3D Computed Tomography Volumes Research Articles

Semi-automatic fine delineation scheme for pancreatic cancer.

Pancreatic cancer fine delineation in medical images by physicians is a major challenge due to the vast volume of medical images and the variability of patients. A semi-automatic fine delineation scheme was designed to assist doctors in accurately and quickly delineating the cancer target region to improve the delineation accuracy of pancreatic cancer in computed tomography (CT) images and effectively reduce the workload of doctors. A target delineation scheme in image blocks was also designed to provide more information for the deep learning delineation model. The start and end slices of the image block were manually delineated by physicians, and the cancer in the middle slices were accurately segmented using a three-dimensional Res U-Net model. Specifically, the input of the network is the CT image of the image block and the delineation of the cancer in the start and end slices, while the output of the network is the cancer area in the middle slices of the image block. Meanwhile, the model performance of pancreatic cancer delineation and the workload of doctors in different image block sizes were studied. We used 37 3D CT volumes for training, 11 volumes for validating and 11 volumes for testing. The influence of different image block sizes on doctors' workload was compared quantitatively. Experimental results showed that the physician's workload was minimal when the image block size was 5, and all cancer could be accurately delineated. The Dice similarity coefficient was 0.894±0.029, the 95% Hausdorff distance was 3.465±0.710mm, the normalized surface Dice was 0.969±0.019. By completing the accurate delineation of all the CT images, the speed of the new method is 2.16 times faster than that of manual sketching. Our proposed 3D semi-automatic delineative method based on the idea of block prediction could accurately delineate CT images of pancreatic cancer and effectively deal with the challenges of class imbalance, background distractions, and non-rigid geometrical features. This study had a significant advantage in reducing doctors' workload, and was expected to help doctors improve their work efficiency in clinical application.

Efficient Multi-Organ Segmentation From 3D Abdominal CT Images With Lightweight Network and Knowledge Distillation.

Accurate segmentation of multiple abdominal organs from Computed Tomography (CT) images plays an important role in computer-aided diagnosis, treatment planning and follow-up. Currently, 3D Convolution Neural Networks (CNN) have achieved promising performance for automatic medical image segmentation tasks. However, most existing 3D CNNs have a large set of parameters and huge floating point operations (FLOPs), and 3D CT volumes have a large size, leading to high computational cost, which limits their clinical application. To tackle this issue, we propose a novel framework based on lightweight network and Knowledge Distillation (KD) for delineating multiple organs from 3D CT volumes. We first propose a novel lightweight medical image segmentation network named LCOV-Net for reducing the model size and then introduce two knowledge distillation modules (i.e., Class-Affinity KD and Multi-Scale KD) to effectively distill the knowledge from a heavy-weight teacher model to improve LCOV-Net's segmentation accuracy. Experiments on two public abdominal CT datasets for multiple organ segmentation showed that: 1) Our LCOV-Net outperformed existing lightweight 3D segmentation models in both computational cost and accuracy; 2) The proposed KD strategy effectively improved the performance of the lightweight network, and it outperformed existing KD methods; 3) Combining the proposed LCOV-Net and KD strategy, our framework achieved better performance than the state-of-the-art 3D nnU-Net with only one-fifth parameters. The code is available at https://github.com/HiLab-git/LCOVNet-and-KD.

A computer-aided tool for automatic volume estimation of hematoma using non-contrast brain CT scans

