Publications by authors named "Arman Rahmim"

119 Publications

Anna Celler, PhD, 1951-2020.

J Nucl Med 2021 Mar;62(3):14N

View Article and Find Full Text PDF

Download full-text PDF

Source
March 2021

Dynamic PET Image Reconstruction Utilizing Intrinsic Data-Driven HYPR4D De-noising Kernel.

Med Phys 2021 Feb 3. Epub 2021 Feb 3.

Department of Physics and Astronomy, The University of British Columbia, 6224 Agricultural Road, Vancouver, B.C, V6T 1Z1, Canada.

Purpose: Reconstructed PET images are typically noisy, especially in dynamic imaging where the acquired data are divided into several short temporal frames. High noise in the reconstructed images translates to poor precision/reproducibility of image features. One important role of 'de-noising' is therefore to improve the precision of image features. However, typical de-noising methods achieve noise reduction at the expense of accuracy. In this work, we present a novel 4D de-noised image reconstruction frame-work, which we validate using 4D simulations, experimental phantom, and clinical patient data, to achieve 4D noise reduction while preserving spatiotemporal patterns/minimizing error introduced by de-noising.

Methods: Our proposed 4D de-noising operator/kernel is based on HighlY constrained backPRojection (HYPR), which is applied either after each update of OSEM reconstruction of dynamic 4D PET data or within the recently proposed kernelized reconstruction frame-work inspired by kernel methods in machine learning. Our HYPR4D kernel makes use of the spatiotemporal high frequency features extracted from a 4D composite, generated within the reconstruction, to preserve the spatiotemporal patterns and constrain the 4D noise increment of the image estimate.

Results: Results from simulations, experimental phantom, and patient data showed that the HYPR4D kernel with our proposed 4D composite outperformed other de-noising methods, such as the standard OSEM with spatial filter, OSEM with 4D filter and HYPR kernel method with the conventional 3D composite in conjunction with recently proposed High Temporal Resolution kernel (HYPRC3D-HTR), in terms of 4D noise reduction while preserving the spatiotemporal patterns or 4D resolution within the 4D image estimate. Consequently, the error in outcome measures obtained from the HYPR4D method was less dependent on the region size, contrast, and uniformity/functional patterns within the target structures compared to the other methods. For outcome measures that depend on spatiotemporal tracer uptake patterns such as the non-displaceable Binding Potential (BP ), the root mean squared error in regional mean of voxel BP values was reduced from ~8% (OSEM with spatial or 4D filter) to ~3% using HYPRC3D-HTR and was further reduced to ~2% using our proposed HYPR4D method for relatively small target structures (~10 mm in diameter). At the voxel level, HYPR4D produced 2-4 times lower mean absolute error in BP relative to HYPRC3D-HTR.

Conclusion: As compared to conventional methods, our proposed HYPR4D method can produce more robust and accurate image features without requiring any prior information.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.14751DOI Listing
February 2021

Evaluation of inverse methods for estimation of mechanical parameters in solid tumors.

Biomed Phys Eng Express 2020 Apr 22;6(3):035027. Epub 2020 Apr 22.

Department of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, Iran. Advanced Bioengineering Initiative Center, Computational Medicine Center, K. N. Toosi University of Technology, Tehran, Iran. Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada. Centre for Biotechnology and Bioengineering (CBB), University of Waterloo, Waterloo, ON, Canada. Cancer Biology Research Centre, Cancer Institute of Iran, Tehran University of Medical Sciences, Tehran, Iran.

To treat cancer, knowledge of mechanical parameters can be essential. This study proposes a new approach for estimating hydraulic conductivity (k) and hydraulic conductivity ratio (α) of a living tissue, based on inverse methods, allowing tissue parameter estimation using only a limited set of measurements. First, two population-based algorithms (Levenberg-Marquardt (LM) method and conjugate gradient (CG) method) and two gradient-based algorithms (genetic algorithm (GA) and particle swarm optimization (PSO) algorithm) are considered, and a comparative study between these different inverse methods is performed to determine which methods have a good performance in terms of convergence rate and stability. CG method is shown to perform well in the case of noise-free input data; however, in the case of noisy input data, it fails to converge. The other three methods (LM, GA, and PSO) converge with estimation errors <10% in both noise-free and noisy input data, suggesting their utility to tackle this problem. In the second part, the effectiveness and good accuracy of these robust algorithms (LM, GA, and PSO) are validated with experimental results. The hydraulic conductivity and hydraulic conductivity ratio of a specific living tumor tissue are then estimated for mammary adenocarcinoma (R3230AC). Moreover, assuming measurement of only one-point interstitial pressure inside the tumor, the effect of the location of this one-point on estimation accuracy of hydraulic conductivity is investigated. We show that estimation errors for points measured near the surface and center of the tumor are greater than at other points.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/2057-1976/ab872bDOI Listing
April 2020

Mars Shot for Nuclear Medicine, Molecular Imaging, and Molecularly Targeted Radiopharmaceutical Therapy.

J Nucl Med 2021 Jan;62(1):6-14

Departments of Radiology and Physics, University of Iowa, Iowa City, Iowa.

The Society of Nuclear Medicine and Molecular Imaging created the Value Initiative in 2017 as a major component of its strategic plan to further demonstrate the value of molecular imaging and molecularly targeted radiopharmaceutical therapy to patients, physicians, payers, and funding agencies. The research and discovery domain, 1 of 5 under the Value Initiative, has a goal of advancing the research and development of diagnostic and therapeutic nuclear medicine. Research and discovery efforts and achievements are essential to ensure a bright future for NM and to translate science to practice. Given the remarkable progress in the field, leaders from the research and discovery domain and society councils identified 5 broad areas of opportunity with potential for substantive growth and clinical impact. This article discusses these 5 growth areas, identifying specific areas of particularly high importance for future study and development. As there was an understanding that goals should be both visionary yet achievable, this effort was called the Mars shot for nuclear medicine.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2967/jnumed.120.253450DOI Listing
January 2021

Robust identification of Parkinson's disease subtypes using radiomics and hybrid machine learning.

Comput Biol Med 2021 Feb 25;129:104142. Epub 2020 Nov 25.

Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada; Department of Radiology, University of British Columbia, Vancouver, BC, Canada. Electronic address:

Objectives: It is important to subdivide Parkinson's disease (PD) into subtypes, enabling potentially earlier disease recognition and tailored treatment strategies. We aimed to identify reproducible PD subtypes robust to variations in the number of patients and features.

Methods: We applied multiple feature-reduction and cluster-analysis methods to cross-sectional and timeless data, extracted from longitudinal datasets (years 0, 1, 2 & 4; Parkinson's Progressive Marker Initiative; 885 PD/163 healthy-control visits; 35 datasets with combinations of non-imaging, conventional-imaging, and radiomics features from DAT-SPECT images). Hybrid machine-learning systems were constructed invoking 16 feature-reduction algorithms, 8 clustering algorithms, and 16 classifiers (C-index clustering evaluation used on each trajectory). We subsequently performed: i) identification of optimal subtypes, ii) multiple independent tests to assess reproducibility, iii) further confirmation by a statistical approach, iv) test of reproducibility to the size of the samples.

Results: When using no radiomics features, the clusters were not robust to variations in features, whereas, utilizing radiomics information enabled consistent generation of clusters through ensemble analysis of trajectories. We arrived at 3 distinct subtypes, confirmed using the training and testing process of k-means, as well as Hotelling's T2 test. The 3 identified PD subtypes were 1) mild; 2) intermediate; and 3) severe, especially in terms of dopaminergic deficit (imaging), with some escalating motor and non-motor manifestations.

Conclusion: Appropriate hybrid systems and independent statistical tests enable robust identification of 3 distinct PD subtypes. This was assisted by utilizing radiomics features from SPECT images (segmented using MRI). The PD subtypes provided were robust to the number of the subjects, and features.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiomed.2020.104142DOI Listing
February 2021

Impact of image reconstruction method on dose distributions derived from Y PET images: phantom and liver radioembolization patient studies.

Phys Med Biol 2020 11 27;65(21):215022. Epub 2020 Nov 27.

Department of Radiology, University of British Columbia, Vancouver, Canada.

PET images acquired after liver Y radioembolization therapies are typically very noisy, which significantly challenges both visualization and quantification of activity distributions. To improve their noise characteristics, regularized iterative reconstruction algorithms such as block sequential regularized expectation maximization (Q.Clear for GE Healthcare, USA) have been proposed. In this study, we aimed to investigate the effects which different reconstruction algorithms may have on patient images, with reconstruction parameters initially narrowed down using phantom studies. Moreover, we evaluated the impact of these reconstruction methods on voxel-based dose distribution in phantom and patient studies (lesions and healthy livers). The International Electrotechnical Commission (IEC)/NEMA phantom, containing six spheres, was filled with Y and imaged using a GE Discovery 690 PET/CT scanner with time-of-flight enabled. The images were reconstructed using Q.Clear (with β parameter ranging from 0 to 8000) and ordered subsets expectation maximization. The image quality and quantification accuracy were evaluated by computing the hot ([Formula: see text]) and cold ([Formula: see text]) contrast recovery coefficients, background variability (BV) and activity bias. Next, dose distributions and dose volume histograms were generated using MIM® software's SurePlan LiverY90 toolbox. Subsequently, parameters optimized in these phantom studies were applied to five patient datasets. Dose parameters, such as D, D, D, and V, were estimated, and their variability for different reconstruction methods was investigated. Based on phantom studies, the β parameter values optimized for image quality and quantification accuracy were 2500 and 300, respectively. When all investigated reconstructions were applied to patient studies, D, D, D, and V showed coefficients of variation below 8%; whereas the variability of D was up to 30% for both phantom and patient images. Although β = 300-1000 would provide accurate activity quantification for a region of interest, when considering activity/dose voxelized distribution, higher β value (e.g. 4000-5000) would provide the greatest accuracy for dose distributions. In this Y radioembolization PET/CT study, the β parameter in regularized iterative (Q.Clear) reconstruction was investigated for image quality, accurate quantification and dose distributions based on phantom experiments and then applied to patient studies. Our results indicate that more accurate dose distribution can be achieved from smoother PET images, reconstructed with larger β values than those yielding the best activity quantifications but noisy images. Most importantly, these results suggest that quantitative measures, which are commonly used in clinics, such as SUV or SUV( equivalent of D), should not be employed for Y PET images, since their values would highly depend on the image reconstruction.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6560/aba8b5DOI Listing
November 2020

Short-duration dynamic FDG PET imaging: Optimization and clinical application.

Phys Med 2020 Dec 11;80:193-200. Epub 2020 Nov 11.

Departments of Radiology and Physics, University of British Columbia, Vancouver, BC, Canada; Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, MD, USA.

Purpose: We aimed to investigate whether short dynamic PET imaging started at injection, complemented with routine clinical acquisition at 60-min post-injection (static), can achieve reliable kinetic analysis.

Methods: Dynamic and static 18F-2-fluoro-2-deoxy-D-glucose (FDG) PET data were generated using realistic simulations to assess uncertainties due to statistical noise as well as bias. Following image reconstructions, kinetic parameters obtained from a 2-tissue-compartmental model (2TCM) were estimated, making use of the static image, and the time duration of dynamic PET data were incrementally shortened. We also investigated, in the first 2-min, different frame sampling rates, towards optimized dynamic PET imaging. Kinetic parameters from shortened dynamic datasets were additionally estimated for 9 patients (15 scans) with liver metastases of colorectal cancer, and were compared with those derived from full dynamic imaging using correlation and Passing-Bablok regression analyses.

Results: The results showed that by reduction of dynamic scan times from 60-min to as short as 5-min, while using static data at 60-min post-injection, bias and variability stayed comparable in estimated kinetic parameters. Early frame samplings of 5, 24 and 30 s yielded highest biases compared to other schemes. An early frame sampling of 10 s generally kept both bias and variability to a minimum. In clinical studies, strong correlation (r ≥ 0.97, P < 0.0001) existed between all kinetic parameters in full vs. shortened scan protocols.

Conclusions: Shortened 5-min dynamic scan, sampled as 12 × 10 + 6 × 30 s, followed by 3-min static image at 60-min post-injection, enables accurate and robust estimation of 2TCM parameters, while enabling generation of SUV estimates.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2020.11.004DOI Listing
December 2020

Feasibility of single-time-point dosimetry for radiopharmaceutical therapies.

J Nucl Med 2020 Oct 30. Epub 2020 Oct 30.

