Set Of Magnetic Resonance Images Research Articles

Proof-of-concept of real-time electromagnetic guidance for gynecologic interstitial catheters in high dose rate brachytherapy

Background and PurposeThe addition of interstitial needles to intracavitary gynecologic (GYN) high dose rate (HDR) brachytherapy has been shown to improve target coverage and organs-at-risk (OAR) sparing. However, no commercial solution allows real-time guidance of interstitial catheter placement. This phantom study aimed to evaluate the feasibility of an electromagnetic (EM) tracking system guidance workflow for GYN HDR brachytherapy treatment in a magnetic resonance imaging (MRI) and real-time transrectal ultrasound (TRUS) fusion scenario. Materials and MethodsA clinical investigational system combining a treatment planning system and the EM tracking technology was used. The 3D T2 weighted magnetic resonance (MR) image set of a patient treated with intracavitary and interstitial HDR brachytherapy was retrospectively chosen. The MR image set was used to delineate the target and the OARs. A preplan was generated to determine needles positions in advance. The implant was reproduced in a water phantom. A 3D TRUS scan was acquired, and a rigid registration between the MR and the TRUS images was performed. ResultsThe accuracy of the EM tracking system was < 1 mm for both the sagittal and the transverse modes of the TRUS probe. Contours that were delineated on the MRI were propagated on the TRUS images after the rigid registration. Needle insertion was successfully guided in real time with the EM tracking system on the TRUS live image using the MRI contours for guidance. ConclusionBased on this proof-of-concept, real-time EM-guidance of interstitial needle for GYN HDR brachytherapy appears to be feasible.

Semi-supervised auto-segmentation method for pelvic organ-at-risk in magnetic resonance images based on deep-learning.

In radiotherapy, magnetic resonance (MR) imaging has higher contrast for soft tissues compared to computed tomography (CT) scanning and does not emit radiation. However, manual annotation of the deep learning-based automatic organ-at-risk (OAR) delineation algorithms is expensive, making the collection of large-high-quality annotated datasets a challenge. Therefore, we proposed the low-cost semi-supervised OAR segmentation method using small pelvic MR image annotations. We trained a deep learning-based segmentation model using 116 sets of MR images from 116 patients. The bladder, femoral heads, rectum, and small intestine were selected as OAR regions. To generate the training set, we utilized a semi-supervised method and ensemble learning techniques. Additionally, we employed a post-processing algorithm to correct the self-annotation data. Both 2D and 3D auto-segmentation networks were evaluated for their performance. Furthermore, we evaluated the performance of semi-supervised method for 50 labeled data and only 10 labeled data. The Dice similarity coefficient (DSC) of the bladder, femoral heads, rectum and small intestine between segmentation results and reference masks is 0.954, 0.984, 0.908, 0.852 only using self-annotation and post-processing methods of 2D segmentation model. The DSC of corresponding OARs is 0.871, 0.975, 0.975, 0.783, 0.724 using 3D segmentation network, 0.896, 0.984, 0.890, 0.828 using 2D segmentation network and common supervised method. The outcomes of our study demonstrate that it is possible to train a multi-OAR segmentation model using small annotation samples and additional unlabeled data. To effectively annotate the dataset, ensemble learning and post-processing methods were employed. Additionally, when dealing with anisotropy and limited sample sizes, the 2D model outperformed the 3D model in terms of performance.

Deep learning application for abdominal organs segmentation on 0.35 T MR-Linac images.