The computation of hematoma volume is the key parameter for treatment planning of Intracerebral hemorrhage (ICH). Non-contrast computed tomography (NCCT) imaging is routinely used for the diagnosis of ICH. Hence, the development of computer-aided tools for three-dimensional (3D) computed tomography (CT) image analysis is essential to estimate the gross volume of hematoma. We propose a methodology for automatic estimation of the hematoma volume from 3D CT volumes. Our approach integrates two different methods, multiple abstract splitting (MAS) and seeded region growing (SRG) to develop a unified hematoma detection pipeline from pre-processed CT volumes. The proposed methodology was tested on 80 cases. The volume was estimated from the delineated hematoma region, validated against the ground-truth volumes, and compared with those obtained from the conventional ABC/2 approach. We also compared our results with the U-Net model (supervised technique) to show the applicability of the proposed method. The volume calculated from manually segmented hematoma was considered the ground truth. The R 2 correlation coefficient between the volume obtained from the proposed algorithm and the ground truth is 0.86, which is equivalent to the R 2 value resulting from the comparison between the volume calculated by ABC/2 and the ground truth. The experimental results of the proposed unsupervised approach are comparable to the deep neural architecture (U-Net models). The average computation time was 132.76 ± 14 seconds. The proposed methodology provides a fast and automatic estimation of hematoma volume, which is similar to the baseline user-guided ABC/2 approach. Implementation of our method does not demand a high-end computational setup. Thus, recommended in clinical practice for computer-assistive volume estimation of hematoma from 3D CT volumes and can be implemented in a simple computer system.

Synthesizing human brain CT images from MRI with deep learning

Rapid development of artificial intelligence techniques significantly promotes important medical imaging applications such as disease diagnosis, medical image analysis and cross-modality synthesis. It is valuable to synthesize Computed Tomography (CT) scans of human brains from Magnetic Resonance Imaging (MRI) scans because CT images contain particular information for diseases such as malignant tumors, cerebrovascular malformations and aneurysms. Although there has been many studies trying to apply machine learning methods (e.g., fully convolutional neural networks and generative adversarial networks) to predict CT images based on MRI, there are still opportunities to increase the quality of synthesized CT images using the latest machine learning algorithms. In this study, we aim to synthesize high-credibility human brain CT images from MRI images using machine learning approaches. We build a dataset of both CT and MRI images of 41 patients from The Cancer Imaging Archive. A data pre-processing pipeline is designed to guarantee that the processed images are suitable as inputs to machine learning algorithms. The pipeline includes (1) pairing MRI and CT scans according to a certain time interval between CT and MRI exams of the same patient, (2) registering all MRI images to a standard MRI template, (3) registering all CT images to paired MRI images, (4) intensity normalization and (5) extracting 2D slices from 3D CT and MRI volumes. Three deep neural networks with encoder–decoder structure are selected and implemented including U-Net, U-Net++ and pix2pix to synthesize human brain CT images from MRI images. Experimental results illustrate that U-Net++ shows better performance than U-Net and pix2pix in synthesizing CT images from MRI by achieving a Mean Squared Error of 0.025, a Mean Absolute Error of 0.082 and a Peak Signal-to-Noise Ratio of 67.90, respectively. The trained machine learning models from this work can be applied in future human brain CT image prediction where CT images are absent and MRI images are available for specific patients, thereby supporting disease diagnosis based on CT images.

A Unified Multi-Phase CT Synthesis and Classification Framework for Kidney Cancer Diagnosis With Incomplete Data.

Multi-phase computed tomography (CT) is widely adopted for the diagnosis of kidney cancer due to the complementary information among phases. However, the complete set of multi-phase CT is often not available in practical clinical applications. In recent years, there have been some studies to generate the missing modality image from the available data. Nevertheless, the generated images are not guaranteed to be effective for the diagnosis task. In this paper, we propose a unified framework for kidney cancer diagnosis with incomplete multi-phase CT, which simultaneously recovers missing CT images and classifies cancer subtypes using the completed set of images. The advantage of our framework is that it encourages a synthesis model to explicitly learn to generate missing CT phases that are helpful for classifying cancer subtypes. We further incorporate lesion segmentation network into our framework to exploit lesion-level features for effective cancer classification in the whole CT volumes. The proposed framework is based on fully 3D convolutional neural networks to jointly optimize both synthesis and classification of 3D CT volumes. Extensive experiments on both in-house and external datasets demonstrate the effectiveness of our framework for the diagnosis with incomplete data compared with state-of-the-art baselines. In particular, cancer subtype classification using the completed CT data by our method achieves higher performance than the classification using the given incomplete data.