Department of Radiology, University of British Columbia; Department of Integrative Oncology, BC Cancer Research Institute; Functional Imaging, BC Cancer, Canada.

Due to challenges in performing routine personalized dosimetry in radiopharmaceutical therapies, interest in single-time-point (STP) dosimetry, particularly utilizing only one SPECT scan, is on the rise. Meanwhile, there are questions about reliability of STP dosimetry, with limited independent validations. In the present work, we analyze two STP dosimetry methods and evaluate dose errors for a number of radiopharmaceuticals based on effective half-life distributions. : We first challenged the common assumption that radiopharmaceutical effective half-lives across the population are Gaussian (normal) distributed. Then, dose accuracy was estimated based on two STP dosimetry methods for a wide range of potential scan-times post-injection (p.i.), for different radiopharmaceuticals applied to neuroendocrine tumors and prostate cancer. The accuracy and limitations of using each of the STP methods were discussed. : Log-normal distribution was shown as more appropriate to capture effective half-life distributions. The STP framework was shown as promising for dosimetry of Lu-DOTATATE, and for kidney dosimetry of different radiopharmaceuticals (errors<30%). Meanwhile, for some radiopharmaceuticals, STP accuracy is compromised (e.g. in bone marrow and tumors for Lu-PSMA therapies). Optimal SPECT scanning time for Lu-DOTATATE is at ~72 h p.i., while 48 h p.i. would be better for Lu-PSMA compounds. : Our results demonstrate that simplified STP dosimetry methods may compromise the accuracy of dose estimates, with some exceptions such as for Lu-DOTATATE and for kidney dosimetry in different radiopharmaceuticals. Simplified personalized dosimetry in the clinic continues to be a challenging task. Based on these results, we make suggestions and recommendations for improved personalized dosimetry using simplified imaging schemes.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2967/jnumed.120.254656DOI Listing
October 2020

Integration of PET/CT Radiomics and Semantic Features for Differentiation between Active Pulmonary Tuberculosis and Lung Cancer.

Mol Imaging Biol 2021 Apr 8;23(2):287-298. Epub 2020 Oct 8.

School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, Guangdong, China.

Purpose: We aim to accurately differentiate between active pulmonary tuberculosis (TB) and lung cancer (LC) based on radiomics and semantic features as extracted from pre-treatment positron emission tomography/X-ray computed tomography (PET/CT) images.

Procedures: A total of 174 patients (77/97 pulmonary TB/LC as confirmed by pathology) were retrospectively selected, with 122 in the training cohort and 52 in the validation cohort. Four hundred eighty-seven radiomics features were initially extracted to quantify phenotypic characteristics of the lesion region in both PET and CT images. Eleven semantic features were additionally defined by two experienced nuclear medicine physicians. Feature selection was performed in 5 steps to enable derivation of robust and effective signatures. Multivariable logistic regression analysis was subsequently used to develop a radiomics nomogram. The calibration, discrimination, and clinical usefulness of the nomogram were evaluated in both the training and independent validation cohorts.

Results: The individualized radiomics nomogram, which combined PET/CT radiomics signature with semantic features, demonstrated good calibration and significantly improved the diagnostic performance with respect to the semantic model alone or PET/CT signature alone in training cohort (AUC 0.97 vs. 0.94 or 0.91, p = 0.0392 or 0.0056), whereas did not significantly improve the performance in validation cohort (AUC 0.93 vs. 0.89 or 0.91, p = 0.3098 or 0.3323).

Conclusion: The radiomics nomogram showed potential for individualized differential diagnosis between solid active pulmonary TB and solid LC, although the improvement of performance was not significant relative to semantic model.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11307-020-01550-4DOI Listing
April 2021

A theranostic approach based on radiolabeled antiviral drugs, antibodies and CRISPR-associated proteins for early detection and treatment of SARS-CoV-2 disease.

Nucl Med Commun 2020 09;41(9):837-840

Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/MNM.0000000000001269DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7485524PMC
September 2020

Impact of image reconstruction method on dose distributions derived fromY PET images: phantom and liver radioembolization patient studies.

Phys Med Biol 2020 Jul 23. Epub 2020 Jul 23.

Radiology, University of British Columbia, Vancouver, CANADA.

PET images acquired after liverY radioembolization therapies are typically very noisy, which significantly challenges both visualization and quantification of activity distributions. To improve their noise characteristics, regularized iterative reconstruction algorithms such as BSREM (Q.Clear for GE Healthcare, USA) have been proposed. . In this study, we aimed to investigate the effects which different reconstruction algorithms may have on patient images, with reconstruction parameters initially narrowed down using phantom studies. Moreover, we evaluated the impact of these reconstruction methods on voxel-based dose distribution in phantom and patient studies (lesions and healthy livers).: The IEC/NEMA phantom containing six spheres was filled withY and imaged using a GE Discovery 690 PET/CT scanner with time-of-flight (TOF) enabled. The images were reconstructed using Q.Clear (with β parameter ranging from 0 to 8000) and OSEM. The image quality and quantification accuracy were evaluated by computing the hot (Q) and cold (Q) contrast recovery coefficients, background variability (BV) and activity bias. Next, dose distributions and dose volume histograms (DVH) were generated using MIM® software's SurePlan LiverY90 toolbox. Subsequently, parameters optimized in these phantom studies were applied to five patient' datasets. Dose parameters (D, D, D, and V) were estimated, and their variability for different reconstruction methods was estimated.: Based on phantom studies,the β parameter values optimized for image quality and quantification accuracy were 2500 and 300, respectively. When all investigated reconstructions applied to patient studies, D, D, D, and Vshowed the coefficient of variation <8%; whereas the variability of Dwas up to >30% for both phantom and patient images. Although β=300-1000 would provide accurate activity quantification for a region of interest, when considering activity/dose voxelized distribution, higher β value (e.g. 4000-5000) would provide the greatest accuracy for dose distributions.: In thisY radioembolization PET/CT study, the β parameter in regularized iterative (Q.Clear) reconstruction was investigated for image quality, accurate quantification and dose distributions based on phantom experiments and then applied to patient studies. Our results indicate that more accurate dose distribution can be achieved from smoother PET images, reconstructed with larger β values than those yielding the best activity quantification, but noisy images. Most importantly, these results suggest that, quantitative measures, which are commonly used in clinics, such as SUVor SUV(equivalent of D), should not be employed forY PET images, since their values would highly depend on the image reconstruction.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6560/aba8b5DOI Listing
July 2020

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test-retest and image registration analyses.