Linear accelerator (linac) incorporating a magnetic resonance (MR) imaging device providing enhanced soft tissue contrast is particularly suited for abdominal radiation therapy. In particular, accurate segmentation for abdominal tumors and organs at risk (OARs) required for the treatment planning is becoming possible. Currently, this segmentation is performed manually by radiation oncologists. This process is very time consuming and subject to inter and intra operator variabilities. In this work, deep learning based automatic segmentation solutions were investigated for abdominal OARs on 0.35 T MR-images. One hundred and twenty one sets of abdominal MR images and their corresponding ground truth segmentations were collected and used for this work. The OARs of interest included the liver, the kidneys, the spinal cord, the stomach and the duodenum. Several UNet based models have been trained in 2D (the Classical UNet, the ResAttention UNet, the EfficientNet UNet, and the nnUNet). The best model was then trained with a 3D strategy in order to investigate possible improvements. Geometrical metrics such as Dice Similarity Coefficient (DSC), Intersection over Union (IoU), Hausdorff Distance (HD) and analysis of the calculated volumes (thanks to Bland-Altman plot) were performed to evaluate the results. The nnUNet trained in 3D mode achieved the best performance, with DSC scores for the liver, the kidneys, the spinal cord, the stomach, and the duodenum of 0.96 ± 0.01, 0.91 ± 0.02, 0.91 ± 0.01, 0.83 ± 0.10, and 0.69 ± 0.15, respectively. The matching IoU scores were 0.92 ± 0.01, 0.84 ± 0.04, 0.84 ± 0.02, 0.54 ± 0.16 and 0.72 ± 0.13. The corresponding HD scores were 13.0 ± 6.0mm, 16.0 ± 6.6mm, 3.3 ± 0.7mm, 35.0 ± 33.0mm, and 42.0 ± 24.0mm. The analysis of the calculated volumes followed the same behavior. Although the segmentation results for the duodenum were not optimal, these findings imply a potential clinical application of the 3D nnUNet model for the segmentation of abdominal OARs for images from 0.35 T MR-Linac.

Reducing annotation burden in MR: A novel MR-contrast guided contrastive learning approach for image segmentation.

Contrastive learning, a successful form of representational learning, has shown promising results in pretraining deep learning (DL) models for downstream tasks. When working with limited annotation data, as in medical image segmentation tasks, learning domain-specific local representations can further improve the performance of DL models. In this work, we extend the contrastive learning framework to utilize domain-specific contrast information from unlabeled Magnetic Resonance (MR) images to improve the performance of downstream MR image segmentation tasks in the presence of limited labeled data. The contrast in MR images is controlled by underlying tissue properties (e.g., T1 or T2) and image acquisition parameters. We hypothesize that learning to discriminate local representations based on underlying tissue properties should improve subsequent segmentation tasks on MR images. We propose a novel constrained contrastive learning (CCL) strategy that uses tissue-specific information via a constraint map to define positive and negative local neighborhoods for contrastive learning, embedding this information in the representational space during pretraining. For a given MR contrast image, the proposed strategy uses local signal characteristics (constraint map) across a set of related multi-contrast MR images as a surrogate for underlying tissue information. We demonstrate the utility of the approach for downstream: (1) multi-organ segmentation tasks in T2-weighted images where a DL model learns T2 information with constraint maps from a set of 2D multi-echo T2-weighted images (n=101) and (2) tumor segmentation tasks in multi-parametric images from the public brain tumor segmentation (BraTS) (n=80) dataset where DL models learn T1 and T2 information from multi-parametric BraTS images. Performance is evaluated on downstream multi-label segmentation tasks with limited data in (1) T2-weighted images of the abdomen from an in-house Radial-T2 (Train/Test=30/20), (2) public Cartesian-T2 (Train/Test=6/12) dataset, and (3) multi-parametric MR images from the public brain tumor segmentation dataset (BraTS) (Train/Test=40/50). The performance of the proposed CCL strategy is compared to state-of-the-art self-supervised contrastive learning techniques. In each task, a model is also trained using all available labeled data for supervised baseline performance. The proposed CCL strategy consistently yielded improved Dice scores, Precision, and Recall metrics, and reduced HD95 values across all segmentation tasks. We also observed performance comparable to the baseline with reduced annotation effort. The t-SNE visualization of features for T2-weighted images demonstrates its ability to embed T2 information in the representational space. On the BraTS dataset, we also observed that using an appropriate multi-contrast space to learn T1+T2, T1, or T2 information during pretraining further improved the performance of tumor segmentation tasks. Learning to embed tissue-specific information that controls MR image contrast with the proposed constrained contrastive learning improved the performance of DL models on subsequent segmentation tasks compared to conventional self-supervised contrastive learning techniques. The use of such domain-specific local representations could help understand, improve performance, and mitigate the scarcity of labeled data in MR image segmentation tasks.

