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

Title: Prediction of standard-dose brain PET image by using MRI and low-dose brain [{sup 18}F]FDG PET images

Abstract

Purpose: Positron emission tomography (PET) is a nuclear medical imaging technology that produces 3D images reflecting tissue metabolic activity in human body. PET has been widely used in various clinical applications, such as in diagnosis of brain disorders. High-quality PET images play an essential role in diagnosing brain diseases/disorders. In practice, in order to obtain high-quality PET images, a standard-dose radionuclide (tracer) needs to be used and injected into a living body. As a result, it will inevitably increase the patient’s exposure to radiation. One solution to solve this problem is predicting standard-dose PET images using low-dose PET images. As yet, no previous studies with this approach have been reported. Accordingly, in this paper, the authors propose a regression forest based framework for predicting a standard-dose brain [{sup 18}F]FDG PET image by using a low-dose brain [{sup 18}F]FDG PET image and its corresponding magnetic resonance imaging (MRI) image. Methods: The authors employ a regression forest for predicting the standard-dose brain [{sup 18}F]FDG PET image by low-dose brain [{sup 18}F]FDG PET and MRI images. Specifically, the proposed method consists of two main steps. First, based on the segmented brain tissues (i.e., cerebrospinal fluid, gray matter, and white matter) in the MRImore » image, the authors extract features for each patch in the brain image from both low-dose PET and MRI images to build tissue-specific models that can be used to initially predict standard-dose brain [{sup 18}F]FDG PET images. Second, an iterative refinement strategy, via estimating the predicted image difference, is used to further improve the prediction accuracy. Results: The authors evaluated their algorithm on a brain dataset, consisting of 11 subjects with MRI, low-dose PET, and standard-dose PET images, using leave-one-out cross-validations. The proposed algorithm gives promising results with well-estimated standard-dose brain [{sup 18}F]FDG PET image and substantially enhanced image quality of low-dose brain [{sup 18}F]FDG PET image. Conclusions: In this paper, the authors propose a framework to generate standard-dose brain [{sup 18}F]FDG PET image using low-dose brain [{sup 18}F]FDG PET and MRI images. Both the visual and quantitative results indicate that the standard-dose brain [{sup 18}F]FDG PET can be well-predicted using MRI and low-dose brain [{sup 18}F]FDG PET.« less

Authors:
 [1];  [2];  [3];  [4];  [5];  [6]
  1. School of Electronics Engineering, Huaihai Institute of Technology, Lianyungang, Jiangsu 222005, China and IDEA Laboratory, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 (United States)
  2. IDEA Laboratory, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 and Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 (United States)
  3. IDEA Laboratory, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 (United States)
  4. Joint UNC-NCSU Department of Biomedical Engineering, North Carolina State University, Raleigh, North Carolina 27695 (United States)
  5. MRI Laboratory, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 (United States)
  6. IDEA Laboratory, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 and Department of Brain and Cognitive Engineering, Korea University, Seoul 136-713 (Korea, Republic of)
Publication Date:
OSTI Identifier:
22581360
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 42; Journal Issue: 9; Other Information: (c) 2015 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; ALGORITHMS; ANIMAL TISSUES; BIOMEDICAL RADIOGRAPHY; BRAIN; CEREBROSPINAL FLUID; DIAGNOSIS; FLUORINE 18; FLUORODEOXYGLUCOSE; IMAGE PROCESSING; IMAGES; ITERATIVE METHODS; NMR IMAGING; POSITRON COMPUTED TOMOGRAPHY; RADIATION DOSES

Citation Formats

Kang, Jiayin, Gao, Yaozong, Shi, Feng, Lalush, David S., Lin, Weili, and Shen, Dinggang, E-mail: dgshen@med.unc.edu. Prediction of standard-dose brain PET image by using MRI and low-dose brain [{sup 18}F]FDG PET images. United States: N. p., 2015. Web. doi:10.1118/1.4928400.
Kang, Jiayin, Gao, Yaozong, Shi, Feng, Lalush, David S., Lin, Weili, & Shen, Dinggang, E-mail: dgshen@med.unc.edu. Prediction of standard-dose brain PET image by using MRI and low-dose brain [{sup 18}F]FDG PET images. United States. doi:10.1118/1.4928400.
Kang, Jiayin, Gao, Yaozong, Shi, Feng, Lalush, David S., Lin, Weili, and Shen, Dinggang, E-mail: dgshen@med.unc.edu. Tue . "Prediction of standard-dose brain PET image by using MRI and low-dose brain [{sup 18}F]FDG PET images". United States. doi:10.1118/1.4928400.