Unsupervised Domain Adaptation for Vertebrae Detection and Identification in 3D CT Volumes Using a Domain Sanity Loss.

A variety of medical computer vision applications analyze 2D slices of computed tomography (CT) scans, whereas axial slices from the body trunk region are usually identified based on their relative position to the spine. A limitation of such systems is that either the correct slices must be extracted manually or labels of the vertebrae are required for each CT scan to develop an automated extraction system. In this paper, we propose an unsupervised domain adaptation (UDA) approach for vertebrae detection and identification based on a novel Domain Sanity Loss (DSL) function. With UDA the model’s knowledge learned on a publicly available (source) data set can be transferred to the target domain without using target labels, where the target domain is defined by the specific setup (CT modality, study protocols, applied pre- and processing) at the point of use (e.g., a specific clinic with its specific CT study protocols). With our approach, a model is trained on the source and target data set in parallel. The model optimizes a supervised loss for labeled samples from the source domain and the DSL loss function based on domain-specific “sanity checks” for samples from the unlabeled target domain. Without using labels from the target domain, we are able to identify vertebra centroids with an accuracy of %. By adding only ten target labels during training the accuracy increases to %, which is on par with the current state-of-the-art for full supervised learning, while using about 20 times less labels. Thus, our model can be used to extract 2D slices from 3D CT scans on arbitrary data sets fully automatically without requiring an extensive labeling effort, contributing to the clinical adoption of medical imaging by hospitals.

A two-stage deep generative adversarial quality enhancement network for real-world 3D CT images

High-quality (HQ) three-dimensional (3D) images are the premise of analyzing the properties of porous media such as rocks. X-ray computed tomography (CT) is one of the most widely used imaging tools to capture the 3D images of rock samples. Nevertheless, the quality (e.g., resolution, sharpness, and the signal-to-noise ratio) of the collected rock CT images may not meet the needs of practical applications in some cases due to the limitations of imaging systems, leading to inaccurate results of property analysis. In this paper, aiming at improving the quality of rock CT images as well as the accuracy of property analysis, we develop a two-stage deep generative adversarial quality enhancement network for real-world 3D CT images, namely the CTQENet. More specifically, the proposed CTQENet consists of a two-dimensional (2D) reconstruction module (2DRM) and a 3D fusion module (3DFM), which enhance the quality of 3D CT images from the perspective of 2D slices and 3D volumes, respectively. In order to remove artifacts and enhance the resolution of real-world CT images, the 2DRM takes the cycle-consistent generative adversarial network as the backbone to learn the mapping from low-quality (LQ) 2D slices to HQ ones without one-to-one paired training data. Then, the 3D CT volumes stacked by the reconstructed HQ slices along the x/y/z-axis are adaptively fused in the generative adversarial network-based 3DFM, to achieve more reliable 3D morphological structures. Qualitative and quantitative comparisons show the effectiveness of the proposed CTQENet for real-world 3D CT images of rock samples. In particular, the reconstructed HQ 3D CT images by CTQENet show similar morphological characteristics and statistical properties with HQ targets. This study makes it possible to obtain higher quality 3D CT images that partly exceed the limitations of CT imaging systems for better visual experience and more accurate property analysis.

Open osteology: Medical imaging databases as skeletal collections

• Medical imaging datasets can be used as skeletal reference collections • Computed tomography data from TCIA can be accessed via 3D Slicer • Many tools in 3D Slicer support skeletal analyses and dissemination products • 3D bone models can be used for education, research, training, web-based reference • Bone modeling in 3D Slicer will support common workflows and shareable datasets The increasing availability of de-identified medical image databases, especially of computed tomography (CT) scans, presents an opportunity for “open osteology,” or the establishment of new skeletal reference collections. The number of free and/or open-source software packages for generating three-dimensional (3D) CT models, such as 3D Slicer, reduces financial obstacles to working with CT data and encourages the development of common workflows and datasets. The direct link to the Cancer Imaging Archive from 3D Slicer facilitates access to medical imaging datasets to support education and research with virtual skeletal data. Generation of 3D models enables computational methods for skeletal analyses and can also lead to the generation of virtual libraries representing large amounts of human skeletal variation. 3D printing of 3D CT models can supplement physical skeletal collections for the classroom and research beyond the standard commercially available specimens. Web-based technologies support 3D model and CT volume visualization, interaction, and measurement, increasing opportunities for dissemination and collaboration as well as the possible integration of 3D data as references for skeletal analysis tools. Increasing awareness and usage of pre-existing free and open-source resources applicable to forensic anthropology will facilitate method/workflow development, validation, and eventually standardization. This presentation will discuss online sources of skeletal data, outline methods for processing CT scans with free software into 3D digital models and discuss web-based technologies and repositories that allow interaction with 3D skeletal models. The demonstration of these methods will contribute to discussions on the expansion of virtual anthropology and open osteology.

Attention-embedded complementary-stream CNN for false positive reduction in pulmonary nodule detection

False positive reduction plays a key role in computer-aided detection systems for pulmonary nodule detection in computed tomography (CT) scans. However, this remains a challenge owing to the heterogeneity and similarity of anisotropic pulmonary nodules. In this study, a novel attention-embedded complementary-stream convolutional neural network (AECS-CNN) is proposed to obtain more representative features of nodules for false positive reduction. The proposed network comprises three function blocks: 1) attention-guided multi-scale feature extraction, 2) complementary-stream block with an attention module for feature integration, and 3) classification block. The inputs of the network are multi-scale 3D CT volumes due to variations in nodule sizes. Subsequently, a gradual multi-scale feature extraction block with an attention module was applied to acquire more contextual information regarding the nodules. A subsequent complementary-stream integration block with an attention module was utilized to learn the significantly complementary features. Finally, the candidates were classified using a fully connected layer block. An exhaustive experiment on the LUNA16 challenge dataset was conducted to verify the effectiveness and performance of the proposed network. The AECS-CNN achieved a sensitivity of 0.92 with 4 false positives per scan. The results indicate that the attention mechanism can improve the network performance in false positive reduction, the proposed AECS-CNN can learn more representative features, and the attention module can guide the network to learn the discriminated feature channels and the crucial information embedded in the data, thereby effectively enhancing the performance of the detection system.

Abstract PO-035: Development of a robust radiomic biomarker of PDL1 expression and patient survival after first-line immunotherapy for non-small cell lung cancer