MWSR-YLCA: Improved YOLOv7 Embedded with Attention Mechanism for Nasopharyngeal Carcinoma Detection from MR Images

Nasopharyngeal carcinoma (NPC) is a malignant tumor, and early diagnosis and timely treatment are important for NPC patients. Accurate and reliable detection of NPC lesions in magnetic resonance (MR) images is very helpful for the disease diagnosis. However, recent deep learning methods need to be improved for NPC detection in MR images. Because NPC tumors are invasive and usually small in size, it is difficult to distinguish NPC tumors from the closely connected surrounding tissues in a huge and complex background. In this paper, we propose an automatic detection method, named MWSR-YLCA, to accurately detect NPC lesions in MR images. Specifically, we design two modules, the multi-window settings resampling (MWSR) module and an improved YOLOv7 embedded with a coordinate attention mechanism (YLCA) module, to detect NPC lesions more accurately. First, the MWSR generates a pseudo-color version of MR images based on a multi-window resampling method, which preserves richer information. Subsequently, the YLCA detects the NPC lesion areas more accurately by constructing a novel network based on an improved YOLOv7 framework embedded with the coordinate attention mechanism. The proposed method was validated on an MR image set of 800 NPC patients and obtained 80.1% mAP detection performance with only 4694 data samples. The experimental results show that the proposed MWSR-YLCA method can perform high-accuracy detection of NPC lesions and has superior performance.

Multi-modal brain MRI images enhancement based on framelet and local weights super-resolution.

Magnetic resonance (MR) image enhancement technology can reconstruct high-resolution image from a low-resolution image, which is of great significance for clinical application and scientific research. T1 weighting and T2 weighting are the two common magnetic resonance imaging modes, each of which has its own advantages, but the imaging time of T2 is much longer than that of T1. Related studies have shown that they have very similar anatomical structures in brain images, which can be utilized to enhance the resolution of low-resolution T2 images by using the edge information of high-resolution T1 images that can be rapidly imaged, so as to shorten the imaging time needed for T2 images. In order to overcome the inflexibility of traditional methods using fixed weights for interpolation and the inaccuracy of using gradient threshold to determine edge regions, we propose a new model based on previous studies on multi-contrast MR image enhancement. Our model uses framelet decomposition to finely separate the edge structure of the T2 brain image, and uses the local regression weights calculated from T1 image to construct a global interpolation matrix, so that our model can not only guide the edge reconstruction more accurately where the weights are shared, but also carry out collaborative global optimization for the remaining pixels and their interpolated weights. Experimental results on a set of simulated MR data and two sets of real MR images show that the enhanced images obtained by the proposed method are superior to the compared methods in terms of visual sharpness or qualitative indicators.

Fully automated multiorgan segmentation of female pelvic magnetic resonance images with coarse-to-fine convolutional neural network.

Brachytherapy combined with external beam radiotherapy (EBRT) is the standard treatment for cervical cancer and has been shown to improve overall survival rates compared to EBRT only. Magnetic resonance (MR) imaging is used for radiotherapy (RT) planning and image guidance due to its excellent soft tissue image contrast. Rapid and accurate segmentation of organs at risk (OAR) is a crucial step in MR image-guided RT. In this paper, we propose a fully automated two-step convolutional neural network (CNN) approach to delineate multiple OARs from T2-weighted (T2W) MR images. We employ a coarse-to-fine segmentation strategy. The coarse segmentation step first identifies the approximate boundary of each organ of interest and crops the MR volume around the centroid of organ-specific region of interest (ROI). The cropped ROI volumes are then fed to organ-specific fine segmentation networks to produce detailed segmentation of each organ. A three-dimensional (3-D) U-Net is trained to perform the coarse segmentation. For the fine segmentation, a 3-D Dense U-Net is employed in which a modified 3-D dense block is incorporated into the 3-D U-Net-like network to acquire inter and intra-slice features and improve information flow while reducing computational complexity. Two sets of T2W MR images (221 cases for MR1 and 62 for MR2) were taken with slightly different imaging parameters and used for our network training and test. The network was first trained on MR1 which was a larger sample set. The trained model was then transferred to the MR2 domain via a fine-tuning approach. Active learning strategy was utilized for selecting the most valuable data from MR2 to be included in the adaptation via transfer learning. The proposed method was tested on 20 MR1 and 32 MR2 test sets. Mean± SD dice similarity coefficients are 0.93± 0.04, 0.87± 0.03, and 0.80± 0.10 on MR1 and 0.94± 0.05, 0.88± 0.04, and 0.80± 0.05 on MR2 for bladder, rectum, and sigmoid, respectively. Hausdorff distances (95th percentile) are 4.18± 0.52, 2.54± 0.41, and 5.03± 1.31mm on MR1 and 2.89± 0.33, 2.24± 0.40, and 3.28± 1.08mm on MR2, respectively. The performance of our method is superior to other state-of-the-art segmentation methods. We proposed a two-step CNN approach for fully automated segmentation of female pelvic MR bladder, rectum, and sigmoid from T2W MR volume. Our experimental results demonstrate that the developed method is accurate, fast, and reproducible, and outperforms alternative state-of-the-art methods for OAR segmentation significantly (p<0.05).