@article{osti_22581360,
title = {Prediction of standard-dose brain PET image by using MRI and low-dose brain [{sup 18}F]FDG PET images},
author = {Kang, Jiayin and Gao, Yaozong and Shi, Feng and Lalush, David S. and Lin, Weili and Shen, Dinggang, E-mail: dgshen@med.unc.edu},
abstractNote = {Purpose: Positron emission tomography (PET) is a nuclear medical imaging technology that produces 3D images reflecting tissue metabolic activity in human body. PET has been widely used in various clinical applications, such as in diagnosis of brain disorders. High-quality PET images play an essential role in diagnosing brain diseases/disorders. In practice, in order to obtain high-quality PET images, a standard-dose radionuclide (tracer) needs to be used and injected into a living body. As a result, it will inevitably increase the patient’s exposure to radiation. One solution to solve this problem is predicting standard-dose PET images using low-dose PET images. As yet, no previous studies with this approach have been reported. Accordingly, in this paper, the authors propose a regression forest based framework for predicting a standard-dose brain [{sup 18}F]FDG PET image by using a low-dose brain [{sup 18}F]FDG PET image and its corresponding magnetic resonance imaging (MRI) image. Methods: The authors employ a regression forest for predicting the standard-dose brain [{sup 18}F]FDG PET image by low-dose brain [{sup 18}F]FDG PET and MRI images. Specifically, the proposed method consists of two main steps. First, based on the segmented brain tissues (i.e., cerebrospinal fluid, gray matter, and white matter) in the MRI image, the authors extract features for each patch in the brain image from both low-dose PET and MRI images to build tissue-specific models that can be used to initially predict standard-dose brain [{sup 18}F]FDG PET images. Second, an iterative refinement strategy, via estimating the predicted image difference, is used to further improve the prediction accuracy. Results: The authors evaluated their algorithm on a brain dataset, consisting of 11 subjects with MRI, low-dose PET, and standard-dose PET images, using leave-one-out cross-validations. The proposed algorithm gives promising results with well-estimated standard-dose brain [{sup 18}F]FDG PET image and substantially enhanced image quality of low-dose brain [{sup 18}F]FDG PET image. Conclusions: In this paper, the authors propose a framework to generate standard-dose brain [{sup 18}F]FDG PET image using low-dose brain [{sup 18}F]FDG PET and MRI images. Both the visual and quantitative results indicate that the standard-dose brain [{sup 18}F]FDG PET can be well-predicted using MRI and low-dose brain [{sup 18}F]FDG PET.},
doi = {10.1118/1.4928400},
journal = {Medical Physics},
number = 9,
volume = 42,
place = {United States},
year = {Tue Sep 15 00:00:00 EDT 2015},
month = {Tue Sep 15 00:00:00 EDT 2015}
}
  • Purpose: To investigate the performance of a new penalized-likelihood PET image reconstruction algorithm using the 1{sub 1}-norm total-variation (TV) sum of the 1st through 4th-order gradients as the penalty. Simulated and brain patient data sets were analyzed. Methods: This work represents an extension of the preconditioned alternating projection algorithm (PAPA) for emission-computed tomography. In this new generalized algorithm (GPAPA), the penalty term is expanded to allow multiple components, in this case the sum of the 1st to 4th order gradients, to reduce artificial piece-wise constant regions (“staircase” artifacts typical for TV) seen in PAPA images penalized with only the 1stmore » order gradient. Simulated data were used to test for “staircase” artifacts and to optimize the penalty hyper-parameter in the root-mean-squared error (RMSE) sense. Patient FDG brain scans were acquired on a GE D690 PET/CT (370 MBq at 1-hour post-injection for 10 minutes) in time-of-flight mode and in all cases were reconstructed using resolution recovery projectors. GPAPA images were compared PAPA and RMSE-optimally filtered OSEM (fully converged) in simulations and to clinical OSEM reconstructions (3 iterations, 32 subsets) with 2.6 mm XYGaussian and standard 3-point axial smoothing post-filters. Results: The results from the simulated data show a significant reduction in the 'staircase' artifact for GPAPA compared to PAPA and lower RMSE (up to 35%) compared to optimally filtered OSEM. A simple power-law relationship between the RMSE-optimal hyper-parameters and the noise equivalent counts (NEC) per voxel is revealed. Qualitatively, the patient images appear much sharper and with less noise than standard clinical images. The convergence rate is similar to OSEM. Conclusions: GPAPA reconstructions using the 1{sub 1}-norm total-variation sum of the 1st through 4th-order gradients as the penalty show great promise for the improvement of image quality over that currently achieved with clinical OSEM reconstructions.« less
  • There is considerable interest in the health effects associated with low-level radiation exposure from medical imaging procedures. Concerns in the medical community that increased radiation exposure from imaging procedures may increase cancer risk among patients are confounded by research showing that low-dose radiation exposure can extend lifespan by increasing the latency period of some types of cancer. The most commonly used radiopharmaceutical for positron emission tomography (PET) scans is 2-[ 18F] fluoro-2-deoxy-d-glucose ( 18F-FDG), which exposes tissue to a low-dose, mixed radiation quality: 634 keV β+ and 511 keV γ-rays. The goal of this research was to investigate how modificationmore » of cancer risk associated with exposure to low-dose ionising radiation in cancer-prone Trp53+/- mice is influenced by radiation quality from PET. At 7-8 weeks of age, Trp53+/- female mice were exposed to one of five treatments: 0 Gy, 10 mGy γ-rays, 10 mGy 18F-FDG, 4 Gy γ-rays, 10 mGy 18F-FDG + 4 Gy γ-rays (n > 185 per group). The large 4-Gy radiation dose significantly reduced the lifespan by shortening the latency period of cancer and significantly increasing the number of mice with malignancies, compared with unirradiated controls. The 10 mGy γ-rays and 10 mGy PET doses did not significantly modify the frequency or latency period of cancer relative to unirradiated mice. Similarly, the PET scan administered prior to a large 4-Gy dose did not significantly modify the latency or frequency of cancer relative to mice receiving a dose of only 4 Gy. The relative biological effectiveness of radiation quality from 18F-FDG, with respect to malignancy, is approximately 1. Furthermore, when non-cancer endpoints were studied, it was found that the 10-mGy PET group had a significant reduction in kidney lesions (P < 0.021), indicating that a higher absorbed dose (20 ± 0.13 mGy), relative to the whole-body average, which occurs in specific tissues, may not be detrimental.« less
  • Purpose: To correlate proton magnetic resonance spectroscopy ({sup 1}H-MRS), dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), and {sup 18}F-labeled fluorodeoxyglucose positron emission tomography ([{sup 18}F]FDG PET) of nodal metastases in patients with head and neck squamous cell carcinoma (HNSCC) for assessment of tumor biology. Additionally, pretreatment multimodality imaging was evaluated for its efficacy in predicting short-term response to treatment. Methods and Materials: Metastatic neck nodes were imaged with {sup 1}H-MRS, DCE-MRI, and [{sup 18}F]FDG PET in 16 patients with newly diagnosed HNSCC, before treatment. Short-term patient radiological response was evaluated at 3 to 4 months. Correlations among {sup 1}H-MRS (choline concentrationmore » relative to water [Cho/W]), DCE-MRI (volume transfer constant [K{sup trans}]; volume fraction of the extravascular extracellular space [v{sub e}]; and redistribution rate constant [k{sub ep}]), and [{sup 18}F]FDG PET (standard uptake value [SUV] and total lesion glycolysis [TLG]) were calculated using nonparametric Spearman rank correlation. To predict short-term responses, logistic regression analysis was performed. Results: A significant positive correlation was found between Cho/W and TLG ({rho} = 0.599; p = 0.031). Cho/W correlated negatively with heterogeneity measures of standard deviation std(v{sub e}) ({rho} = -0.691; p = 0.004) and std(k{sub ep}) ({rho} = -0.704; p = 0.003). Maximum SUV (SUVmax) values correlated strongly with MRI tumor volume ({rho} = 0.643; p = 0.007). Logistic regression indicated that std(K{sup trans}) and SUVmean were significant predictors of short-term response (p < 0.07). Conclusion: Pretreatment multimodality imaging using {sup 1}H-MRS, DCE-MRI, and [{sup 18}F]FDG PET is feasible in HNSCC patients with nodal metastases. Additionally, combined DCE-MRI and [{sup 18}F]FDG PET parameters were predictive of short-term response to treatment.« less
  • Purpose: The aim of this study was to implement a Dirichlet process mixture (DPM) model for automatic tumor edge identification on {sup 18}F-fluorodeoxyglucose positron emission tomography ({sup 18}F-FDG PET) images by optimizing the parameters on which the algorithm depends, to validate it experimentally, and to test its robustness. Methods: The DPM model belongs to the class of the Bayesian nonparametric models and uses the Dirichlet process prior for flexible nonparametric mixture modeling, without any preliminary choice of the number of mixture components. The DPM algorithm implemented in the statistical software package R was used in this work. The contouring accuracymore » was evaluated on several image data sets: on an IEC phantom (spherical inserts with diameter in the