Med Phys 2020 Sep 28;47(9):4265-4280. Epub 2020 Jul 28.

Departments of Radiology and Physics, University of British Columbia, Vancouver, BC, Canada.

Purpose: To assess the repeatability of radiomic features in magnetic resonance (MR) imaging of glioblastoma (GBM) tumors with respect to test-retest, different image registration approaches and inhomogeneity bias field correction.

Methods: We analyzed MR images of 17 GBM patients including T1- and T2-weighted images (performed within the same imaging unit on two consecutive days). For image segmentation, we used a comprehensive segmentation approach including entire tumor, active area of tumor, necrotic regions in T1-weighted images, and edema regions in T2-weighted images (test studies only; registration to retest studies is discussed next). Analysis included N3, N4 as well as no bias correction performed on raw MR images. We evaluated 20 image registration approaches, generated by cross-combination of four transformation and five cost function methods. In total, 714 images (17 patients × 2 images × ((4 transformations × 5 cost functions) + 1 test image) and 2856 segmentations (714 images × 4 segmentations) were prepared for feature extraction. Various radiomic features were extracted, including the use of preprocessing filters, specifically wavelet (WAV) and Laplacian of Gaussian (LOG), as well as discretization into fixed bin width and fixed bin count (16, 32, 64, 128, and 256), Exponential, Gradient, Logarithm, Square and Square Root scales. Intraclass correlation coefficients (ICC) were calculated to assess the repeatability of MRI radiomic features (high repeatability defined as ICC ≥ 95%).

Results: In our ICC results, we observed high repeatability (ICC ≥ 95%) with respect to image preprocessing, different image registration algorithms, and test-retest analysis, for example: RLNU and GLNU from GLRLM, GLNU and DNU from GLDM, Coarseness and Busyness from NGTDM, GLNU and ZP from GLSZM, and Energy and RMS from first order. Highest fraction (percent) of repeatable features was observed, among registration techniques, for the method Full Affine transformation with 12 degrees of freedom using Mutual Information cost function (mean 32.4%), and among image processing methods, for the method Laplacian of Gaussian (LOG) with Sigma (2.5-4.5 mm) (mean 78.9%). The trends were relatively consistent for N4, N3, or no bias correction.

Conclusion: Our results showed varying performances in repeatability of MR radiomic features for GBM tumors due to test-retest and image registration. The findings have implications for appropriate usage in diagnostic and predictive models.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.14368DOI Listing
September 2020

Deep-JASC: joint attenuation and scatter correction in whole-body F-FDG PET using a deep residual network.

Eur J Nucl Med Mol Imaging 2020 10 15;47(11):2533-2548. Epub 2020 May 15.

Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland.

Objective: We demonstrate the feasibility of direct generation of attenuation and scatter-corrected images from uncorrected images (PET-nonASC) using deep residual networks in whole-body F-FDG PET imaging.

Methods: Two- and three-dimensional deep residual networks using 2D successive slices (DL-2DS), 3D slices (DL-3DS) and 3D patches (DL-3DP) as input were constructed to perform joint attenuation and scatter correction on uncorrected whole-body images in an end-to-end fashion. We included 1150 clinical whole-body F-FDG PET/CT studies, among which 900, 100 and 150 patients were randomly partitioned into training, validation and independent validation sets, respectively. The images generated by the proposed approach were assessed using various evaluation metrics, including the root-mean-squared-error (RMSE) and absolute relative error (ARE %) using CT-based attenuation and scatter-corrected (CTAC) PET images as reference. PET image quantification variability was also assessed through voxel-wise standardized uptake value (SUV) bias calculation in different regions of the body (head, neck, chest, liver-lung, abdomen and pelvis).

Results: Our proposed attenuation and scatter correction (Deep-JASC) algorithm provided good image quality, comparable with those produced by CTAC. Across the 150 patients of the independent external validation set, the voxel-wise REs (%) were - 1.72 ± 4.22%, 3.75 ± 6.91% and - 3.08 ± 5.64 for DL-2DS, DL-3DS and DL-3DP, respectively. Overall, the DL-2DS approach led to superior performance compared with the other two 3D approaches. The brain and neck regions had the highest and lowest RMSE values between Deep-JASC and CTAC images, respectively. However, the largest ARE was observed in the chest (15.16 ± 3.96%) and liver/lung (11.18 ± 3.23%) regions for DL-2DS. DL-3DS and DL-3DP performed slightly better in the chest region, leading to AREs of 11.16 ± 3.42% and 11.69 ± 2.71%, respectively (p value < 0.05). The joint histogram analysis resulted in correlation coefficients of 0.985, 0.980 and 0.981 for DL-2DS, DL-3DS and DL-3DP approaches, respectively.

Conclusion: This work demonstrated the feasibility of direct attenuation and scatter correction of whole-body F-FDG PET images using emission-only data via a deep residual network. The proposed approach achieved accurate attenuation and scatter correction without the need for anatomical images, such as CT and MRI. The technique is applicable in a clinical setting on standalone PET or PET/MRI systems. Nevertheless, Deep-JASC showing promising quantitative accuracy, vulnerability to noise was observed, leading to pseudo hot/cold spots and/or poor organ boundary definition in the resulting PET images.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00259-020-04852-5DOI Listing
October 2020

A physics-guided modular deep-learning based automated framework for tumor segmentation in PET.

Phys Med Biol 2020 Dec 18;65(24):245032. Epub 2020 Dec 18.

Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United States of America. The Russell H. Morgan Department of Radiology, Johns Hopkins University, Baltimore, MD, United States of America.

