Segmentation of parotid glands from registered CT and MR images

PurposeTo develop an automatic multimodal method for segmentation of parotid glands (PGs) from pre-registered computed tomography (CT) and magnetic resonance (MR) images and compare its results to the results of an existing state-of-the-art algorithm that segments PGs from CT images only.MethodsMagnetic resonance images of head and neck were registered to the accompanying CT images using two different state-of-the-art registration procedures. The reference domains of registered image pairs were divided on the complementary PG regions and backgrounds according to the manual delineation of PGs on CT images, provided by a physician. Patches of intensity values from both image modalities, centered around randomly sampled voxels from the reference domain, served as positive or negative samples in the training of the convolutional neural network (CNN) classifier. The trained CNN accepted a previously unseen (registered) image pair and classified its voxels according to the resemblance of its patches to the patches used for training. The final segmentation was refined using a graph-cut algorithm, followed by the dilate-erode operations.ResultsUsing the same image dataset, segmentation of PGs was performed using the proposed multimodal algorithm and an existing monomodal algorithm, which segments PGs from CT images only. The mean value of the achieved Dice overlapping coefficient for the proposed algorithm was 78.8%, while the corresponding mean value for the monomodal algorithm was 76.5%.ConclusionsAutomatic PG segmentation on the planning CT image can be augmented with the MR image modality, leading to an improved RT planning of head and neck cancer.     

Efficient liver segmentation in CT images based on graph cuts and bottleneck detection

Liver segmentation from abdominal computed tomography (CT) volumes is extremely important for computer-aided liver disease diagnosis and surgical planning of liver transplantation. Due to ambiguous edges, tissue adhesion, and variation in liver intensity and shape across patients, accurate liver segmentation is a challenging task. In this paper, we present an efficient semi-automatic method using intensity, local context, and spatial correlation of adjacent slices for the segmentation of healthy liver regions in CT volumes. An intensity model is combined with a principal component analysis (PCA) based appearance model to exclude complex background and highlight liver region. They are then integrated with location information from neighboring slices into graph cuts to segment the liver in each slice automatically. Finally, a boundary refinement method based on bottleneck detection is used to increase the segmentation accuracy. Our method does not require heavy training process or statistical model construction, and is capable of dealing with complicated shape and intensity variations. We apply the proposed method on XHCSU14 and SLIVER07 databases, and evaluate it by MICCAI criteria and Dice similarity coefficient. Experimental results show our method outperforms several existing methods on liver segmentation.     

Artifacts in magnetic resonance imaging and computed tomography caused by dental materials

Background

Artifacts caused by dental restorations, such as dental crowns, dental fillings and orthodontic appliances, are a common problem in MRI and CT scans of the head and neck. The aim of this in-vitro study was to identify and evaluate the artifacts produced by different dental restoration materials in CT and MRI images.

Methods

Test samples of 44 materials (Metal and Non-Metal) commonly used in dental restorations were fabricated and embedded with reference specimens in gelatin moulds. MRI imaging of 1.5T and CT scan were performed on the samples and evaluated in two dimensions. Artifact size and distortions were measured using a digital image analysis software.

Results

In MRI, 13 out of 44 materials produced artifacts, while in CT 41 out of 44 materials showed artifacts. Artifacts produced in both MRI and CT images were categorized according to the size of the artifact.

Significance

Metal based restoration materials had strong influence on CT and less artifacts in MRI images. Rare earth elements such as Ytterbium trifluoride found in composites caused artifacts in both MRI and CT. Recognizing these findings would help dental materials manufacturers and developers to produce materials which can cause less artifacts in MRI and CT images.     

Précautions,pièges et artefacts en TEP/TDM au 18FDG : généralités et cas particulier des pathologies de la tête et du cou

The PET/CT imaging with 18F-FDG is an essential diagnostic tool in the management of many diseases today. However, because of its functional and metabolic nature, it requires for its realization the respect of certain precautions to avoid abnormal images or false negative tests. Moreover, in the context of head and neck diseases, knowledge of anatomy and physiological uptakes appears essential for quality interpretation. In this paper, we illustrate with several personal circumstances or particular clinical situations from literature, the potential pitfalls and artifacts that could lead to misinterpretation.     