Abstract Pembrolizumab (PEMBRO), a PD1antagonist, is 1st-line therapy for non-small cell lung cancer (NSCLC) without actionable mutations. While up to 70% of PDL1 enriched NSCLC respond to PEMBRO, those that will fail therapy, with resulting worse overall survival, cannot be reliably predicted. We propose a novel radiomic biomarker which integrates with PDL1 expression data to enhance precision in therapy response prediction. NSCLC patients (n=98) treated with PEMBRO at our institution, either alone or in combination with chemotherapy, with available staging computed tomography (CT) imaging were retrospectively identified. 3D tumor CT volumes were labeled by thoracic radiologists using ITK-SNAP software and radiomic features were extracted from segmented tumor volumes using PyRadiomics (Py) (107 features) and the Cancer Imaging Phenomics Toolkit (CaPTk)(102 features). The impact of imaging acquisition heterogeneity was mitigated using a nested ComBat approach, sequentially parsing parameters as batch covariates to harmonize differences in radiomic features. Harmonization reduced the number of features (KS test p < 0.05; Py: 41.67%, CaPTk: 22.4% feature reduction) significantly different by kernel resolution. Six principal components (PCs) capturing 85% of the variance from the retained robust radiomic features of each software package were extracted and combined into a prognostic model (number of predictors capped at six (deaths = 59) to avoid overfitting). The concordance index for overall survival prediction was computed using a 5-fold cross-validated (CV) Cox proportional hazards model (200 iterations). Results for the ComBat feature PCs model are (C-statistic, 95% CI): CaPTk (0.58, [0.52, 0.62]), Py (0.59, [0.53,0.63]) For patients with available PDL1 expression data (n=67, deaths= 40), we used three radiomic PCs to predict survival for tumors with ≥ 50% PDL1 expression. Results for ComBat feature PCs are (5-fold CV AUC results): CaPTk (0.68), Py (0.71). We also combined the three radiomic PCs with a binary variable indicating the presence of >50% PDL1 expression into a model. The complete dataset was used to evaluate the models’ ability to separate patients above versus below the median prognostic score in a Kaplan Meier curve (for all cases, log-rank test p values < 0.05). The five-fold cross-validated ComBat PCs model had the highest accuracy in the prediction of overall survival among all the tested models. The ComBat PCs model performance is ((5-fold cross-validated C-statistic, 95% CI): Captk (0.60, [0.51, 0.64]), Py model (0.61, [0.52,0.65])). We demonstrated that both toolkits capture similar information from the tumor imaging volume with comparable prediction modeling results. ComBat harmonizes differences in image acquisition parameters and allows the generation of a radiomic model leveraging heterogeneous imaging data typical of the standard of care CT. Combining radiomic feature analysis with tumor PDL1 expression improves NSCLC survival prediction for therapy with PEMBRO. Citation Format: Apurva Singh, Hannah Horng, Joanna Weeks, Michelle Hershman, Leonid Roshkovan, Sharyn Katz, Despina Kontos. Development of a robust radiomic biomarker of PDL1 expression and patient survival after first-line immunotherapy for non-small cell lung cancer [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-035.

Empirical greedy machine‐based automatic liver segmentation in CT images

Segmentation of the liver from 3D computed tomography volumes plays a significant role in trajectory development for computer-assisted interventional surgery for the liver disease. Despite a lot of studies, liver segmentation remains a challenging task due to the lack of clear edges on most liver boundaries coupled with high variability of both anatomical and intensity patterns. In addition, there is a problem with the segmentation of the left portal vein, in which the size of this vein prominently estimates the liver tumour area. The empirical greedy machine is proposed to make the precise, automated segmentation of the liver as well as the left portal vein. In which the empirical robust nature trains the features of the liver proficiently thereby segmenting the liver from other organs without the omission of adjacent organs and liver lobe region. Hence this proposed method can achieve one of the highest accuracies compared to other segmentation methods and the performance is calculated using several parameters such as volumetric overlap error, relative absolute volume difference (RVD), average symmetric absolute surface distance (ASD), root mean square surface distance, maximum symmetric ASD.

Iterative 3D feature enhancement network for pancreas segmentation from CT images

Automatic and accurate pancreas segmentation from 3D computed tomography volumes is a crucial prerequisite for computer-aided diagnosis, intraoperative planning and guidance. However, this is a challenging task because of the high inter-subject variability in the shape and location of the pancreas, as well as the existence of the surrounding organs. In order to address the above challenges, we propose a novel iterative 3D feature enhancement network to segment pancreas accurately. Specifically, the multi-level integrated features and the individual features at different levels can be progressively enhanced in an iterative manner by leveraging the complementary information encoded in different features. Therefore, the non-pancreas information at lower layers can be suppressed, and the fine details of pancreas at higher layers can be increased. In addition, because the pancreas region occupies only a small part of the scan, in order to prevent the final predictions from being biased toward the background class, we design the Dice similarity coefficients loss function in the training phase to mitigate this issue. Meanwhile, deep supervision with auxiliary classifier is incorporated in the intermediate layers at each iteration to guide the back-propagation of gradient flows and boost the discriminative capability at lower layers. Finally, in order to verify the effectiveness of the proposed method, we evaluated our approach on the publicly available NIH pancreas segmentation dataset. Extensive experiments illustrate that the proposed method achieves better performance than the state-of-the-art algorithms, and it can be easily applied to other volumetric image segmentation tasks.