An important need exists for reliable positron emission tomography (PET) tumor-segmentation methods for tasks such as PET-based radiation-therapy planning and reliable quantification of volumetric and radiomic features. To address this need, we propose an automated physics-guided deep-learning-based three-module framework to segment PET images on a per-slice basis. The framework is designed to help address the challenges of limited spatial resolution and lack of clinical training data with known ground-truth tumor boundaries in PET. The first module generates PET images containing highly realistic tumors with known ground-truth using a new stochastic and physics-based approach, addressing lack of training data. The second module trains a modified U-net using these images, helping it learn the tumor-segmentation task. The third module fine-tunes this network using a small-sized clinical dataset with radiologist-defined delineations as surrogate ground-truth, helping the framework learn features potentially missed in simulated tumors. The framework was evaluated in the context of segmenting primary tumors in F-fluorodeoxyglucose (FDG)-PET images of patients with lung cancer. The framework's accuracy, generalizability to different scanners, sensitivity to partial volume effects (PVEs) and efficacy in reducing the number of training images were quantitatively evaluated using Dice similarity coefficient (DSC) and several other metrics. The framework yielded reliable performance in both simulated (DSC: 0.87 (95% confidence interval (CI): 0.86, 0.88)) and patient images (DSC: 0.73 (95% CI: 0.71, 0.76)), outperformed several widely used semi-automated approaches, accurately segmented relatively small tumors (smallest segmented cross-section was 1.83 cm), generalized across five PET scanners (DSC: 0.74 (95% CI: 0.71, 0.76)), was relatively unaffected by PVEs, and required low training data (training with data from even 30 patients yielded DSC of 0.70 (95% CI: 0.68, 0.71)). In conclusion, the proposed automated physics-guided deep-learning-based PET-segmentation framework yielded reliable performance in delineating tumors in FDG-PET images of patients with lung cancer.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6560/ab8535DOI Listing
December 2020

Next-Generation Radiogenomics Sequencing for Prediction of EGFR and KRAS Mutation Status in NSCLC Patients Using Multimodal Imaging and Machine Learning Algorithms.

Mol Imaging Biol 2020 08;22(4):1132-1148

Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, MD, USA.

Purpose: Considerable progress has been made in the assessment and management of non-small cell lung cancer (NSCLC) patients based on mutation status in the epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma viral oncogene (KRAS). At the same time, NSCLC management through KRAS and EGFR mutation profiling faces challenges. In the present work, we aimed to evaluate a comprehensive radiomics framework that enabled prediction of EGFR and KRAS mutation status in NSCLC patients based on radiomic features from low-dose computed tomography (CT), contrast-enhanced diagnostic quality CT (CTD), and positron emission tomography (PET) imaging modalities and use of machine learning algorithms.

Methods: Our study involved NSCLC patients including 150 PET, low-dose CT, and CTD images. Radiomic features from original and preprocessed (including 64 bin discretizing, Laplacian-of-Gaussian (LOG), and Wavelet) images were extracted. Conventional clinically used standard uptake value (SUV) parameters and metabolic tumor volume (MTV) were also obtained from PET images. Highly correlated features were pre-eliminated, and false discovery rate (FDR) correction was performed with the resulting q-values reported for univariate analysis. Six feature selection methods and 12 classifiers were then used for multivariate prediction of gene mutation status (provided by polymerase chain reaction (PCR)) in patients. We performed 10-fold cross-validation for model tuning to improve robustness, and our developed models were assessed on an independent validation set with 68 patients (common in all three imaging modalities). The average area under the receiver operator characteristic curve (AUC) was utilized for performance evaluation.

Results: The best predictive power for conventional PET parameters was achieved by SUV (AUC 0.69, p value = 0.0002) and MTV (AUC 0.55, p value = 0.0011) for EGFR and KRAS, respectively. Univariate analysis of extracted radiomics features improved AUC performance to 0.75 (q-value 0.003, Short-Run Emphasis feature of GLRLM from LOG preprocessed image of PET with sigma value 1.5) and 0.71 (q-value 0.00005, Large Dependence Low Gray-Level Emphasis feature of GLDM in LOG preprocessed image of CTD with sigma value 5) for EGFR and KRAS, respectively. Furthermore, multivariate machine learning-based AUC performances were significantly improved to 0.82 for EGFR (LOG preprocessed image of PET with sigma 3 with variance threshold (VT) feature selector and stochastic gradient descent (SGD) classifier (q-value = 4.86E-05) and 0.83 for KRAS (LOG preprocessed image of CT with sigma 3.5 with select model (SM) feature selector and SGD classifier (q-value = 2.81E-09).

Conclusion: Our work demonstrated that non-invasive and reliable radiomics analysis can be successfully used to predict EGFR and KRAS mutation status in NSCLC patients. We demonstrated that radiomic features extracted from different image-feature sets could be used for EGFR and KRAS mutation status prediction in NSCLC patients and showed improved predictive power relative to conventional image-derived metrics.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11307-020-01487-8DOI Listing
August 2020

Computationally Efficient System Matrix Calculation Techniques in Computed Tomography Iterative Reconstruction.

J Med Signals Sens 2020 Jan-Mar;10(1):1-11. Epub 2020 Feb 6.

Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran.

Background: Relative to classical methods in computed tomography, iterative reconstruction techniques enable significantly improved image qualities and/or lowered patient doses. However, the computational speed is a major concern for these iterative techniques. In the present study, we present a method for fast system matrix calculation based on the line integral model (LIM) to speed up the computations without compromising the image quality. In addition, we develop a hybrid line-area integral model (AIM) that highlights the advantages of both LIM and AIMs.

Methods: The contributing detectors for a given pixel and a given projection view, and the length of corresponding intersection lines with pixels, are calculated using our proposed algorithm. For the hybrid method, the respective narrow-angle fan beam was modeled by multiple equally spaced lines. The computed system matrix was evaluated in the context of reconstruction using the simultaneous algebraic reconstruction technique (SART) as well as maximum likelihood expectation maximization (MLEM).

Results: The proposed LIM offers a considerable reduction in calculation times compared to the standard Siddon algorithm: 2.9 times faster. Differences in root mean square error and peak signal-to-noise ratio were not significant between the proposed LIM and the Siddon algorithm for both SART and MLEM reconstruction methods ( > 0.05). Meanwhile, the proposed hybrid method resulted in significantly improved image qualities relative to LIM and the Siddon algorithm ( < 0.05), though computations were 4.9 times more intensive than the proposed LIM.

Conclusion: We have proposed two fast algorithms to calculate the system matrix. The first is based on LIM and was faster than the Siddon algorithm, with matched image quality, whereas the second method is a hybrid LIM-AIM that achieves significantly improved images though with its computational requirements.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.4103/jmss.JMSS_29_19DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7038747PMC
February 2020

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.

Radiology 2020 05 10;295(2):328-338. Epub 2020 Mar 10.

