We also used the self-information of a given IF channel as a criterion to select the optimal channels to use for registration. Additionally, as precise labeling of cellular membranes in situ is essential for robust cell segmentation, a pan-membrane immunohistochemical staining method was developed for incorporation into mIF panels or for use as an IHC followed by cross-registration. In this study, we demonstrate this process by registering whole-slide 6-plex/7-color mIF images with whole-slide brightfield mIHC images, including a CD3 and a pan-membrane stain. Our algorithm, WSI, mutual information registration (WSIMIR), performed highly accurate registration allowing the retrospective generation of an 8-plex/9-color, WSI, and outperformed 2 alternative automated methods for cross-registration by Jaccard index and Dice similarity coefficient (WSIMIR vs automated WARPY, P < .01 and P < .01, respectively, vs HALO + transformix, P = .083 and P = .049, respectively). Furthermore, the addition of a pan-membrane IHC stain cross-registered to an mIF panel facilitated improved automated cell segmentation across mIF WSIs, as measured by significantly increased correct detections, Jaccard index (0.78 vs 0.65), and Dice similarity coefficient (0.88 vs 0.79).

Improving performance of medical image alignment through super-resolution.

Medical image alignment is an important tool for tracking patient conditions, but the quality of alignment is influenced by the effectiveness of low-dose Cone-beam CT (CBCT) imaging and patient characteristics. To address these two issues, we propose an unsupervised alignment method that incorporates a preprocessing super-resolution process. We constructed the model based on a private clinical dataset and validated the enhancement of the super-resolution on alignment using clinical and public data. Through all three experiments, we demonstrate that higher resolution data yields better results in the alignment process. To fully constrain similarity and structure, a new loss function is proposed; Pearson correlation coefficient combined with regional mutual information. In all test samples, the newly proposed loss function obtains higher results than the common loss function and improve alignment accuracy. Subsequent experiments verified that, combined with the newly proposed loss function, the super-resolution processed data boosts alignment, can reaching up to 9.58%. Moreover, this boost is not limited to a single model, but is effective in different alignment models. These experiments demonstrate that the unsupervised alignment method with super-resolution preprocessing proposed in this study effectively improved alignment and plays an important role in tracking different patient conditions over time.

Coarse-to-Fine Image Registration for Multi-Temporal High Resolution Remote Sensing Based on a Low-Rank Constraint

For multi-temporal high resolution remote sensing images, the image registration is important but difficult due to the high resolution and low-stability land-cover. Especially, the changing of land-cover, solar altitude angle, radiation intensity, and terrain fluctuation distortion in the overlapping areas can represent different image characteristics. These time-varying properties cause traditional registration methods with known reference information to fault. Therefore, in this paper we propose a comprehensive coarse-to-fine registration (CCFR) algorithm. First, we design a low-rank constraint-based batch reference extraction (LRC-BRE) method. Under the low-rank constraint, the stable features with highly spatial co-occurrence can be reconstructed via matrix decomposition, and are set as reference images to batch registration. Second, we improve the general feature registration with block feature matching and local linear transformation (BFM-LLT) operators including match outlier filtering (MOF) on regional mutual information and dual-weighted block fitting (DWBF). Finally, based on combining LRC-BRE and BFM-LLT, CCFR is integrated. Experimental results show that the proposed method has a good batch alignment effect, especially in the registration of large difference image pairs. The proposed CCFR achieves a significant performance improvement over many state-of-the-art registration algorithms.

Atrial fibrillation driver identification through regional mutual information networks: a modeling perspective

PurposeEffective identification of electrical drivers within remodeled tissue is a key for improving ablation treatment for atrial fibrillation. We have developed a mutual information, graph-based approach to identify and propose fault tolerance metric of local efficiency as a distinguishing feature of rotational activation and remodeled atrial tissue.MethodsVoltage data were extracted from atrial tissue simulations (2D Karma, 3D physiological, and the Multiscale Cardiac Simulation Framework (MSCSF)) using multi-spline open and parallel regional mapping catheter geometries. Graphs were generated based on varied mutual information thresholds between electrode pairs and the local efficiency for each graph was calculated.ResultsHigh-resolution mapping catheter geometries can distinguish between rotational and irregular activation patterns using the derivative of local efficiency as a function of increasing mutual information threshold. The derivative is decreased for rotational activation patterns comparing to irregular activations in both a simplified 2D model (0.0017 ± 1 × 10−4 vs. 0.0032 ± 1 × 10−4, p < 0.01) and a more realistic 3D model (0.00092 ± 5 × 10−5 vs. 0.0014 ± 4 × 10−5, p < 0.01). Average local efficiency derivative can also distinguish between degrees of remodeling. Simulations using the MSCSF model, with 10 vs. 90% remodeling, display distinct derivatives in the grid design parallel spline catheter configuration (0.0015 ± 5 × 10−5 vs. 0.0019 ± 6 × 10−5, p < 0.01) and the flower shaped open spline configuration (0.0011 ± 5 × 10−5 vs. 0.0016 ± 4 × 10−5, p < 0.01).ConclusionA decreased derivative of local efficiency characterizes rotational activation and varies with atrial remodeling. This suggests a distinct communication pattern in cardiac rotational activation detectable via high-resolution regional mapping and could enable identification of electrical drivers for targeted ablation.