Deep Learning Cross-Phase Style Transfer for Motion Artifact Correction in Coronary Computed Tomography Angiography

Motion artifacts may occur in coronary computed tomography angiography (CCTA) due to the heartbeat and impede the clinician's diagnosis of coronary arterial diseases. Thus, motion artifact correction of the coronary artery is required to quantify the risk of disease more accurately. We present a novel method based on deep learning for motion artifact correction in CCTA. Because the image of the coronary artery without motion (the ground-truth data required in supervised deep learning) is medically unattainable, we apply a style transfer method to 2D image patches cropped from full-phase 4D computed tomography (CT) to synthesize these images. We then train a convolutional neural network (CNN) for motion artifact correction using this synthetic ground-truth (SynGT). During testing, the output motion-corrected 2D image patches of the trained network are reinserted into the 3D CT volume with volumetric interpolation. The proposed method is evaluated using both phantom and clinical data. A phantom study demonstrates comparable results to other methods in quantitative performance and outperforms those methods in computation time. For clinical data, a quantitative analysis based on metric measurements is presented that confirms the correction of motion artifacts. Moreover, an observer study finds that by applying the proposed method, motion artifacts are markedly reduced, and boundaries of the coronary artery are much sharper, with a strong inter-observer agreement (κ = 0.78). Finally, evaluations using commercial software on the original and resulting CT volumes of the proposed method reveal a considerable increase in tracked coronary artery length.

Nonrigid Medical Image Registration Using an Information Theoretic Measure Based on Arimoto Entropy with Gradient Distributions.

This paper introduces a new nonrigid registration approach for medical images applying an information theoretic measure based on Arimoto entropy with gradient distributions. A normalized dissimilarity measure based on Arimoto entropy is presented, which is employed to measure the independence between two images. In addition, a regularization term is integrated into the cost function to obtain the smooth elastic deformation. To take the spatial information between voxels into account, the distance of gradient distributions is constructed. The goal of nonrigid alignment is to find the optimal solution of a cost function including a dissimilarity measure, a regularization term, and a distance term between the gradient distributions of two images to be registered, which would achieve a minimum value when two misaligned images are perfectly registered using limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) optimization scheme. To evaluate the test results of our presented algorithm in non-rigid medical image registration, experiments on simulated three-dimension (3D) brain magnetic resonance imaging (MR) images, real 3D thoracic computed tomography (CT) volumes and 3D cardiac CT volumes were carried out on elastix package. Comparison studies including mutual information (MI) and the approach without considering spatial information were conducted. These results demonstrate a slight improvement in accuracy of non-rigid registration.

Extraction of open-state mitral valve geometry from CT volumes.

The importance of mitral valve therapies is rising due to an aging population. Visualization and quantification of the valve anatomy from image acquisitions is an essential component of surgical and interventional planning. The segmentation of the mitral valve from computed tomography (CT) acquisitions is challenging due to high variation in appearance and visibility across subjects. We present a novel semi-automatic approach to segment the open-state valve in 3D CT volumes that combines user-defined landmarks to an initial valve model which is automatically adapted to the image information, even if the image data provide only partial visibility of the valve. Context information and automatic view initialization are derived from segmentation of the left heart lumina, which incorporates topological, shape and regional information. The valve model is initialized with user-defined landmarks in views generated from the context segmentation and then adapted to the image data in an active surface approach guided by landmarks derived from sheetness analysis. The resulting model is refined by user landmarks. For evaluation, three clinicians segmented the open valve in 10 CT volumes of patients with mitral valve insufficiency. Despite notable differences in landmark definition, the resulting valve meshes were overall similar in appearance, with a mean surface distance of [Formula: see text] mm. Each volume could be segmented in 5-22min. Our approach enables an expert user to easily segment the open mitral valve in CT data, even when image noise or low contrast limits the visibility of the valve.