From OncoRay-National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Fetscherstr 74, PF 41, 01307 Dresden, Germany (A.Z., S. Leger, E.G.C.T., C.R., S. Löck); National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany (A.Z.); Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden and Helmholtz Association/Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Dresden, Germany (A.Z., S. Leger, E.G.C.T.); German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany (A.Z., S. Leger, E.G.C.T., C.R., S. Löck); Medical Physics Unit, McGill University, Montréal, Canada (M.V., I.E.N.); Image Response Assessment Team Core Facility, Moffitt Cancer Center, Tampa, Fla (M.A.A.); Dana-Farber Cancer Institute, Brigham and Women's Hospital, and Harvard Medical School, Harvard University, Boston, Mass (H.J.W.L.A.); Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland (V.A., A.D., H.M.); Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY (A.A.); Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, Md (S.A.); Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, Md (S.A., A.R.); Center for Biomedical image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, Pa (S.B., C.D., S.M.H., S.P.); Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa (S.B., C.D., S.M.H., S.P.); Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa (S.B.); Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen (UMCG), Groningen, the Netherlands (R.J.B., R.B., E.A.G.P.); Radiology and Nuclear Medicine, VU University Medical Centre (VUMC), Amsterdam, the Netherlands (R.B.); Department of Radiation Oncology, University Hospital Zurich, University of Zurich, Zurich, Switzerland (M.B., M.Guckenberger, S.T.L.); Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Rome, Italy (L.B., N.D., R.G., J.L., V.V.); Laboratoire d'Imagerie Translationnelle en Oncologie, Université Paris Saclay, Inserm, Institut Curie, Orsay, France (I.B., C.N., F.O.); Cancer Imaging Dept, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom (G.J.R.C., V.G., M.M.S.); Department of Nuclear Medicine and Molecular Imaging, Lausanne University Hospital, Lausanne, Switzerland (A.D.); Laboratory of Medical Information Processing (LaTIM)-team ACTION (image-guided therapeutic action in oncology), INSERM, UMR 1101, IBSAM, UBO, UBL, Brest, France (M.C.D., M.H., T.U.); Department of Radiation Oncology, the Netherlands Cancer Institute (NKI), Amsterdam, the Netherlands (C.V.D.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (S.E., S.N.); Department of Radiation Oncology, Physics Division, University of Michigan, Ann Arbor, Mich (I.E.N., A.U.K.R.); Surgical Planning Laboratory, Brigham and Women's Hospital and Harvard Medical School, Harvard University, Boston, Mass (A.Y.F.); Department of Cancer Imaging and Metabolism, Moffitt Cancer Center, Tampa, Fla (R.J.G.); Department of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany (M. Götz, F.I., K.H.M.H., J.S.); The D-Lab, Department of Precision Medicine, GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, the Netherlands (P.L., R.T.H.L.); Section for Biomedical Physics, Department of Radiation Oncology, University of Tübingen, Germany (F.L., J.S.F., D.T.); Department of Clinical Medicine, University of Bergen, Bergen, Norway (A.L.); Department of Radiation Oncology, University of California, San Francisco, Calif (O.M.); University of Geneva, Geneva, Switzerland (H.M.); Department of Electrical Engineering, Stanford University, Stanford, Calif (S.N.); Department of Medicine (Biomedical Informatics Research), Stanford University School of Medicine, Stanford, Calif (S.N.); Departments of Radiology and Physics, University of British Columbia, Vancouver, Canada (A.R.); Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Mich (A.U.K.R.); Department of Radiation Oncology, University of Groningen, University Medical Center Groningen (UMCG), Groningen, the Netherlands (N.M.S., R.J.H.M.S., L.V.v.D.); School of Engineering, Cardiff University, Cardiff, United Kingdom (E.S., P.W.); Department of Medical Physics, Velindre Cancer Centre, Cardiff, United Kingdom (E.S.); Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany (E.G.C.T., C.R., S. Löck), Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiooncology-OncoRay, Dresden, Germany (E.G.C.T., C.R.); Department of Nuclear Medicine, CHU Milétrie, Poitiers, France (T.U.); Department of Radiology, the Netherlands Cancer Institute (NKI), Amsterdam, the Netherlands (J.v.G.); GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, the Netherlands (J.v.G.); Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Mass (J.v.G.); and Department of Radiology, Leiden University Medical Center (LUMC), Leiden, the Netherlands (F.H.P.v.V.).

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 See also the editorial by Kuhl and Truhn in this issue.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1148/radiol.2020191145DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7193906PMC
May 2020

Transcranial photoacoustic imaging of NMDA-evoked focal circuit dynamics in the rat hippocampus.

J Neural Eng 2020 04 8;17(2):025001. Epub 2020 Apr 8.

Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, MD, United States of America. Laboratory of Computational Sensing and Robotics, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, United States of America.

Objective: We report the transcranial functional photoacoustic (fPA) neuroimaging of N-methyl-D-aspartate (NMDA) evoked neural activity in the rat hippocampus. Concurrent quantitative electroencephalography (qEEG) and microdialysis were used to record real-time circuit dynamics and excitatory neurotransmitter concentrations, respectively.

Approach: We hypothesized that location-specific fPA voltage-sensitive dye (VSD) contrast would identify neural activity changes in the hippocampus which correlate with NMDA-evoked excitatory neurotransmission.

Main Results: Transcranial fPA VSD imaging at the contralateral side of the microdialysis probe provided NMDA-evoked VSD responses with positive correlation to extracellular glutamate concentration changes. qEEG validated a wide range of glutamatergic excitation, which culminated in focal seizure activity after a high NMDA dose. We conclude that transcranial fPA VSD imaging can distinguish focal glutamate loads in the rat hippocampus, based on the VSD redistribution mechanism which is sensitive to the electrophysiologic membrane potential.

Significance: Our results suggest the future utility of this emerging technology in both laboratory and clinical sciences as an innovative functional neuroimaging modality.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1741-2552/ab78caDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7145727PMC
April 2020

Machine learning methods for optimal prediction of motor outcome in Parkinson's disease.

Phys Med 2020 Jan 7;69:233-240. Epub 2020 Jan 7.

Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada; Department of Radiology, University of British Columbia, Vancouver, BC, Canada; Department of Radiology, Johns Hopkins University, Baltimore, MD, USA. Electronic address:

Purpose: It is vital to appropriately power clinical trials towards discovery of novel disease-modifying therapies for Parkinson's disease (PD). Thus, it is critical to improve prediction of outcome in PD patients.

