Dataset Information

Image Decomposition Algorithm for Dual-Energy Computed Tomography via Fully Convolutional Network.

ABSTRACT:

Background

Dual-energy computed tomography (DECT) has been widely used due to improved substances identification from additional spectral information. The quality of material-specific image produced by DECT attaches great importance to the elaborated design of the basis material decomposition method.

Objective

The aim of this work is to develop and validate a data-driven algorithm for the image-based decomposition problem.

Methods

A deep neural net, consisting of a fully convolutional net (FCN) and a fully connected net, is proposed to solve the material decomposition problem. The former net extracts the feature representation of input reconstructed images, and the latter net calculates the decomposed basic material coefficients from the joint feature vector. The whole model was trained and tested using a modified clinical dataset.

Results

The proposed FCN delivers image with about 60% smaller bias and 70% lower standard deviation than the competing algorithms, suggesting its better material separation capability. Moreover, FCN still yields excellent performance in case of photon noise.

Conclusions

Our deep cascaded network features high decomposition accuracies and noise robust property. The experimental results have shown the strong function fitting ability of the deep neural network. Deep learning paradigm could be a promising way to solve the nonlinear problem in DECT.

SUBMITTER: Xu Y

PROVIDER: S-EPMC6145159 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Image Decomposition Algorithm for Dual-Energy Computed Tomography via Fully Convolutional Network.

Xu Yifu Y Yan Bin B Zhang Jingfang J Chen Jian J Zeng Lei L Wang Linyuang L

Computational and mathematical methods in medicine 20180905

<h4>Background</h4>Dual-energy computed tomography (DECT) has been widely used due to improved substances identification from additional spectral information. The quality of material-specific image produced by DECT attaches great importance to the elaborated design of the basis material decomposition method.<h4>Objective</h4>The aim of this work is to develop and validate a data-driven algorithm for the image-based decomposition problem.<h4>Methods</h4>A deep neural net, consisting of a fully co ...[more]

PMID: 30254689

Similar Datasets

Project description:BackgroundMulti-energy computed tomography (CT) provides multiple channel-wise reconstructed images, and they can be used for material identification and k-edge imaging. Nonetheless, the projection datasets are frequently corrupted by various noises (e.g., electronic, Poisson) in the acquisition process, resulting in lower signal-noise-ratio (SNR) measurements. Multi-energy CT images have local sparsity, nonlocal self-similarity in spatial dimension, and correlation in spectral dimension.MethodsIn this paper, we propose an image-spectral decomposition extended-learning assisted by sparsity (IDEAS) method to fully exploit these intrinsic priors for multi-energy CT image reconstruction. Particularly, a nonlocal low-rank Tucker decomposition (TD) is employed to utilize the correlation and nonlocal self-similarity priors. Moreover, considering the advantages of multi-task tensor dictionary learning (TDL) in sparse representation, an adaptive spatial dictionary and an adaptive spectral dictionary are trained during the iterative reconstruction process. Furthermore, a weighted total variation (TV) regularization term is employed to encourage local sparsity.ResultsNumerical simulation, physical phantom, and preclinical mouse experiments are performed to validate the proposed IDEAS algorithm. Specifically, in the simulation experiments, the proposed IDEAS reconstructed high-quality images that are very close to the references. For example, the root mean square error (RMSE) of IDEAS image in energy bin 1 is as low as 0.0672, while the RMSE of other methods are higher than 0.0843. Besides, the structural similarity (SSIM) of IDEAS reconstructed image in energy bin 1 is greater than 0.98. For material decomposition, the RMSE of IDEAS bone component is as low as 0.0152, and other methods are higher than 0.0199. In addition, the computational cost of IDEAS is as low as 98.8 s for one iteration, and the competing tensor decomposition method is higher than 327 s.ConclusionsTo further improve the quality of the reconstructed multi-energy CT images, multiple prior regularizations are introduced to the multi-energy CT reconstructed model, leading to an IDEAS method. Both qualitative and quantitative evaluation of our results confirm the outstanding performance of the proposed algorithm compared to the state-of-the-arts.