Automated measurement of sulcus angle on axial knee magnetic resonance images

AbstractPatellar dislocation is a disorder in the human knee where patella slips out of its expected position. The orthopedic experts need to manually measure the parameters indicating patellar instability from knee scans, which is a laborious and time‐consuming task. An automated method for measuring these parameters can resolve the issue of inter‐observer and intra‐observer variations and significantly lessen the burden of the experts. Therefore, in this work, a two‐step approach has been proposed for the automated measurement of the sulcus angle from knee magnetic resonance (MR) images to assist the experts in the diagnosis of patellar dislocation. Firstly, a variant of U‐Net architecture has been proposed harnessing the capabilities of the residual network to segment the region of interest (ROI) from the axial knee MR images. Secondly, the contour of ROI is used for the detection of key points required to compute sulcus angle. A T2‐weighted knee magnetic resonance imaging dataset of 50 patients obtained from Post Graduate Institute of Medical Education &amp; Research, Chandigarh, has been used. Out of 50 patients, the randomly selected knee MR images of 25 patients have been used to train the segmentation model. The intersection over union and dice similarity coefficient values of 94.71% and 97.28%, respectively, were achieved for the proposed segmentation model. The automated measurement of the sulcus angle resulted in a mean error of 2.52 ± 1.52° when tested on another set of axial knee MR images of 25 patients. The proposed framework produced results comparable to the manual expert measurements.

Abstract PO-077: Image clustering of brain tumor patients using a deep neural network

Abstract Purpose: The clustering of pediatric patients based on their unlabeled brain magnetic resonance (MR) images reveal the latent features and group structures. It is an unbiased approach to finding image-based markers and risk-stratification for neurocognitive functions. Analyzing large sets of MR images is time-intensive and challenging due to the MR images' high dimensionality and complexity. The extraction of low-dimension informative feature space instead of high-dimension MR image is an effective and fast solution to cluster images accurately. We aimed at developing a feature extraction method using deep learning. Our long-term research goal is to develop a feature extraction model using deep learning to automatically and accurately identify brain regions in association with neurocognitive outcomes. Methods: We used 124 registered fractional anisotropy (FA)-mapped of diffusion tensor (DT) images of pediatric medulloblastoma patients obtained after tumor surgery and before radiation from the SJMB03 clinical trial. First, we developed a 3D convolutional auto-encoder model based on a deep neural network for the voxel-wise analysis of 3D images to produce low-dimensional features, which can reconstruct input images accurately. Then, we applied the density-based clustering model, named OPTICS (Ordering Points To Identify the Clustering Structure), to the features. To train two models, we used a soft and dynamic algorithm to simultaneously combine two loss functions. Distance measure and CAHL (Cluster Assignment Loss Hardening) are used to measure feature learning and clustering performance. Results: Our experiment demonstrates that the proposed models yield results comparable in quality to manual clustering. The model trained regarding using a sufficient dataset and reducing dynamic loss function. Our model can cluster patients precisely and extract representative hidden features of the images, which is much more time- and labor-efficient compared to manual clustering by experts. Conclusions: In this study, we focused on a new feature extraction method and clustering of brain images. Because of the deep neural networks' unique advantages in image processing, we considered a 3D convolutional auto-encoder for the feature extraction part and OPTICS algorithm for the clustering part of the model. This method is highly useful in neuroimaging and neurocognitive research. Citation Format: Hadi Hosseini, Cheng Cheng, John Glass, Gene Reddick, Amar Gajjar, Zhaohua Lu. Image clustering of brain tumor patients using a deep neural network [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-077.