Intensity-Mosaic: automatic panorama mosaicking of disordered images with insufficient features.

Purpose: Handling low-quality and few-feature medical images is a challenging task in automatic panorama mosaicking. Current mosaicking methods for disordered input images are based on feature point matching, whereas in this case intensity-based registration achieves better performance than feature-point registration methods. We propose a mosaicking method that enables the use of mutual information (MI) registration for mosaicking randomly ordered input images with insufficient features. Approach: Dimensionality reduction is used to map disordered input images into a low dimensional space. Based on the low dimensional representation, the image global correspondence can be recognized efficiently. For adjacent image pairs, we optimize the MI metric for registration. The panorama is then created after image blending. We demonstrate our method on relatively lower-cost handheld devices that acquire images from the retina in vivo, kidney ex vivo, and bladder phantom, all of which contain sparse features. Results: Our method is compared with three baselines: AutoStitch, "dimension reduction + SIFT," and "MI-Only." Our method compared to the first two feature-point based methods exhibits 1.25 (ex vivo microscope dataset) to two times (in vivo retina dataset) rate of mosaic completion, and MI-Only has the lowest complete rate among three datasets. When comparing the subsequent complete mosaics, our target registration errors can be 2.2 and 3.8 times reduced when using the microscopy and bladder phantom datasets. Conclusions: Using dimensional reduction increases the success rate of detecting adjacent images, which makes MI-based registration feasible and narrows the search range of MI optimization. To the best of our knowledge, this is the first mosaicking method that allows automatic stitching of disordered images with intensity-based alignment, which provides more robust and accurate results when there are insufficient features for classic mosaicking methods.

Medium-low resolution multisource remote sensing image registration based on SIFT and robust regional mutual information

ABSTRACTOwing to significant geometric distortions and illumination differences, high precision and robust matching of multisource remote sensing images is a difficult task. To solve this, mutual information (MI)-based methods have been a preferred choice, as MI represents a measure of statistical dependence between the two images. However, MI only considers original grey information and neglects spatial information in the calculation of the probability distribution. In this paper, a novel similarity metric based on rotationally invariant regional mutual information (RIRMI) is proposed. The RIRMI metric is constructed by combining MI with a regional information based on the statistical relationship between rotationally invariant centre-symmetric local binary patterns of the images. The similarity metric based on RIRMI considers not only the spatial information, but the effect of the local grey variations and rotation changes on computing probability density function as well. The proposed method is tested on various simulated remote sensing images (5–30 m GSD) and real remote sensing images (2–30 m GSD) which are taken at different sensors, spectral bands, and times. Results verify that RIRMI is more robust and accurate than the common MI-based registration method.

Co-Registration of ex vivo Surgical Histopathology and in vivo T2 weighted MRI of the Prostate via multi-scale spectral embedding representation

Multi-modal image co-registration via optimizing mutual information (MI) is based on the assumption that intensity distributions of multi-modal images follow a consistent relationship. However, images with a substantial difference in appearance violate this assumption, thus MI directly based on image intensity alone may be inadequate to drive similarity based co-registration. To address this issue, we introduce a novel approach for multi-modal co-registration called Multi-scale Spectral Embedding Registration (MSERg). MSERg involves the construction of multi-scale spectral embedding (SE) representations from multimodal images via texture feature extraction, scale selection, independent component analysis (ICA) and SE to create orthogonal representations that decrease the dissimilarity between the fixed and moving images to facilitate better co-registration. To validate the MSERg method, we aligned 45 pairs of in vivo prostate MRI and corresponding ex vivo histopathology images. The dataset was split into a learning set and a testing set. In the learning set, length scales of 5 × 5, 7 × 7 and 17 × 17 were selected. In the independent testing set, we compared MSERg with intensity-based registration, multi-attribute combined mutual information (MACMI) registration and scale-invariant feature transform (SIFT) flow registration. Our results suggest that multi-scale SE representations generated by MSERg are found to be more appropriate for radiology-pathology co-registration.