Project description:BackgroundMany patients with malignant tumors require chemotherapy and radiation therapy, which can result in a decline in physical function and potentially influence bone mineral density (BMD). Furthermore, these treatments necessitate enhanced computed tomography (CT) scans for determining disease staging or treatment outcomes, and opportunistic screening with available imaging data is beneficial for patients at high risk for osteoporosis if existing imaging data can be used. The study aimed to investigate the feasibility of opportunistic screening for osteoporosis using enhanced CT based on a dual-energy CT (DECT) material decomposition technique.MethodsWe prospectively enrolled 346 consecutive patients who underwent abdominal unenhanced and triphasic contrast-enhanced CT (arterial, portal venous, and delayed phases) between June 2021 and June 2022. The BMD, and the density of hydroxyapatite (HAP) on HAP-iodine images and calcium (Ca) on Ca-iodine images were measured on the L1-L3 vertebral bodies. The iodine intake was recorded. Pearson analysis was conducted to assess the correlation between iodine intake and the density values in three phases and the correlation between BMD and the densities of HAP and Ca. Furthermore, linear regression was employed for quantitative evaluation. Bland-Altman analysis was used to evaluate the agreement between calculated BMD derived from DECT (BMD-DECT) and reference BMD derived from quantitative CT (BMD-QCT). Receiver operating characteristic (ROC) analysis was applied to assess the diagnostic efficacy.ResultsThe HAP and Ca density of the L1-L3 vertebral bodies did not differ significantly among the three phases of contrast-enhanced CT (F=0.001-0.049; P>0.05). Significant positive correlations were found between HAP, Ca densities, and BMD (HAP-BMD: r=0.9472, R2=0.8973; Ca-BMD: r=0.9470, R2=0.8968; all P<0.001). Bland-Altman plots showed high agreement between BMD-DECT and BMD-QCT. The area under the curve (AUC) using HAP and Ca measurements was 0.963 [95% confidence interval (CI): 0.937-0.980] and 0.964 (95% CI: 0.939-0.981), respectively, for diagnosing osteoporosis and was 0.951 (95% CI: 0.917-0.973) and 0.950 (95% CI: 0.916-0.973), respectively, for diagnosing osteopenia.ConclusionsThe HAP and Ca density measurements generated through the material decomposition technique in DECT have good diagnostic performances in assessing BMD, which offers a new perspective for opportunistic screening of osteoporosis on contrast-enhanced CT.

Project description:Cardiac computed tomography angiography (CTA) is an emerging imaging modality for assessing coronary artery as well as various cardiovascular structures. Recently, deep learning (DL) methods have been successfully applied to many applications of medical image analysis including cardiac CTA structure segmentation. However, DL requires a large amounts of data and high-quality labels for training which can be burdensome to obtain due to its labor-intensive nature. In this study, we aim to develop a fully automatic artificial intelligence (AI) system, named DeepHeartCT, for accurate and rapid cardiac CTA segmentation based on DL. The proposed system was trained using a large clinical dataset with computer-generated labels to segment various cardiovascular structures including left and right ventricles (LV, RV), left and right atria (LA, RA), and LV myocardium (LVM). This new system was trained directly using high-quality computer labels generated from our previously developed multi-atlas based AI system. In addition, a reverse ranking strategy was proposed to assess the segmentation quality in the absence of manual reference labels. This strategy allowed the new framework to assemble optimal computer-generated labels from a large dataset for effective training of a deep convolutional neural network (CNN). A large clinical cardiac CTA studies (n = 1,064) were used to train and validate our framework. The trained model was then tested on another independent dataset with manual labels (n = 60). The Dice score, Hausdorff distance and mean surface distance were used to quantify the segmentation accuracy. The proposed DeepHeartCT framework yields a high median Dice score of 0.90 [interquartile range (IQR), 0.90-0.91], a low median Hausdorff distance of 7 mm (IQR, 4-15 mm) and a low mean surface distance of 0.80 mm (IQR, 0.57-1.29 mm) across all segmented structures. An additional experiment was conducted to evaluate the proposed DL-based AI framework trained with a small vs. large dataset. The results show our framework also performed well when trained on a small optimal training dataset (n = 110) with a significantly reduced training time. These results demonstrated that the proposed DeepHeartCT framework provides accurate and rapid cardiac CTA segmentation that can be readily generalized for handling large-scale medical imaging applications.

Project description:PurposeThe deformable nature of the liver can make focal treatment challenging and is not adequately addressed with simple rigid registration techniques. More advanced registration techniques can take deformations into account (eg, biomechanical modeling) but require segmentations of the whole liver for each scan, which is a time-intensive process. We hypothesize that fully convolutional networks can be used to rapidly and accurately autosegment the liver, removing the temporal bottleneck for biomechanical modeling.Methods and materialsManual liver segmentations on computed tomography scans from 183 patients treated at our institution and 30 scans from the Medical Image Computing & Computer Assisted Intervention challenges were collected for this study. Three architectures were investigated for rapid automated segmentation of the liver (VGG-16, DeepLabv3 +, and a 3-dimensional UNet). Fifty-six cases were set aside as a final test set for quantitative model evaluation. Accuracy of the autosegmentations was assessed using Dice similarity coefficient and mean surface distance. Qualitative evaluation was also performed by 3 radiation oncologists on 50 independent cases with previously clinically treated liver contours.ResultsThe mean (minimum-maximum) mean surface distance for the test groups with the final model, DeepLabv3 +, were as follows: μContrast(N = 17): 0.99 mm (0.47-2.2), μNon_Contrast(N = 19)l: 1.12 mm (0.41-2.87), and μMiccai(N = 30)t: 1.48 mm (0.82-3.96). The qualitative evaluation showed that 30 of 50 autosegmentations (60%) were preferred to manual contours (majority voting) in a blinded comparison, and 48 of 50 autosegmentations (96%) were deemed clinically acceptable by at least 1 reviewing physician.ConclusionsThe autosegmentations were preferred compared with manually defined contours in the majority of cases. The ability to rapidly segment the liver with high accuracy achieved in this investigation has the potential to enable the efficient integration of biomechanical model-based registration into a clinical workflow.

Dataset Information

Image Decomposition Algorithm for Dual-Energy Computed Tomography via Fully Convolutional Network.

Background

Objective

Methods

Results

Conclusions

Publications

Image Decomposition Algorithm for Dual-Energy Computed Tomography via Fully Convolutional Network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets