skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: MO-DE-207A-09: Low-Dose CT Image Reconstruction Via Learning From Different Patient Normal-Dose Images

Abstract

Purpose: To investigate a novel low-dose CT (LdCT) image reconstruction strategy for lung CT imaging in radiation therapy. Methods: The proposed approach consists of four steps: (1) use the traditional filtered back-projection (FBP) method to reconstruct the LdCT image; (2) calculate structure similarity (SSIM) index between the FBP-reconstructed LdCT image and a set of normal-dose CT (NdCT) images, and select the NdCT image with the highest SSIM as the learning source; (3) segment the NdCT source image into lung and outside tissue regions via simple thresholding, and adopt multiple linear regression to learn high-order Markov random field (MRF) pattern for each tissue region in the NdCT source image; (4) segment the FBP-reconstructed LdCT image into lung and outside regions as well, and apply the learnt MRF prior in each tissue region for statistical iterative reconstruction of the LdCT image following the penalized weighted least squares (PWLS) framework. Quantitative evaluation of the reconstructed images was based on the signal-to-noise ratio (SNR), local binary pattern (LBP) and histogram of oriented gradients (HOG) metrics. Results: It was observed that lung and outside tissue regions have different MRF patterns predicted from the NdCT. Visual inspection showed that our method obviously outperformed the traditional FBPmore » method. Comparing with the region-smoothing PWLS method, our method has, in average, 13% increase in SNR, 15% decrease in LBP difference, and 12% decrease in HOG difference from reference standard for all regions of interest, which indicated the superior performance of the proposed method in terms of image resolution and texture preservation. Conclusion: We proposed a novel LdCT image reconstruction method by learning similar image characteristics from a set of NdCT images, and the to-be-learnt NdCT image does not need to be scans from the same subject. This approach is particularly important for enhancing image quality in radiation therapy.« less

Authors:
;  [1];  [2]
  1. Stanford University, Palo Alto, CA (United States)
  2. Stony Brook University, Stony Brook, NY (United States)
Publication Date:
OSTI Identifier:
22649551
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 43; Journal Issue: 6; Other Information: (c) 2016 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 61 RADIATION PROTECTION AND DOSIMETRY; ANIMAL TISSUES; BIOMEDICAL RADIOGRAPHY; COMPUTERIZED TOMOGRAPHY; IMAGE PROCESSING; ITERATIVE METHODS; LEARNING; LUNGS; PLANT TISSUES; SIGNAL-TO-NOISE RATIO