Non-invasive predictive model for hepatic venous pressure gradient based on a 3-dimensional computed tomography volume rendering technology.

Portal hypertension secondary to liver cirrhosis may cause a number of life-threatening complications. The rupture of gastroesophageal varices is associated with a high mortality rate of 15–30%. Hepatic venous pressure gradient (HVPG) is an accurate reflection of disease severity, however this can only be assessed via an invasive interventional procedure. The aim of the present study was to explore a non-invasive method based on 3D computed tomography (CT) volume rendering technology to accurately predict HVPG. A total of 77 patients diagnosed with liver cirrhosis underwent HVPG examination in the present study and the appropriate clinical and radiological data were retrospectively reviewed. A 3D liver and spleen volume rendering was constructed for volume measurements. All non-invasive parameters were tested using univariate analysis and the resulting variables that were statistically significant (P<0.20) were used in the multivariate linear regression model. The HVPG predictive model was as follows: HVPG = 18.726 - 0.324 (albumin) + 1.57 (aminotransferase-to-platelet ratio index) + 0.004 (liver volume) (multivariate regression analysis, P=0.006). The corresponding area under receiver operating characteristic curve to identify clinically significant portal hypertension defined as HVPG ≥10 mmHg was 0.810 (95% confidence interval; 0.705–0.891), with an optimal cut-off value of 12.84, yielding a sensitivity of 80.36% a specificity of 76.19%. The results of the present study indicate that 3D CT volume rendering technology may have the potential to be used for non-invasive prediction of HVPG.

Computer assisted electromagnetic navigation improves accuracy in computed tomography guided interventions: A prospective randomized clinical trial.

PurposeTo assess the accuracy and usability of an electromagnetic navigation system designed to assist Computed Tomography (CT) guided interventions.Materials and methods120 patients requiring a percutaneous CT intervention (drainage, biopsy, tumor ablation, infiltration, sympathicolysis) were included in this prospective randomized trial. Nineteen radiologists participated. Conventional procedures (CT group) were compared with procedures assisted by a navigation system prototype using an electromagnetic localizer to track the position and orientation of a needle holder (NAV group). The navigation system displays the needle path in real-time on 2D reconstructed CT images extracted from the 3D CT volume. The regional ethics committee approved this study and all patients gave written informed consent. The main outcome was the distance between the planned trajectory and the achieved needle trajectory calculated from the initial needle placement.Results120 patients were analyzable in intention-to-treat (NAV: 60; CT: 60). Accuracy improved when the navigation system was used: distance error (in millimeters: median[P25%; P75%]) with NAV = 4.1[2.7; 9.1], vs. with CT = 8.9[4.9; 15.1] (p<0.001). After the initial needle placement and first control CT, fewer subsequent CT acquisitions were necessary to reach the target using the navigation system: NAV = 2[2; 3]; CT = 3[2; 4] (p = 0.01).ConclusionThe tested system was usable in a standard clinical setting and provided significant improvement in accuracy; furthermore, with the help of navigation, targets could be reached with fewer CT control acquisitions.

Automatical Cranial Suture Detection based on Thresholding Method

Purpose The head of infants under 24 months old who has Craniosynostosis grows extraordinarily that makes head shape unusual. To diagnose the Craniosynostosis, surgeon has to inspect computed tomography(CT) images of the patient in person. It's very time consuming process. Moreover, without a surgeon, it's difficult to diagnose the Craniosynostosis. Therefore, we developed technique which detects Craniosynostosis automatically from the CT volume. Materials and Methods At first, rotation correction is performed to the 3D CT volume for detection of the Craniosynostosis. Then, cranial area is extracted using the iterative thresholding method we proposed. Lastly, we diagnose Craniosynostosis by analyzing centroid relationships of clusters of cranial bone which was divided by cranial suture. Results Using this automatical cranial detection technique, we can diagnose Craniosynostosis correctly. The proposed method resulted in 100% sensitivity and 90% specificity. The method perfectly diagnosed abnormal patients. Conclusion By plugging-in the software on CT machine, it will be able to warn the possibility of Craniosynostosis. It is expected that early treatment of Craniosynostosis would be possible with our proposed algorithm.