3D interactive surgical visualization system using mobile spatial information acquisition and autostereoscopic display

Three-dimensional (3D) visualization of preoperative and intraoperative medical information becomes more and more important in minimally invasive surgery. We develop a 3D interactive surgical visualization system using mobile spatial information acquisition and autostereoscopic display for surgeons to observe surgical target intuitively. The spatial information of regions of interest (ROIs) is captured by the mobile device and transferred to a server for further image processing. Triangular patches of intraoperative data with texture are calculated with a dimension-reduced triangulation algorithm and a projection-weighted mapping algorithm. A point cloud selection-based warm-start iterative closest point (ICP) algorithm is also developed for fusion of the reconstructed 3D intraoperative image and the preoperative image. The fusion images are rendered for 3D autostereoscopic display using integral videography (IV) technology. Moreover, 3D visualization of medical image corresponding to observer’s viewing direction is updated automatically using mutual information registration method. Experimental results show that the spatial position error between the IV-based 3D autostereoscopic fusion image and the actual object was 0.38±0.92mm (n=5). The system can be utilized in telemedicine, operating education, surgical planning, navigation, etc. to acquire spatial information conveniently and display surgical information intuitively.

Image Registration Algorithm Based on Copula Distribution Estimation

In order to solve the problem that the measure function is easy to fall into the local extremum because of much local extremes in the mutual information registration method, this paper designs an optimization algorithm applied to image registration. One measure function based on mutual information and gradient similarity is constructed combining with evolutional copula estimation of distribution algorithm (ECEDA). New algorithm fully pays attention to the correlation between multidimensional variables joining with the linear weighted based on nonparametric estimation method to overcome the randomness of nonparametric estimation method. Experimental results show that comparing with the traditional copula estimation of distribution algorithm and other existing registration algorithms, the proposed algorithm has higher accurate rate and robustness.

Regional mutual information-based identification and reduction of flicker artifacts during video encoding

Present manuscript discusses a novel technique to identify flicker-prone regions in video and reduce its effects. The flicker-prone regions are identified with the help of regional mutual information which takes into account the geometrical properties of the frames while requiring no prior information about the data under consideration, which makes it suitable for video-processing applications. The flicker-prone regions are passed through a temporal filter before standard compliant encoding of the video sequence. Accurate measurement of the flicker-prone regions and independence of the encoding methodology makes the proposed method suitable for wide variety of encoders.

Validation of Registration for Renal Dynamic Contrast Enhanced MRI Imaging

In Dynamic Contrast Enhanced Resonance Imaging (DCE-MRI), abdomen is scanned repeatedly and rapidly after injection of a contrast agent. During data acquisition, collected images suffer from the motion induced by the patient if he/she moves or breathes heavily during the scan. Therefore, these images should be aligned accurately to correct the motion. Recently, mutual information (MI) registration has become the first tool to register renal DCE-MRI images before any further processing. However, MI registration is sensitive to initial conditions and optimization methods, and it is bound to fail under certain conditions such as extreme movement or noise in the image. Therefore, if automated image analysis for renal DCE-MRI is to enter the clinical settings, it is necessary to have validation strategies that show the limitations of registration models on known datasets. In this study, two methods are introduced for the validation of registration of renal DCE-MRI images. The first method demonstrates how to use the inverse transform to generate realistic looking DCE-MRI kidney images and use them in validation. The second method shows how to generate checkerboard images and how to evaluate the goodness of registration for real DCE-MRI images. These validation methods can be incorporated into the registration studies to quantitatively and qualitatively demonstrate the success and the limitations of registration models.

Wavelet subspace decomposition of thermal infrared images for defect detection in artworks

Health of ancient artworks must be routinely monitored for their adequate preservation. Faults in these artworks may develop over time and must be identified as precisely as possible. The classical acoustic testing techniques, being invasive, risk causing permanent damage during periodic inspections. Infrared thermometry offers a promising solution to map faults in artworks. It involves heating the artwork and recording its thermal response using infrared camera. A novel strategy based on pseudo-random binary excitation principle is used in this work to suppress the risks associated with prolonged heating. The objective of this work is to develop an automatic scheme for detecting faults in the captured images. An efficient scheme based on wavelet based subspace decomposition is developed which favors identification of, the otherwise invisible, weaker faults. Two major problems addressed in this work are the selection of the optimal wavelet basis and the subspace level selection. A novel criterion based on regional mutual information is proposed for the latter. The approach is successfully tested on a laboratory based sample as well as real artworks. A new contrast enhancement metric is developed to demonstrate the quantitative efficiency of the algorithm. The algorithm is successfully deployed for both laboratory based and real artworks.