range 10–37 mm) acquired by a Philips Gemini Big Bore PET-CT scanner, using 9 different target-to-background ratios (TBRs) from 2.5 to 70; on a digital phantom simulating spherical/uniform lesions and tumors, irregular in shape and activity; and on 20 clinical cases (10 lung and 10 esophageal cancer patients). The influence of the DPM parameters on contour generation was studied in two steps. In the first one, only the IEC spheres having diameters of 22 and 37 mm and a sphere of the digital phantom (41.6 mm diameter) were studied by varying the main parameters until the diameter of the spheres was obtained within 0.2% of the true value. In the second step, the results obtained for this training set were applied to the entire data set to determine DPM based volumes of all available lesions. These volumes were compared to those obtained by applying already known algorithms (Gaussian mixture model and gradient-based) and to true values, when available. Results: Only one parameter was found able to significantly influence segmentation accuracy (ANOVA test). This parameter was linearly connected to the uptake variance of the tested region of interest (ROI). In the first step of the study, a calibration curve was determined to automatically generate the optimal parameter from the variance of the ROI. This “calibration curve” was then applied to contour the whole data set. The accuracy (mean discrepancy between DPM model-based contours and reference contours) of volume estimation was below (1 ± 7)% on the whole data set (1 SD). The overlap between true and automatically segmented contours, measured by the Dice similarity coefficient, was 0.93 with a SD of 0.03. Conclusions: The proposed DPM model was able to accurately reproduce known volumes of FDG concentration, with high overlap between segmented and true volumes. For all the analyzed inserts of the IEC phantom, the algorithm proved to be robust to variations in radius and in TBR. The main advantage of this algorithm was that no setting of DPM parameters was required in advance, since the proper setting of the only parameter that could significantly influence the segmentation results was automatically related to the uptake variance of the chosen ROI. Furthermore, the algorithm did not need any preliminary choice of the optimum number of classes to describe the ROIs within PET images and no assumption about the shape of the lesion and the uptake heterogeneity of the tracer was required.« less
  • Purpose: To quantify the relationship between bone marrow (BM) response to radiation and radiation dose by using {sup 18}F-labeled fluorodeoxyglucose positron emission tomography [{sup 18}F]FDG-PET standard uptake values (SUV) and to correlate these findings with hematological toxicity (HT) in cervical cancer (CC) patients treated with chemoradiation therapy (CRT). Methods and Materials: Seventeen women with a diagnosis of CC were treated with standard doses of CRT. All patients underwent pre- and post-therapy [{sup 18}F]FDG-PET/computed tomography (CT). Hemograms were obtained before and during treatment and 3 months after treatment and at last follow-up. Pelvic bone was autosegmented as total bone marrow (BM{sub TOT}).more » Active bone marrow (BM{sub ACT}) was contoured based on SUV greater than the mean SUV of BM{sub TOT}. The volumes (V) of each region receiving 10, 20, 30, and 40 Gy (V{sub 10}, V{sub 20}, V{sub 30}, and V{sub 40}, respectively) were calculated. Metabolic volume histograms and voxel SUV map response graphs were created. Relative changes in SUV before and after therapy were calculated by separating SUV voxels into radiation therapy dose ranges of 5 Gy. The relationships among SUV decrease, radiation dose, and HT were investigated using multiple regression models. Results: Mean relative pre-post-therapy SUV reductions in BM{sub TOT} and BM{sub ACT} were 27% and 38%, respectively. BM{sub ACT} volume was significantly reduced after treatment (from 651.5 to 231.6 cm{sup 3}, respectively; P<.0001). BM{sub ACT} V{sub 30} was significantly correlated with a reduction in BM{sub ACT} SUV (R{sup 2}, 0.14; P<.001). The reduction in BM{sub ACT} SUV significantly correlated with reduction in white blood cells (WBCs) at 3 months post-treatment (R{sup 2}, 0.27; P=.04) and at last follow-up (R{sup 2}, 0.25; P=.04). Different dosimetric parameters of BM{sub TOT} and BM{sub ACT} correlated with long-term hematological outcome. Conclusions: The volumes of BM{sub TOT} and BM{sub ACT} that are exposed to even relatively low doses of radiation are associated with a decrease in WBC counts following CRT. The loss in proliferative BM SUV uptake translates into low WBC nadirs after treatment. These results suggest the potential of intensity modulated radiation therapy to spare BM{sub TOT} to reduce long-term hematological toxicity.« less