Personalized Graphical Models for Anatomical Landmark Localization in Whole-Body Medical Images

The goal of this work is to accurately and reliably localize anatomical landmarks in 3D Computed Tomography (CT) scans of the upper bodies of cancer patients even in the presence of pathologies and imaging artifacts that may markedly change the appearances of anatomical structures. We propose a method based on dense matching of parts-based graphical models. For landmark localization, we replace population averaged models by personalized models that are adapted to each test image at runtime. We do so by jointly leveraging weighted combinations of labeled training exemplars. We report results for localizing standard anatomical landmarks in clinical 3D CT volumes, using a database of 83 lung cancer patients. We compare our method against both (baseline) population averaged graphical models and against atlas-based deformable registration and show the method is in each case able to localize landmarks with significantly improved reliability and accuracy.

A palaeobiologist's guide to 'virtual' micro-CT preparation

This paper provides a brief but comprehensive guide to creating, preparing and dissecting a ‘virtual’ fossil, using a worked example to demonstrate some standard data processing techniques. Computed tomography (CT) is a 3D imaging modality for producing ‘virtual’ models of an object on a computer. In the last decade, CT technology has greatly improved, allowing bigger and denser objects to be scanned increasingly rapidly. The technique has now reached a stage where systems can facilitate large-scale, non-destructive comparative studies of extinct fossils and their living relatives. Consequently the main limiting factor in CT-based analyses is no longer scanning, but the hurdles of data processing (see disclaimer). The latter comprises the techniques required to convert a 3D CT volume (stack of digital slices) into a virtual image of the fossil that can be prepared (separated) from the matrix and ‘dissected’ into its anatomical parts. This technique can be applied to specimens or part of specimens embedded in the rock matrix that until now have been otherwise impossible to visualise. This paper presents a suggested workflow explaining the steps required, using as example a fossil tooth of Sphenacanthus hybodoides (Egerton), a shark from the Late Carboniferous of England. The original NHMUK copyrighted CT slice stack can be downloaded for practice of the described techniques, which include segmentation, rendering, movie animation, stereo-anaglyphy, data storage and dissemination. Fragile, rare specimens and type materials in university and museum collections can therefore be virtually processed for a variety of purposes, including virtual loans, website illustrations, publications and digital collections. Micro-CT and other 3D imaging techniques are increasingly utilized to facilitate data sharing among scientists and on education and outreach projects. Hence there is the potential to usher in a new era of global scientific collaboration and public communication using specimens in museum collections. Richard Leslie Abel, MSK Laboratory, Department of Surgery and Cancer, Charring Cross Hospital, Imperial College, W6 8RF London, United Kingdom. richard.abel@imperil.ac.uk and Image and Analysis Centre, Mineralogy Department, Natural History Museum, Cromwell Road, SW7 5BD London, United Kingdom. Carolina Rettondini Laurini, Laboratorio de Paleontologia Departamento de Biologia FFCLRP USP, Av. Bandeirantes, 3900 CEP 14040-901, Bairro Monte Alegre, Ribeirao Preto, SP, Brazil. xirra.carolina@gmail.com PE Article Number: 15.2.6T Copyright: Palaeontological Association May 2012 Submission: 12 May 2011. Acceptance: 25 April 2012 Abel, Richard Leslie, Laurini, Carolina Rettondini, and Richter, Martha 2012. A palaeobiologist’s guide to ‘virtual’ micro-CT preparation. Palaeontologia Electronica Vol. 15, Issue 2;6T,17p; palaeo-electronica.org/content/issue-2-2012-technical-articles/233-micro-ct-workflow ABEL ET AL.: MICRO-CT WORKFLOW Martha Richter, Department of Palaeontology, Natural History Museum, Cromwell Road, SW7 5BD London, United Kingdom. m.richter@nhm.ac.uk