SU‐F‐J‐96: Comparison of Frame‐Based and Mutual Information Registration Techniques for CT and MR Image Sets

Purpose:To compare the accuracy of CT‐MR registration using a mutual information method with registration using a frame‐based localizer box.Methods:Ten patients having the Leksell head frame and scanned with a modality specific localizer box were imported into the treatment planning system. The fiducial rods of the localizer box were contoured on both the MR and CT scans. The skull was contoured on the CT images. The MR and CT images were registered by two methods. The frame‐based method used the transformation that minimized the mean square distance of the centroids of the contours of the fiducial rods from a mathematical model of the localizer. The mutual information method used automated image registration tools in the TPS and was restricted to a volume‐of‐interest defined by the skull contours with a 5 mm margin. For each case, the two registrations were adjusted by two evaluation teams, each comprised of an experienced radiation oncologist and neurosurgeon, to optimize alignment in the region of the brainstem. The teams were blinded to the registration method.Results:The mean adjustment was 0.4 mm (range 0 to 2 mm) and 0.2 mm (range 0 to 1 mm) for the frame and mutual information methods, respectively. The median difference between the frame and mutual information registrations was 0.3 mm, but was not statistically significant using the Wilcoxon signed rank test (p=0.37).Conclusion:The difference between frame and mutual information registration techniques was neither statistically significant nor, for most applications, clinically important. These results suggest that mutual information is equivalent to frame‐based image registration for radiosurgery. Work is ongoing to add additional evaluators and to assess the differences between evaluators.

Automated Registration of Multimodal Optic Disc Images: Clinical Assessment of Alignment Accuracy.

To determine the accuracy of automated alignment algorithms for the registration of optic disc images obtained by 2 different modalities: fundus photography and scanning laser tomography. Images obtained with the Heidelberg Retina Tomograph II and paired photographic optic disc images of 135 eyes were analyzed. Three state-of-the-art automated registration techniques Regional Mutual Information, rigid Feature Neighbourhood Mutual Information (FNMI), and nonrigid FNMI (NRFNMI) were used to align these image pairs. Alignment of each composite picture was assessed on a 5-point grading scale: "Fail" (no alignment of vessels with no vessel contact), "Weak" (vessels have slight contact), "Good" (vessels with <50% contact), "Very Good" (vessels with >50% contact), and "Excellent" (complete alignment). Custom software generated an image mosaic in which the modalities were interleaved as a series of alternate 5×5-pixel blocks. These were graded independently by 3 clinically experienced observers. A total of 810 image pairs were assessed. All 3 registration techniques achieved a score of "Good" or better in >95% of the image sets. NRFNMI had the highest percentage of "Excellent" (mean: 99.6%; range, 95.2% to 99.6%), followed by Regional Mutual Information (mean: 81.6%; range, 86.3% to 78.5%) and FNMI (mean: 73.1%; range, 85.2% to 54.4%). Automated registration of optic disc images by different modalities is a feasible option for clinical application. All 3 methods provided useful levels of alignment, but the NRFNMI technique consistently outperformed the others and is recommended as a practical approach to the automated registration of multimodal disc images.

Efficient Morphometric Techniques in Alzheimer&amp;rsquo;s Disease Detection: Survey and Tools

The development of advance techniques in the multiple fields such as image processing, data mining and machine learning are required for the early detection of Alzheimer’s Disease (AD) and to prevent the progression of the disease to the later stages. The longitudinal and cross sectional images of elderly subjects were obtained from the standard datasets like ADNI, OASIS, MIRIAD and ICBM. The subject image obtained from the dataset, can be geometrically aligned to the template image through the process of registration. The registration techniques like Mutual Information Registration, Fluid registration, Rigid registration, Spatial Transformation algorithm for registration, Elastic Registration are selected based on type of transformation and similarity measures to suit the required application. The registered images are then subjected to the process of segmentation in order to segment relevant tissues or desired region of interest that are significant in AD detection. The different types of segmentation techniques such as Tissue Segmentation, Atlas based Segmentation, Hippocampus Segmentation and other segmentation techniques have been discussed. The segmented images are then subjected to morphometry techniques to identify the morphological changes developed in an abnormal image. The different types of morphometry techniques used are Voxel Based Morphometry (VBM), Deformation Based Morphometry (DBM), Shape Based Morphometry (SBM) and Feature Based Morphometry (FBM). But in recent years, the main focus of researchers is towards the FBM and SBM to overcome the disadvantage of group analysis that existed in VBM and DBM. Further the data is classified into healthy normal and AD by supervised, unsupervised or probabilistic methods.

Minimum mutual information based level set clustering algorithm for fast MRI tissue segmentation.

Accurate and accelerated MRI tissue recognition is a crucial preprocessing for real-time 3d tissue modeling and medical diagnosis. This paper proposed an information de-correlated clustering algorithm implemented by variational level set method for fast tissue segmentation. The key idea is to design a local correlation term between original image and piecewise constant into the variational framework. The minimized correlation will then lead to de-correlated piecewise regions. Firstly, by introducing a continuous bounded variational domain describing the image, a probabilistic image restoration model is assumed to modify the distortion. Secondly, regional mutual information is introduced to measure the correlation between piecewise regions and original images. As a de-correlated description of the image, piecewise constants are finally solved by numerical approximation and level set evolution. The converged piecewise constants automatically clusters image domain into discriminative regions. The segmentation results show that our algorithm performs well in terms of time consuming, accuracy, convergence and clustering capability.

Automatic Detection of Calcaneal-Fifth Metatarsal Angle Using Radiograph: A Computer-Aided Diagnosis of Flat Foot for Military New Recruits in Taiwan.

Flatfoot (pes planus) is one of the most important physical examination items for military new recruits in Taiwan. Currently, the diagnosis of flatfoot is mainly based on radiographic examination of the calcaneal-fifth metatarsal (CA–MT5) angle, also known as the arch angle. However, manual measurement of the arch angle is time-consuming and often inconsistent between different examiners. In this study, seventy male military new recruits were studied. Lateral radiographic images of their right and left feet were obtained, and mutual information (MI) registration was used to automatically calculate the arch angle. Images of two critical bones, the calcaneus and the fifth metatarsal bone, were isolated from the lateral radiographs to form reference images, and were then compared with template images to calculate the arch angle. The result of this computer-calculated arch angle was compared with manual measurement results from two radiologists, which showed that our automatic arch angle measurement method had a high consistency. In addition, this method had a high accuracy of 97% and 96% as compared with the measurements of radiologists A and B, respectively. The findings indicated that our MI registration measurement method cannot only accurately measure the CA–MT5 angle, but also saves time and reduces human error. This method can increase the consistency of arch angle measurement and has potential clinical application for the diagnosis of flatfoot.

SU‐E‐J‐224: Using UTE and T1 Weighted Spin Echo Pulse Sequences for MR‐Only Treatment Planning; Phantom Study

Purpose:Investigating a new approach in MRI based treatment planning using the combination of (Ultrashort Echo Time) UTE and T1 weighted spin echo pulse sequences to delineate air, bone and water (soft tissues) in generating pseudo CT images comparable with CT.Methods:A gel phantom containing chicken bones, ping pang balls filled with distilled water and air bubbles, was made. It scanned with MRI using UTE and 2D T1W SE pulse sequences with (in plane resolution= 0.53mm, slice thickness= 2 mm) and CT with (in plane resolution= 0.5 mm and slice thickness= 0.75mm) as a ground truth for geometrical accuracy. The UTE and T1W SE images were registered with CT using mutual information registration algorithm provided by Philips Pinnacle treatment planning system. The phantom boundaries were detected using Canny edge detection algorithm for CT, and MR images. The bone, air bubbles and water in ping pong balls were segmented from CT images using threshold 300HU, ‐ 950HU and 0HU, respectively. These tissue inserts were automatically segmented from combined UTE and T1W SE images using edge detection and relative intensity histograms of the phantom. The obtained segmentations of air, bone and water inserts were evaluated with those obtained from CT.Results:Bone and air can be clearly differentiated in UTE images comparable to CT. Combining UTE and T1W SE images successfully segmented the air, bone and water. The maximum segmentation differences from combine MRI images (UTE and T1W SE) and CT are within 1.3 mm, 1.1mm for bone, air, respectively. The geometric distortion of UTE sequence is small less than 1 pixel (0.53 mm) of MR image resolution.Conclusion:Our approach indicates that MRI can be used solely for treatment planning and its quality is comparable with CT.