Multi-Atlas Based Adaptive Active Contour Model with Application to Organs at Risk Segmentation in Brain MR Images

BackgroundAccurate delineation of organs at risk (OARs) is critical in radiotherapy. Manual delineation is tedious and suffers from both interobserver and intraobserver variability. Automatic segmentation of brain MR images has a wide range of applications in brain tumor radiotherapy. In this paper, we propose a multi-atlas based adaptive active contour model for OAR automatic segmentation in brain MR images.MethodsThe proposed method consists of two parts: multi-atlas based OAR contour initiation and an adaptive edge and local region based active contour evolution. In the adaptive active contour model, we define an energy functional with an adaptive edge intensity fitting force which is responsible for evaluating contour inwards or outwards, and a local region intensity fitting force which guides the evolution of the contour.ResultsExperimental results show that the proposed method achieved more accurate segmentation results in brainstem, eyes and lens automatic segmentation with the Dice Similar Coefficient (DSC) value of 87.19%, 91.96%, 77.11% respectively. Besides, the dosimetric parameters also demonstrate the high consistency of the manual OAR delineations and the auto segmentation results of the proposed method in brain tumor radiotherapy.ConclusionsThe geometric and dosimetric evaluations show the desirable performance of the proposed method on the application of OARs segmentations in brain tumor radiotherapy.     

Zero echo time MRI-only treatment planning for radiation therapy of brain tumors after resection

Using magnetic resonance imaging (MRI) as the sole imaging modality for patient modeling in radiation therapy (RT) is a challenging task due to the need to derive electron density information from MRI and construct a so-called pseudo-computed tomography (pCT) image. We have previously published a new method to derive pCT images from head T1-weighted (T1-w) MR images using a single-atlas propagation scheme followed by a post hoc correction of the mapped CT numbers using local intensity information. The purpose of this study was to investigate the performance of our method with head zero echo time (ZTE) MR images. To evaluate results, the mean absolute error in bins of 20 HU was calculated with respect to the true planning CT scan of the patient. We demonstrated that applying our method using ZTE MR images instead of T1-w improved the correctness of the pCT in case of bone resection surgery prior to RT (that is, an example of large anatomical difference between the atlas and the patient).     

An Active Contour Model for the Segmentation of Images with Intensity Inhomogeneities and Bias Field Estimation

Intensity inhomogeneity causes many difficulties in image segmentation and the understanding of magnetic resonance (MR) images. Bias correction is an important method for addressing the intensity inhomogeneity of MR images before quantitative analysis. In this paper, a modified model is developed for segmenting images with intensity inhomogeneity and estimating the bias field simultaneously. In the modified model, a clustering criterion energy function is defined by considering the difference between the measured image and estimated image in local region. By using this difference in local region, the modified method can obtain accurate segmentation results and an accurate estimation of the bias field. The energy function is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. The proposed model first appeared as a two-phase model and then extended to a multi-phase one. The experimental results demonstrate the advantages of our model in terms of accuracy and insensitivity to the location of the initial contours. In particular, our method has been applied to various synthetic and real images with desirable results.     

Effectiveness of PET/CT with 18F-fluorothymidine in the staging of patients with squamous cell head and neck carcinomas before radiotherapy

Aim

The aim of our study was to compare the staging of the disease declared before anticancer treatment was begun with the staging that was found after the planning PET/CT scanning with ¹⁸F-FLT was performed.

Background

PET/CT in radiotherapy planning of head and neck cancers can facilitate the contouring of the primary tumour and the definition of metastatic lymph nodes.

Materials and methods

Between November 2010 and November 2013, 26 patients suffering from head and neck carcinomas underwent planning PET/CT examination with ¹⁸F-FLT. We compared the staging of the disease and the treatment strategy declared before and after ¹⁸F-FLT-PET/CT was performed.

Results

The findings from ¹⁸FLT-PET/CT led in 22 patients to a change of staging: in 19 patients it led to upstaging of the disease and in 3 patients it led to downstaging of the disease. In one patient, a secondary malignancy was found.

Conclusions

We have confirmed in this study that the use of ¹⁸F-FLT-PET/CT scanning in radiotherapy planning of squamous cell head and neck carcinomas has a great potential in the precise evaluation of disease staging and consequently in the precise determination of target volumes.     

A prospective observational study to analyse the influence of bladder and rectal volume changes on prostate radiotherapy using IMRT

AimTo analyse the interfractional bladder and rectal volume changes and the influence on prostate position.BackgroundInterfractional displacement of prostate due to variation in bladder and rectal volume is usual. It is only rational to study the bladder and rectal volume changes and their effects on prostate position during intensity modulated radiotherapy of prostate cancer.Materials and MethodsA prospective study was conducted on twenty patients with localized prostate cancer during the first phase of radiotherapy, where 50 gray in 25 fractions was delivered by the IMRT technique with daily cone beam computed tomography Bladder and rectum volumes were delineated on CBCT images and their volumes were noted. Prostate position was noted on each set of CBCT images with respect to specific reference points defined on the ileum and coccyx, and daily prostate displacement was noted.ResultsMean setup errors in vertical, longitudinal and lateral directions were noted as 1.49, 0.498 and 0.17 cm, respectively. Mean change in bladder and rectal volumes in daily CBCT images with respect to that on the first day CT images was noted as 101.94 and 10.22, respectively. Mean lateral and vertical displacement in prostate position was noted as 0.53 and 0.49 cm respectively. No considerable changes in dosimetric parameters were observed because of bladder and rectal volume changes.ConclusionsDaily CBCT should be done for accurate treatment delivery by the IMRT technique for prostate radiotherapy as prostate shifts physiologically with changes in rectal and bladder volumes.     

Automatic Structural Parcellation of Mouse Brain MRI Using Multi-Atlas Label Fusion

Multi-atlas segmentation propagation has evolved quickly in recent years, becoming a state-of-the-art methodology for automatic parcellation of structural images. However, few studies have applied these methods to preclinical research. In this study, we present a fully automatic framework for mouse brain MRI structural parcellation using multi-atlas segmentation propagation. The framework adopts the similarity and truth estimation for propagated segmentations (STEPS) algorithm, which utilises a locally normalised cross correlation similarity metric for atlas selection and an extended simultaneous truth and performance level estimation (STAPLE) framework for multi-label fusion. The segmentation accuracy of the multi-atlas framework was evaluated using publicly available mouse brain atlas databases with pre-segmented manually labelled anatomical structures as the gold standard, and optimised parameters were obtained for the STEPS algorithm in the label fusion to achieve the best segmentation accuracy. We showed that our multi-atlas framework resulted in significantly higher segmentation accuracy compared to single-atlas based segmentation, as well as to the original STAPLE framework.     

Fully Automated Whole-Head Segmentation with Improved Smoothness and Continuity,with Theory Reviewed

Individualized current-flow models are needed for precise targeting of brain structures using transcranial electrical or magnetic stimulation (TES/TMS). The same is true for current-source reconstruction in electroencephalography and magnetoencephalography (EEG/MEG). The first step in generating such models is to obtain an accurate segmentation of individual head anatomy, including not only brain but also cerebrospinal fluid (CSF), skull and soft tissues, with a field of view (FOV) that covers the whole head. Currently available automated segmentation tools only provide results for brain tissues, have a limited FOV, and do not guarantee continuity and smoothness of tissues, which is crucially important for accurate current-flow estimates. Here we present a tool that addresses these needs. It is based on a rigorous Bayesian inference framework that combines image intensity model, anatomical prior (atlas) and morphological constraints using Markov random fields (MRF). The method is evaluated on 20 simulated and 8 real head volumes acquired with magnetic resonance imaging (MRI) at 1 mm3 resolution. We find improved surface smoothness and continuity as compared to the segmentation algorithms currently implemented in Statistical Parametric Mapping (SPM). With this tool, accurate and morphologically correct modeling of the whole-head anatomy for individual subjects may now be feasible on a routine basis. Code and data are fully integrated into SPM software tool and are made publicly available. In addition, a review on the MRI segmentation using atlas and the MRF over the last 20 years is also provided, with the general mathematical framework clearly derived.     

Assessing the need for adaptive radiotherapy in head and neck cancer patients using an automatic planning tool

BackgroundUnbiased analysis of the impact of adaptive radiotherapy (ART) is necessary to evaluate dosimetric benefit and optimize clinics’ workflows. The aim of the study was to assess the need for adaptive radiotherapy (ART) in head and neck (H&N) cancer patients using an automatic planning tool in a retrospective planning study.Materials and methodsThirty H&N patients treated with adaptive radiotherapy were analysed. Patients had a CT scan for treatment planning and a verification CT during treatment according to the clinic’s protocol. Considering these images, three plans were retrospectively generated using the iCycle tool to simulate the scenarios with and without adaptation: 1) the optimized plan based on the planning CT; 2) the optimized plan based on the verification CT (ART-plan); 3) the plan obtained by considering treatment plan 1 re-calculated in the verification CT (non-ART plan). The dosimetric endpoints for both target volumes and OAR were compared between scenarios 2 and 3 and the SPIDERplan used to evaluate plan quality.ResultsThe most significant impact of ART was found for the PTVs, which demonstrated decreased D98% in the non-ART plan. A general increase in the dose was observed for the OAR but only the spinal cord showed a statistical significance. The SPIDERplan analysis indicated an overall loss of plan quality in the absence of ART.ConclusionThese results confirm the advantages of ART in H&N patients, especially for the coverage of target volumes. The usage of an automatic planning tool reduces planner-induced bias in the results, guaranteeing that the observed changes derive from the application of ART.     