Citation Formats

Han, H, Xing, L, and Liang, Z. MO-DE-207A-09: Low-Dose CT Image Reconstruction Via Learning From Different Patient Normal-Dose Images. United States: N. p., 2016. Web. doi:10.1118/1.4957237.
Han, H, Xing, L, & Liang, Z. MO-DE-207A-09: Low-Dose CT Image Reconstruction Via Learning From Different Patient Normal-Dose Images. United States. doi:10.1118/1.4957237.
Han, H, Xing, L, and Liang, Z. 2016. "MO-DE-207A-09: Low-Dose CT Image Reconstruction Via Learning From Different Patient Normal-Dose Images". United States. doi:10.1118/1.4957237.
@article{osti_22649551,
title = {MO-DE-207A-09: Low-Dose CT Image Reconstruction Via Learning From Different Patient Normal-Dose Images},
author = {Han, H and Xing, L and Liang, Z},
abstractNote = {Purpose: To investigate a novel low-dose CT (LdCT) image reconstruction strategy for lung CT imaging in radiation therapy. Methods: The proposed approach consists of four steps: (1) use the traditional filtered back-projection (FBP) method to reconstruct the LdCT image; (2) calculate structure similarity (SSIM) index between the FBP-reconstructed LdCT image and a set of normal-dose CT (NdCT) images, and select the NdCT image with the highest SSIM as the learning source; (3) segment the NdCT source image into lung and outside tissue regions via simple thresholding, and adopt multiple linear regression to learn high-order Markov random field (MRF) pattern for each tissue region in the NdCT source image; (4) segment the FBP-reconstructed LdCT image into lung and outside regions as well, and apply the learnt MRF prior in each tissue region for statistical iterative reconstruction of the LdCT image following the penalized weighted least squares (PWLS) framework. Quantitative evaluation of the reconstructed images was based on the signal-to-noise ratio (SNR), local binary pattern (LBP) and histogram of oriented gradients (HOG) metrics. Results: It was observed that lung and outside tissue regions have different MRF patterns predicted from the NdCT. Visual inspection showed that our method obviously outperformed the traditional FBP method. Comparing with the region-smoothing PWLS method, our method has, in average, 13% increase in SNR, 15% decrease in LBP difference, and 12% decrease in HOG difference from reference standard for all regions of interest, which indicated the superior performance of the proposed method in terms of image resolution and texture preservation. Conclusion: We proposed a novel LdCT image reconstruction method by learning similar image characteristics from a set of NdCT images, and the to-be-learnt NdCT image does not need to be scans from the same subject. This approach is particularly important for enhancing image quality in radiation therapy.},
doi = {10.1118/1.4957237},
journal = {Medical Physics},
number = 6,
volume = 43,
place = {United States},
year = 2016,
month = 6
}
  • Purpose: Spectral CT enabled by an energy-resolved photon-counting detector outperforms conventional CT in terms of material discrimination, contrast resolution, etc. One reconstruction method for spectral CT is to generate a color image from a reconstructed component in each energy channel. However, given the radiation dose, the number of photons in each channel is limited, which will result in strong noise in each channel and affect the final color reconstruction. Here we propose a novel dictionary learning method for spectral CT that combines dictionary-based sparse representation method and the patch based low-rank constraint to simultaneously improve the reconstruction in each channelmore » and to address the inter-channel correlations to further improve the reconstruction. Methods: The proposed method has two important features: (1) guarantee of the patch based sparsity in each energy channel, which is the result of the dictionary based sparse representation constraint; (2) the explicit consideration of the correlations among different energy channels, which is realized by patch-by-patch nuclear norm-based low-rank constraint. For each channel, the dictionary consists of two sub-dictionaries. One is learned from the average of the images in all energy channels, and the other is learned from the average of the images in all energy channels except the current channel. With average operation to reduce noise, these two dictionaries can effectively preserve the structural details and get rid of artifacts caused by noise. Combining them together can express all structural information in current channel. Results: Dictionary learning based methods can obtain better results than FBP and the TV-based method. With low-rank constraint, the image quality can be further improved in the channel with more noise. The final color result by the proposed method has the best visual quality. Conclusion: The proposed method can effectively improve the image quality of low-dose spectral CT. This work is partially supported by the National Natural Science Foundation of China (No. 61302136), and the Natural Science Basic Research Plan in Shaanxi Province of China (No. 2014JQ8317).« less
  • Purpose: To develop an automated technique for estimating patient-specific regional imparted energy and dose from tube current modulated (TCM) computed tomography (CT) exams across a diverse set of head and body protocols. Methods: A library of 58 adult computational anthropomorphic extended cardiac-torso (XCAT) phantoms were used to model a patient population. A validated Monte Carlo program was used to simulate TCM CT exams on the entire library of phantoms for three head and 10 body protocols. The net imparted energy to the phantoms, normalized by dose length product (DLP), and the net tissue mass in each of the scan regionsmore » were computed. A knowledgebase containing relationships between normalized imparted energy and scanned mass was established. An automated computer algorithm was written to estimate the scanned mass from actual clinical CT exams. The scanned mass estimate, DLP of the exam, and knowledgebase were used to estimate the imparted energy to the patient. The algorithm was tested on 20 chest and 20 abdominopelvic TCM CT exams. Results: The normalized imparted energy increased with increasing kV for all protocols. However, the normalized imparted energy was relatively unaffected by the strength of the TCM. The average imparted energy was 681 ± 376 mJ for abdominopelvic exams and 274 ± 141 mJ for chest exams. Overall, the method was successful in providing patientspecific estimates of imparted energy for 98% of the cases tested. Conclusion: Imparted energy normalized by DLP increased with increasing tube potential. However, the strength of the TCM did not have a significant effect on the net amount of energy deposited to tissue. The automated program can be implemented into the clinical workflow to provide estimates of regional imparted energy and dose across a diverse set of clinical protocols.« less