A brain tumor detection system using gradient based watershed marked active contours and curvelet transform

AbstractComputer aided brain tumor detection is an efficient research area in brain image processing. In this study, a methodology called GWMAC‐CT (gradient based watershed marked active contours and curvelet transform) is proposed to detect the brain tumors in magnetic resonance (MR) images. The implemented system is based on skull removing, segmentation of region of interest (ROI), feature extraction, and ROI classification as tumor or nontumor. The proposed GWMAC is a two‐stage segmentation method which includes gradient based watershed transform (GWT) and improved active contours. The rough ROIs obtained with GWT are utilized as initial contours for the improved active contours method instead of marking initial contours manually. Curvelet transform‐based features of the exact ROI contours are classified via well‐known classification methods such as support vector machine (SVM), K‐nearest neighbors, random forest tree, and Naïve Bayes. Experiments are carried out on a set of brain MR images from BRATS database to demonstrate the effectiveness of the proposed method. The performance evaluators such as accuracy, kappa statistics, false positive rate, precision, F1‐measure, and area under ROC curve are calculated as 96.81%, 0.927, 0.046, 0.905, 0.95, and 0.977, respectively with SVM.

Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy.

Magnetic resonance (MR) only radiation therapy for prostate treatment provides superior contrast for defining targets and organs-at-risk (OARs). This study aims to develop a deep learning model to leverage this advantage to automate the contouring process. Six structures (bladder, rectum, urethra, penile bulb, rectal spacer, prostate and seminal vesicles) were contoured and reviewed by a radiation oncologist on axial T2-weighted MR image sets from 50 patients, which constituted expert delineations. The data was split into a 40/10 training and validation set to train a two-dimensional fully convolutional neural network, DeepLabV3+, using transfer learning. The T2-weighted image sets were pre-processed to 2D false color images to leverage pre-trained (from natural images) convolutional layers' weights. Independent testing was performed on an additional 50 patient's MR scans. Performance comparison was done against a U-Net deep learning method. Algorithms were evaluated using volumetric Dice similarity coefficient (VDSC) and surface Dice similarity coefficient (SDSC). When comparing VDSC, DeepLabV3+ significantly outperformed U-Net for all structures except urethra (P < 0.001). Average VDSC was 0.93 ± 0.04 (bladder), 0.83 ± 0.06 (prostate and seminal vesicles [CTV]), 0.74 ± 0.13 (penile bulb), 0.82 ± 0.05 (rectum), 0.69 ± 0.10 (urethra), and 0.81 ± 0.1 (rectal spacer). Average SDSC was 0.92 ± 0.1 (bladder), 0.85 ± 0.11 (prostate and seminal vesicles [CTV]), 0.80 ± 0.22 (penile bulb), 0.87 ± 0.07 (rectum), 0.85 ± 0.25 (urethra), and 0.83 ± 0.26 (rectal spacer). A deep learning-based model produced contours that show promise to streamline an MR-only planning workflow in treating prostate cancer.

Segmentation of bias field induced brain MR images using rough sets and stomped-t distribution

Over the past few decades, automatic segmentation of brain magnetic resonance (MR) images into different tissue classes has remained an important research area, particularly due to the presence of bias field artifact in MR images. In this regard, the stomped normal (StN) distribution is proved to generate an optimal representation of the intensity distribution in brain MR images, by incorporating the properties of rough sets in the probabilistic framework. The StN distribution is capable of successfully modelling the central tendency, dispersion, and width of the intensity distribution. However, it does not take into consideration the kurtosis of the distribution, which controls the concentration of values around the mean and shape of the tail of intensity distribution. In this regard, the paper presents a novel method for simultaneous segmentation and bias field correction in brain MR images. It integrates the concept of rough sets and the merit of a recently introduced probability distribution, called stomped-t (St-t) distribution. The St-t distribution incorporates the property of kurtosis in rough-probabilistic framework, where each tissue class is modelled using a crisp lower approximation and a probabilistic boundary region. The brain MR image is modelled using a mixture of finite number of St-t distributions and one uniform distribution. The uniform distribution takes into account cerebro-spinal fluid, pathologies, and other non-brain tissues. The proposed method employs both expectation-maximization algorithm and hidden Markov random field model for accurate and robust image segmentation. The performance of the proposed approach, along with a comparison with related methods, is illustrated on a set of synthetic and real brain MR images for different bias fields and noise levels.

A novel automated magnetic resonance image segmentation approach based on elliptical gamma mixture model for breast lumps detection

AbstractThis article introduces a novel semisupervised automated segmentation approach for breast magnetic resonance (MR) image on multicore CPU‐GPU systems. The basic idea of the proposed method is clustering‐based semisupervised classifier devised by elliptical gamma mixture model (EGMM). Parameters of EGMM are identified by the iterative log‐expectation maximization (EM) algorithm. The suggested classifier labels the groups of voxels in an input image first and then classifies the image slices using the EGMM. Two different implementations of the proposed algorithm have been developed based on two different types of high‐performance computing architectures such as graphics processing units (GPUs) and multicore processors. To realize the real‐time segmentation performance of our algorithm with two distinctive architecture, we have tested a set of breast MR images collected from MedPix. Comparison between two architectures in terms of segmentation performance and computational cost is assessed by the analysis of simulation and experimental results.

45 Quantification of geometric distortion on MR images and evaluation of the impact of distortion correction

Introduction Magnetic resonance (MR) images have proven very useful for target definition in radiotherapy. However, geometric distortions might be of concern. In this study, a GE software based solution to correct geometric distortions is evaluated. The amount of residual distortions on corrected MRI is then quantified and used to determine PTV margins. Methods Axial T1 gradient-echo sequences of an MR compatible phantom and of patients with brain metastases were acquired on a 3T MRI. All patients were injected with Gadolinium. MR images were corrected for geometric distortion using the default algorithm implemented on our acquisition software, leading to two sets of MR images per acquisition (corrected and uncorrected). The gross tumor volume (GTV) was then contoured by a physician on both corrected and uncorrected MR images of the patients. Acquisition parameters were the ones commonly used in clinical practice for intracranial tumors. The MR phantom external contour was drawn on both corrected and uncorrected MR images, and used to deform uncorrected images to match corrected images. The amplitude of the displacement vector field was used to identify the main regions of the image undergoing large geometric distortions (Figs. 1 and 2). The same work was done on patients using the external surface of the patients. Geometric distortions were quantified using visible markers on both CT and MR images (Fig. 3). Results The main regions affected by geometric distortion were identified using the vector displacement field. These regions are located apart from the machine isocenter in the transverse direction (Figs. 4 and 5). Maximum distortions measured on the phantom for uncorrected MR images ranged from 1 to 2 mm for slices located near the isocenter and until 3 mm for the most distant slices. Distortions remained below 1 mm in corrected MRI. Considering patient images, a maximum distance of 2 mm was observed between the GTVs contoured on both corrected and uncorrected MRI (Fig. 6). Conclusions Our results point out the importance of using a correction for geometric distortions in MR images. Without being corrected for, distortions might reach several millimeters. The correction algorithm we used significantly reduces the amount of distortion in the images, particularly in regions located away from the isocenter. Quantification of residual distortions was made on phantom. However, additional sources of distortions might be of interest when patients are considered as for example the difference in magnetic susceptibility among tissues. We are currently investigating a multimodal approach based on CT-MRI registration to quantify patient-specific distortions. Download : Download high-res image (570KB) Download : Download full-size image

P276] Impact on proton range estimates using a novel mr-based artifact reduction algorithm

Purpose Metal implants lead to streak and cupping artifacts in computed tomography (CT) images, causing erroneous CT number estimates for radiation therapy (RT) planning. We recently introduced kerMAR, a novel Magnetic Resonance (MR)-based CT metal artifact reduction algorithm that combines kernel regression on uncorrupted CT value/MR patch pairs with a forward model of the CT metal artifacts. Here, we compare the impact of kerMAR and the clinical oMAR algorithm (Philips) on the proton range in calculated spot scanning (SS) dose plans for proton RT. Methods We acquired T1w MR and CT image sets of a veal shank phantom with and without metal markers inserted, and applied kerMAR and oMAR to the former. We then created SS plans in Eclipse v. 13.7 (Varian) delivering 150 MeV protons in a 0.55 cm single spot that passed 1) near a metal marker at shallow depth and 2) near two different markers located at shallow (near bone) and deep depths, respectively. Similar images were acquired for 4 head-and-neck (HN) RT patients with dental implants, and plans using the same phantom beam, angled through the artifact corrupted oral cavity, were devised, leading to a configuration most resembling phantom beam 2. We finally recalculated the dose plans for the same beamline settings and monitor units on all CT sets, and compared the proton ranges defined as the depth with 80% of the maximum dose. Results For the phantom plans, the following range deviations relative to the metal-free reference plan (uncorrected CT, oMAR, kerMAR) were observed: Plan 1: (0.6, 0.6, 0.6)%; plan 2: (−4, −1.8, −2.1)%. The patient plans showed the following deviations from the uncorrected CT plan: kerMAR: (10, 8, −7, 11)%; oMAR: (3, 0.1, −10, 0.2)%. Conclusions Proton range calculations on a phantom showed similar improvements compared to the uncorrupted reference with kerMAR and oMAR. Similar calculations on HN patients, however, displayed systematic proton range increases when applying kerMAR as compared to oMAR.

Review of strategies for MRI based reconstruction of endocavitary and interstitial applicators in brachytherapy of cervical cancer.

Brachytherapy plays an essential role in the curative intent management of locally advanced cervical cancer. The introduction of the magnetic resonance (MR) as a preferred image modality and the development of new type of applicators with interstitial components have further improved its benefits. The aim of this work is to review the current status of one important aspect in the cervix cancer brachytherapy procedure, namely catheter reconstruction. MR compatible intracavitary and interstitial applicators are described. Considerations about the use of MR imaging (MRI) regarding appropriate strategies for applicator reconstruction, technical requirements, MR sequences, patient preparation and applicator commissioning are included. It is recommendable to perform the reconstruction process in the same image study employed by the physician for contouring, that is, T2 weighted (T2W) sequences. Nevertheless, a clear identification of the source path inside the catheters and the applicators is a challenge when using exclusively T2W sequences. For the intracavitary component of the implant, sometimes the catheters may be filled with some substance that produces a high intensity signal on MRI. However, this strategy is not feasible for plastic tubes or titanium needles, which, moreover, induce magnetic susceptibility artifacts. In these situations, the use of applicator libraries available in the treatment planning system (TPS) is useful, since they not only include accurate geometrical models of the intracavitary applicators, but also recent developments have made possible the implementation of the interstitial component. Another strategy to improve the reconstruction process is based on the incorporation of MR markers, such as small pellets, to be used as anchor points. Many institutions employ computed tomography (CT) as a supporting image modality. The registration of CT and MR image sets should be carefully performed, and its uncertainty previously assessed. Besides, an important research work is being carried out regarding the use of ultrasound and electromagnetic tracking technologies.

Estimating Accurate Target Coordinates with Magnetic Resonance Images by Using Multiple Phase-Encoding Directions during Acquisition

Background: Stereotactic procedures are image guided, often using magnetic resonance (MR) images limited by image distortion, which may influence targets for stereotactic procedures. Objectives: The aim of this work was to assess methods of identifying target coordinates for stereotactic procedures with MR in multiple phase-encoding directions. Methods: In 30 patients undergoing deep brain stimulation, we acquired 5 image sets: stereotactic brain computed tomography (CT), T2-weighted images (T2WI), and T1WI in both right-to-left (RL) and anterior-to-posterior (AP) phase-encoding directions. Using CT coordinates as a reference, we analyzed anterior commissure and posterior commissure coordinates to identify any distortion relating to phase-encoding direction. Results: Compared with CT coordinates, RL-directed images had more positive x-axis values (0.51 mm in T1WI, 0.58 mm in T2WI). AP-directed images had more negative y-axis values (0.44 mm in T1WI, 0.59 mm in T2WI). We adopted 2 methods to predict CT coordinates with MR image sets: parallel translation and selective choice of axes according to phase-encoding direction. Both were equally effective at predicting CT coordinates using only MR; however, the latter may be easier to use in clinical settings. Conclusion: Acquiring MR in multiple phase-encoding directions and selecting axes according to the phase-encoding direction allows identification of more accurate coordinates for stereotactic procedures.

Segmentation of Brain MRI Using Wavelet Transform and Grammatical Bee Colony

Multimodal Magnetic Resonance Imaging (MRI) is an imaging technique widely used in the diagnosis and treatment planning of patients. Lesion segmentation of brain MRI is one of the most important image analysis task in medical imaging. In this paper, a new method for the supervised segmentation of the lesion in brain MRI using Grammatical Bee Colony (GBC) is proposed. The segmentation process is adversely affected by the presence of noises and intensity inhomogeneities in the Magnetic Resonance (MR) images. Therefore, noises are removed from the images and intensity inhomogeneities are corrected in the pre-processing steps. A set of stationary wavelet features are extracted from the co-registered [Formula: see text]1-weighted ([Formula: see text]-[Formula: see text]), [Formula: see text]2-weighted ([Formula: see text]-[Formula: see text]) and Fluid–Attenuated Inversion Recovery (FLAIR) images after skull stripping. A classifier is evolved using the GBC to classify the tissues as healthy tissues or lesions. The GBC classifier is trained with extracted features. The trained classifier is used to segment the test Magnetic Resonance (MR) image into healthy tissues or lesion regions. Finally, the connected component labeling algorithm is used to extract the lesions from the segmented images in the post-processing step. Effectiveness of the proposed method is tested by identifying the brain lesions from a set of MR images.

Technical Developments: Zero Echo Time Imaging of the Shoulder: Enhanced Osseous Detail by Using MR Imaging.

Purpose To determine the intermodality agreement of morphologic grading and clinically relevant quantitative measurements between computed tomography (CT) and zero echo time (ZTE) magnetic resonance (MR) imaging of the shoulder. The primary objective was to demonstrate the clinical applicability of ZTE in osseous shoulder imaging. Materials and Methods Thirty-four patients undergoing standard-of-care (SOC) MR imaging with concomitant CT were enrolled in this institutional review board-approved study. ZTE images were acquired after SOC MR imaging. Glenoid morphology (version, vault depth, erosion), injury or disease (osteoarthritis, Bankart and Hill-Sachs lesions, subchondral cysts), and evidence of prior surgery were graded or measured. κ Values, intraclass correlation coefficients (ICCs), and Bland-Altman limits of agreement were used to establish agreement. Qualitative comparison of osseous findings was performed between ZTE and SOC MR imaging. Results Binary classification and nominal/ordinal grades showed substantial or better agreement between raters and modalities (κ or ICC > 0.6). Continuous measurements exhibited strong correlation between raters and modalities, although not universally. Bankart ICCs were not significant, owing to low prevalence. ZTE exhibited greater conspicuity of enthesopathic cysts and marrow edema. In 21 of 34 cases, ZTE imaging of osseous features exceeded SOC MR imaging. Conclusion ZTE MR imaging provides "CT-like" contrast for bone. The results of this study demonstrate strong intermodality agreement between measurements and grades from CT and ZTE images in a cohort of patients undergoing imaging with both modalities. A majority of ZTE image sets provided superior visualization of osseous features when compared with SOC MR image sets. This superiority coupled with strong quantitative agreement with CT suggests that ZTE may be used clinically in lieu of CT in some cases. © RSNA, 2017 Online supplemental material is available for this article.

Spatially Constrained Student’s t-Distribution Based Mixture Model for Robust Image Segmentation

The finite Gaussian mixture model is one of the most popular frameworks to model classes for probabilistic model-based image segmentation. However, the tails of the Gaussian distribution are often shorter than that required to model an image class. Also, the estimates of the class parameters in this model are affected by the pixels that are atypical of the components of the fitted Gaussian mixture model. In this regard, the paper presents a novel way to model the image as a mixture of finite number of Student’s t-distributions for image segmentation problem. The Student’s t-distribution provides a longer tailed alternative to the Gaussian distribution and gives reduced weight to the outlier observations during the parameter estimation step in finite mixture model. Incorporating the merits of Student’s t-distribution into the hidden Markov random field framework, a novel image segmentation algorithm is proposed for robust and automatic image segmentation, and the performance is demonstrated on a set of HEp-2 cell and natural images. Integrating the bias field correction step within the proposed framework, a novel simultaneous segmentation and bias field correction algorithm has also been proposed for segmentation of magnetic resonance (MR) images. The efficacy of the proposed approach, along with a comparison with related algorithms, is demonstrated on a set of real and simulated brain MR images both qualitatively and quantitatively.