A rhesus monkey reference label atlas for template driven segmentation

Background We have acquired dual‐echo spin‐echo (DE SE) MRI data of the rhesus monkey brain since 1994 as part of an ongoing study of normal aging. To analyze these legacy data for regional volume changes, we have created a reference label atlas for the Template Driven Segmentation (TDS) algorithm. Methods The atlas was manually created from DE SE legacy MRI data of one behaviorally normal, young, male rhesus monkey and consisted of 14 regions of interest (ROI’s). We analyzed the reproducibility and validity of the TDS algorithm using the atlas relative to manual segmentation. Results ROI volumes were comparable between the two segmentation methodologies, except TDS overestimated the volume of basal ganglia regions. Both methodologies were highly reproducible, but TDS had lower sensitivity and comparable specificity. Conclusions TDS segmentation calculates accurate volumes for most ROI’s. Sensitivity will be improved in future studies through the acquisition of higher quality data.     

Analysis of degenerated aortic valve bioprosthesis by segmentation of preoperative CT images

In the next future, transcatheter aortic valve implantation could represent a minimally invasive option in case of bioprosthesis failure for patients at high surgical risk. CT based preoperative planning of this procedure could be useful to optimize valve-in-valve implantation. In this context, bioprosthesis 3D analysis seems to be necessary, particularly for leaflets. The goal of this study was to propose different methods to segment and characterize a degenerated bioprosthesis using standard preoperative CT scan images in order to map structural injury of bioprosthesis and, ultimately, to plan the best positioning for valve-in-valve implantation. We report our preliminary results on segmentation of a degenerated bioprosthesis in aortic position. Three different methods have been tested and all allowed obtaining segmentation of the different bioprosthesis components. Results were compared by means of quantitative criteria. Explanted bioprosthesis CT images were used as reference. Semi-automatic segmentation seems to provide an interesting approach for the morphological characterization of degenerated bioprosthesis.     

Omni-wedge technique for increased dose homogeneity in head and neck radiotherapy

Dose homogeneity in head and neck tumour irradiation is a challenging task for conventional radiotherapy due to large anatomic contour irregularities and tissue heterogeneities in irradiation volumes. We present a simple technique based on the omni-wedge concept which uses superimposed fields, orthogonally wedged, to improve target-volumes homogeneity in head and neck tumour irradiation. The routine implementation of this technique is straightforward and easy to achieve with standard radiotherapy equipment and treatment planning software. Our five-year experience in the clinical implementation of this technique is presented.     

A voxel-based head-and-neck phantom built from tomographic colored images.

Recent progress in computer speed and medical imaging has made possible the development of a new family of anthropomorphic models, based on a volume elements (voxels) approach to phantom design. Such phantoms can represent details of the anatomical structures of the human body more realistically. Tomographic images (CT or MRI) contain the basic information for the construction of voxel-based phantoms. Use of voxel-based phantoms has its most significant application in the planning of individual patients therapy. To be implemented, results must be obtained in a reasonably short period of time. The segmentation of organs and tissues is a critical step in this process. This article presents a new approach in the construction of voxel-based phantoms that was implemented to simplify the segmentation process of organs and tissues, reducing the time used in this procedure. A voxel-based head and neck phantom, called MCvoxEL, was built using this new approach. The volumes and masses of the segmented organs and tissues were compared with data published by other investigators.     

Deep learning-based metal artifact reduction using cycle-consistent adversarial network for intensity-modulated head and neck radiation therapy treatment planning

PurposeTo develop a deep learning-based metal artifact reduction (DL-MAR) method using unpaired data and to evaluate its dosimetric impact in head and neck intensity-modulated radiation therapy (IMRT) compared with the water density override method.MethodsThe data set comprised the data of 107 patients who underwent radiotherapy. Fifteen patients with dental fillings were used as the test data set. The computed tomography (CT) images of the remaining 92 patients were divided into two domains: the metal artifact and artifact-free domains. CycleGAN was used for domain translation. The artifact index of the DL-MAR images was compared with that of the original uncorrected (UC) CT images. The dose distributions of the DL-MAR and UC plans were created by comparing the reference clinical plan with the water density override method (water plan) in each dataset. Dosimetric deviation in the oral cavity from the water plan was evaluated.ResultsThe artifact index of the DL-MAR images was significantly smaller than that of the UC images in all patients (13.2 ± 4.3 vs. 267.3 ± 113.7). Compared with the reference water plan, dose differences of the UC plans were greater than those of the DL-MAR plans. DL-MAR images provided dosimetric results that were more similar to those of the water plan than the UC plan.ConclusionsWe developed a fast DL-MAR method using CycleGAN for head and neck IMRT. The proposed method could provide consistent dose calculation against metal artifact and improve the efficiency of the planning process by eliminating manual delineation.     

FDG-PET imaging for radiotherapy target volume definition in lung cancer

Multimodality imaging plays a key role in the management of malignant tumours by radiation oncologists. The tumour extension at diagnosis identifies the patients in whom curative-intent radiotherapy is indicated. The target volumes and organs at risk are delineated on the relevant image modality (CT, MRI, PET), co-registered on a CT scan in treatment position for dose calculation purpose. The treatment machines are nowadays able to achieve heterogeneous dose distributions, possibly modulated within the target volume according to variations in the risk of failure. For instance, areas with high initial FDG uptake, low oxygenation, or insufficient response during radiotherapy could become the targets for selective dose increase. The scientific challenge includes registration and iterative segmentation of poorly contrasted images acquired on living bodies (variation in acquisition position, physiological movements and hollow organs filling, signal alteration induced by treatment…). The clinical validation of these innovative approaches and their diffusion in daily routine require a very close collaboration between many disciplines, based on a common language and understanding of radiotherapy target volumes, as illustrated in the present paper with FDG-PET imaging.     

A database for management of gene expression data in situ

MOTIVATION: To create a spatiotemporal atlas of Drosophila segmentation gene expression at cellular resolution. RESULTS: The expression of segmentation genes plays a crucial role in the establishment of the Drosophila body plan. Using the IBM DB2 Relational Database Management System we have designed and implemented the FlyEx database. FlyEx contains 2832 images of 14 segmentation gene expression patterns obtained from 954 embryos and 2,073,662 quantitative data records. The averaged data is available for most of segmentation genes at eight time points. FlyEx supports operations on images of gene expression patterns. The database can be used to examine the quality of data, analyze the dynamics of formation of segmentation gene expression domains, as well as estimate the variability of gene expression patterns. We also provide the capability to download data of interest. AVAILABILITY: http://urchin.spbcas.ru/flyex, http://flyex.ams.sunysb.edu/flyex     

Automated Movement Correction for Dynamic PET/CT Images: Evaluation with Phantom and Patient Data

Head movement during a dynamic brain PET/CT imaging results in mismatch between CT and dynamic PET images. It can cause artifacts in CT-based attenuation corrected PET images, thus affecting both the qualitative and quantitative aspects of the dynamic PET images and the derived parametric images. In this study, we developed an automated retrospective image-based movement correction (MC) procedure. The MC method first registered the CT image to each dynamic PET frames, then re-reconstructed the PET frames with CT-based attenuation correction, and finally re-aligned all the PET frames to the same position. We evaluated the MC method''s performance on the Hoffman phantom and dynamic FDDNP and FDG PET/CT images of patients with neurodegenerative disease or with poor compliance. Dynamic FDDNP PET/CT images (65 min) were obtained from 12 patients and dynamic FDG PET/CT images (60 min) were obtained from 6 patients. Logan analysis with cerebellum as the reference region was used to generate regional distribution volume ratio (DVR) for FDDNP scan before and after MC. For FDG studies, the image derived input function was used to generate parametric image of FDG uptake constant (K_i) before and after MC. Phantom study showed high accuracy of registration between PET and CT and improved PET images after MC. In patient study, head movement was observed in all subjects, especially in late PET frames with an average displacement of 6.92 mm. The z-direction translation (average maximum = 5.32 mm) and x-axis rotation (average maximum = 5.19 degrees) occurred most frequently. Image artifacts were significantly diminished after MC. There were significant differences (P<0.05) in the FDDNP DVR and FDG Ki values in the parietal and temporal regions after MC. In conclusion, MC applied to dynamic brain FDDNP and FDG PET/CT scans could improve the qualitative and quantitative aspects of images of both tracers.