  • Purpose: Respiratory-correlated cone-beam CT (4DCBCT) images acquired immediately prior to treatment have the potential to represent patient motion patterns and anatomy during treatment, including both intra- and inter-fractional changes. We develop a method to generate patient-specific motion models based on 4DCBCT images acquired with existing clinical equipment and used to generate time varying volumetric images (3D fluoroscopic images) representing motion during treatment delivery. Methods: Motion models are derived by deformably registering each 4DCBCT phase to a reference phase, and performing principal component analysis (PCA) on the resulting displacement vector fields. 3D fluoroscopic images are estimated by optimizing the resulting PCAmore » coefficients iteratively through comparison of the cone-beam projections simulating kV treatment imaging and digitally reconstructed radiographs generated from the motion model. Patient and physical phantom datasets are used to evaluate the method in terms of tumor localization error compared to manually defined ground truth positions. Results: 4DCBCT-based motion models were derived and used to generate 3D fluoroscopic images at treatment time. For the patient datasets, the average tumor localization error and the 95th percentile were 1.57 and 3.13 respectively in subsets of four patient datasets. For the physical phantom datasets, the average tumor localization error and the 95th percentile were 1.14 and 2.78 respectively in two datasets. 4DCBCT motion models are shown to perform well in the context of generating 3D fluoroscopic images due to their ability to reproduce anatomical changes at treatment time. Conclusion: This study showed the feasibility of deriving 4DCBCT-based motion models and using them to generate 3D fluoroscopic images at treatment time in real clinical settings. 4DCBCT-based motion models were found to account for the 3D non-rigid motion of the patient anatomy during treatment and have the potential to localize tumor and other patient anatomical structures at treatment time even when inter-fractional changes occur. This project was supported, in part, through a Master Research Agreement with Varian Medical Systems, Inc., Palo Alto, CA. The project was also supported, in part, by Award Number R21CA156068 from the National Cancer Institute.« less
  • Purpose: We develop a method to generate time varying volumetric images (3D fluoroscopic images) using patient-specific motion models derived from four-dimensional cone-beam CT (4DCBCT). Methods: Motion models are derived by selecting one 4DCBCT phase as a reference image, and registering the remaining images to it. Principal component analysis (PCA) is performed on the resultant displacement vector fields (DVFs) to create a reduced set of PCA eigenvectors that capture the majority of respiratory motion. 3D fluoroscopic images are generated by optimizing the weights of the PCA eigenvectors iteratively through comparison of measured cone-beam projections and simulated projections generated from the motionmore » model. This method was applied to images from five lung-cancer patients. The spatial accuracy of this method is evaluated by comparing landmark positions in the 3D fluoroscopic images to manually defined ground truth positions in the patient cone-beam projections. Results: 4DCBCT motion models were shown to accurately generate 3D fluoroscopic images when the patient cone-beam projections contained clearly visible structures moving with respiration (e.g., the diaphragm). When no moving anatomical structure was clearly visible in the projections, the 3D fluoroscopic images generated did not capture breathing deformations, and reverted to the reference image. For the subset of 3D fluoroscopic images generated from projections with visibly moving anatomy, the average tumor localization error and the 95th percentile were 1.6 mm and 3.1 mm respectively. Conclusion: This study showed that 4DCBCT-based 3D fluoroscopic images can accurately capture respiratory deformations in a patient dataset, so long as the cone-beam projections used contain visible structures that move with respiration. For clinical implementation of 3D fluoroscopic imaging for treatment verification, an imaging field of view (FOV) that contains visible structures moving with respiration should be selected. If no other appropriate structures are visible, the images should include the diaphragm. This project was supported, in part, through a Master Research Agreement with Varian Medical Systems, Inc, Palo Alto, CA.« less
  • Purpose: While 4DCT provides organ/tumor motion information, it often samples data over 10–20 breathing cycles. For patients presenting with compromised pulmonary function, breathing patterns can change over the acquisition time, potentially leading to tumor delineation discrepancies. This work introduces a novel adaptive velocity-modulated binning (AVB) 4DCT algorithm that modulates the reconstruction based on the respiratory waveform, yielding a patient-specific 4DCT solution. Methods: AVB was implemented in a research reconstruction configuration. After filtering the respiratory waveform, the algorithm examines neighboring data to a phase reconstruction point and the temporal gate is widened until the difference between the reconstruction point and waveformmore » exceeds a threshold value—defined as percent difference between maximum/minimum waveform amplitude. The algorithm only impacts reconstruction if the gate width exceeds a set minimum temporal width required for accurate reconstruction. A sensitivity experiment of threshold values (0.5, 1, 5, 10, and 12%) was conducted to examine the interplay between threshold, signal to noise ratio (SNR), and image sharpness for phantom and several patient 4DCT cases using ten-phase reconstructions. Individual phase reconstructions were examined. Subtraction images and regions of interest were compared to quantify changes in SNR. Results: AVB increased signal in reconstructed 4DCT slices for respiratory waveforms that met the prescribed criteria. For the end-exhale phases, where the respiratory velocity is low, patient data revealed a threshold of 0.5% demonstrated increased SNR in the AVB reconstructions. For intermediate breathing phases, threshold values were required to be >10% to notice appreciable changes in CT intensity with AVB. AVB reconstructions exhibited appreciably higher SNR and reduced noise in regions of interest that were photon deprived such as the liver. Conclusion: We demonstrated that patient-specific velocity-based 4DCT reconstruction is feasible. Image noise was reduced with AVB, suggesting potential applications for low-dose acquisitions and to improve 4DCT reconstruction for irregular breathing patients. The submitting institution holds research agreements with Philips Healthcare.« less