Methods: We systematically probed a range of robust predictor algorithms, aiming to find best combinations of features for significantly improved prediction of motor outcome (MDS-UPDRS-III) in PD. We analyzed 204 PD patients with 18 features (clinical measures; dopamine-transporter (DAT) SPECT imaging measures), performing different randomized arrangements and utilizing data from 64%/6%/30% of patients in each arrangement for training/training validation/final testing. We pursued 3 approaches: i) 10 predictor algorithms (accompanied with automated machine learning hyperparameter tuning) were first applied on 32 experimentally created combinations of 18 features, ii) we utilized Feature Subset Selector Algorithms (FSSAs) for more systematic initial feature selection, and iii) considered all possible combinations between 18 features (262,143 states) to assess contributions of individual features.

Results: A specific set (set 18) applied to the LOLIMOT (Local Linear Model Trees) predictor machine resulted in the lowest absolute error 4.32 ± 0.19, when we firstly experimentally created 32 combinations of 18 features. Subsequently, 2 FSSAs (Genetic Algorithm (GA) and Ant Colony Optimization (ACO)) selecting 5 features, combined with LOLIMOT, reached an error of 4.15 ± 0.46. Our final analysis indicated that longitudinal motor measures (MDS-UPDRS-III years 0 and 1) were highly significant predictors of motor outcome.

Conclusions: We demonstrate excellent prediction of motor outcome in PD patients by employing automated hyperparameter tuning and optimal utilization of FSSAs and predictor algorithms.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2019.12.022DOI Listing
January 2020

The impact of iterative reconstruction protocol, signal-to-background ratio and background activity on measurement of PET spatial resolution.

Jpn J Radiol 2020 Mar 1;38(3):231-239. Epub 2020 Jan 1.

Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran.

Objectives: The present study aims to assess the impact of acquisition time, different iterative reconstruction protocols as well as image context (including contrast levels and background activities) on the measured spatial resolution in PET images.

Methods: Discovery 690 PET/CT scanner was used to quantify spatial resolutions in terms of full width half maximum (FWHM) as derived (i) directly from capillary tubes embedded in air and (ii) indirectly from 10 mm-diameter sphere of the NEMA phantom. Different signal-to-background ratios (SBRs), background activity levels and acquisition times were applied. The emission data were reconstructed using iterative reconstruction protocols. Various combinations of iterations and subsets (it × sub) were evaluated.

Results: For capillary tubes, improved FWHM values were obtained for higher it × sub, with improved performance for PSF algorithms relative to non-PSF algorithms. For the NEMA phantom, by increasing acquisition times from 1 to 5 min, intrinsic FWHM for reconstructions with it × sub 32 (54) was improved by 15.3% (13.2%), 15.1% (13.8%), 14.5% (12.8%) and 13.7% (12.7%) for OSEM, OSEM + PSF, OSEM + TOF and OSEM + PSF + TOF, respectively. Furthermore, for all reconstruction protocols, the FWHM improved with more impact for higher it × sub.

Conclusion: Our results indicate that PET spatial resolution is greatly affected by SBR, background activity and the choice of the reconstruction protocols.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11604-019-00914-3DOI Listing
March 2020

Multi-Level Multi-Modality Fusion Radiomics: Application to PET and CT Imaging for Prognostication of Head and Neck Cancer.

IEEE J Biomed Health Inform 2020 Aug 4;24(8):2268-2277. Epub 2019 Dec 4.

To characterize intra-tumor heterogeneity comprehensively, we propose a multi-level fusion strategy to combine PET and CT information at the image-, matrix-and feature-levels towards improved prognosis. Specifically, we developed fusion radiomics in the context of 3 prognostic outcomes in a multi-center setting (4 centers) involving 296 head & neck cancer patients. Eight clinical parameters were first utilized to build a (1) clinical model. We also built models by extracting 127 radiomics features from (2) PET images alone; (3-8) PET and CT images fused via wavelet-based fusion (WF) using CT-weights of 0.2, 0.4, 0.6 and 0.8, gradient transfer fusion (GTF), and guided filtering-based fusion (GFF); (9) fused matrices (sumMat); (10-11) fused features constructed via feature averaging (avgFea) and feature concatenation (conFea); and finally, (12) CT images alone; above models were also expanded to include both clinical and radiomics features. Seven variations of training and testing partitions were investigated. Highest performance in 5, 6 and 5 partitions was achieved by image-level fusion strategies for RFS, MFS and OS prediction, respectively. Among all partitions, WF0.6 and WF0.8 showed significantly higher performance than CT model for RFS (C-index: 0.60 ± 0.04 vs. 0.56 ± 0.03, p-value: 0.015) and MFS (C-index: 0.71 ± 0.13 vs. 0.62 ± 0.08, p-value: 0.020) predictions, respectively. In partition CER 23 vs. 14, WF0.6 significantly outperformed Clinical model for RFS prediction (C-index: 0.67 vs. 0.53, p-value: 0.003); both avgFea and WF0.6 showed C-index of 0.64 and significantly higher than that of PET only (C-index: 0.51, p-value: 0.018 and 0.031, respectively) for OS prediction. Fusion radiomics modeling showed varying improvements compared to single modality models for different outcome predictions in different partitions, highlighting the importance of generalizing radiomics models. Image-level fusion holds potential to capture more useful characteristics.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/JBHI.2019.2956354DOI Listing
August 2020

Joint compensation of motion and partial volume effects by iterative deconvolution incorporating wavelet-based denoising in oncologic PET/CT imaging.

Phys Med 2019 Dec 18;68:52-60. Epub 2019 Nov 18.

Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran; Research Center for Molecular and Cellular Imaging (RCMCI), Tehran University of Medical Sciences, Tehran, Iran.

Objectives: We aim to develop and rigorously evaluate an image-based deconvolution method to jointly compensate respiratory motion and partial volume effects (PVEs) for quantitative oncologic PET imaging, including studying the impact of various reconstruction algorithms on quantification performance.

Procedures: An image-based deconvolution method that incorporated wavelet-based denoising within the Lucy-Richardson algorithm was implemented and assessed. The method was evaluated using phantom studies with signal-to-background ratios (SBR) of 4 and 8, and clinical data of 10 patients with 42 lung lesions ≤30 mm in diameter. In each study, PET images were reconstructed using four different algorithms: OSEM-basic, PSF, TOF, and TOFPSF. The performance was quantified using contrast recovery (CR), coefficient of variation (COV) and contrast-to-noise-ratio (CNR) metrics. Further, in each study, variabilities arising due to the four different reconstruction algorithms were assessed.

Results: In phantom studies, incorporation of wavelet-based denoising improved COV in all cases. Processing images using proposed method yielded significantly higher CR and CNR particularly in small spheres, for all reconstruction algorithms and all SBRs (P < 0.05). In patient studies, processing images using the proposed method yielded significantly higher CR and CNR (P < 0.05). The choice of the reconstruction algorithm impacted quantification performance for changes in motion amplitude, tumor size and SBRs.

Conclusions: Our results provide strong evidence that the proposed joint-compensation method can yield improved PET quantification. The choice of the reconstruction algorithm led to changes in quantitative accuracy, emphasizing the need to carefully select the right combination of reconstruction-image-based compensation methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2019.10.031DOI Listing
December 2019

Transcranial Recording of Electrophysiological Neural Activity in the Rodent Brain Using Functional Photoacoustic Imaging of Near-Infrared Voltage-Sensitive Dye.

Front Neurosci 2019 9;13:579. Epub 2019 Aug 9.

Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, United States.

Minimally-invasive monitoring of electrophysiological neural activities in real-time-that enables quantification of neural functions without a need for invasive craniotomy and the longer time constants of fMRI and PET-presents a very challenging yet significant task for neuroimaging. In this paper, we present functional PA (fPA) imaging of chemoconvulsant rat seizure model with intact scalp using a fluorescence quenching-based cyanine voltage-sensitive dye (VSD) characterized by a lipid vesicle model mimicking different levels of membrane potential variation. The framework also involves use of a near-infrared VSD delivered through the blood-brain barrier (BBB), opened by pharmacological modulation of adenosine receptor signaling. Our normalized time-frequency analysis presented VSD response in the seizure group significantly distinguishable from those of the control groups at sub-mm spatial resolution. Electroencephalogram (EEG) recording confirmed the changes of severity and frequency of brain activities, induced by chemoconvulsant seizures of the rat brain. The findings demonstrate that the near-infrared fPA VSD imaging is a promising tool for recording of brain activities through intact scalp, which would pave a way to its future translation in real time human brain imaging.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fnins.2019.00579DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6696882PMC
August 2019

Imager-4D: New Software for Viewing Dynamic PET Scans and Extracting Radiomic Parameters from PET Data.

J Digit Imaging 2019 12;32(6):1071-1080

The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 550 N. Broadway Suite 300, Baltimore, MD, 21205, USA.

Extensive research is currently being conducted into dynamic positron emission tomography (PET) acquisitions (including dynamic whole-body imaging) as well as extraction of radiomic features from imaging modalities. We describe a new PET viewing software known as Imager-4D that provides a facile means of viewing and analyzing dynamic PET data and obtaining associated quantitative metrics including radiomic parameters. The Imager-4D was programmed in the Java language utilizing the FX extensions. It is executable on any system for which a Java w/FX compliant virtual machine is available. The software incorporates the ability to view and analyze dynamic data acquired with different types of dynamic protocols. For image display, the program maintains a built-in library of 62 different lookup tables with monochromatic and full-color distributions. The Imager-4D provides multiple display layouts and can display fused images. Multiple methods of volume-of-interest (VOI) selection are available. Dynamic analysis features, such as image summation and full Patlak analysis, are also available. The user interface includes window width and level, blending, and zoom functionality. VOI sizes are adjustable and data from VOIs can either be displayed numerically or graphically within the software or exported. An example case of a 50-year-old woman with metastatic colorectal cancer and thyroiditis is included and demonstrates the steps for a user to obtain standard PET parameters, dynamic data, and radiomic features using selected VOIs. The Imager-4D represents a novel PET viewer that allows the user to view dynamic PET data, to derive dynamic and radiomic parameters from that data, and to combine dynamic data with radiomics ("dynomics"). The Imager-4D is available as a free download. This software has the potential to speed the adoption of advanced analysis of dynamic PET data into routine clinical use.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s10278-019-00255-7DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6841823PMC
December 2019

Machine Learning Methods for Optimal Radiomics-Based Differentiation Between Recurrence and Inflammation: Application to Nasopharyngeal Carcinoma Post-therapy PET/CT Images.

Mol Imaging Biol 2020 06;22(3):730-738

School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, Guangdong, China.

Purpose: To identify optimal machine learning methods for radiomics-based differentiation of local recurrence versus inflammation from post-treatment nasopharyngeal positron emission tomography/X-ray computed tomography (PET/CT) images.

Procedures: Seventy-six nasopharyngeal carcinoma (NPC) patients were enrolled (41/35 local recurrence/inflammation as confirmed by pathology). Four hundred eighty-seven radiomics features were extracted from PET images for each patient. The diagnostic performance was investigated for 42 cross-combinations derived from 6 feature selection methods and 7 classifiers. Of the original cohort, 70 % was applied for feature selection and classifier development, and the remaining 30 % used as an independent validation set. The diagnostic performance was evaluated using area under the ROC curve (AUC), test error, sensitivity, and specificity. Furthermore, the performance of the radiomics signatures against routine features was statistically compared using DeLong's method.

Results: The cross-combination fisher score (FSCR) + k-nearest neighborhood (KNN), FSCR + support vector machines with radial basis function kernel (RBF-SVM), FSCR + random forest (RF), and minimum redundancy maximum relevance (MRMR) + RBF-SVM outperformed others in terms of accuracy (AUC 0.883, 0.867, 0.892, 0.883; sensitivity 0.833, 0.864, 0.831, 0.750; specificity 1, 1, 0.873, 1) and reliability (test error 0.091, 0.136, 0.150, 0.136). Compared with conventional metrics, the radiomics signatures showed higher AUC values (0.867-0.892 vs. 0.817), though the differences were not statistically significant (p = 0.462-0.560).

Conclusion: This study identified the most accurate and reliable machine learning methods, which could enhance the application of radiomics methods in the precision of diagnosis of NPC.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11307-019-01411-9DOI Listing
June 2020

Optimized machine learning methods for prediction of cognitive outcome in Parkinson's disease.

Comput Biol Med 2019 08 28;111:103347. Epub 2019 Jun 28.

Department of Radiology, University of British Columbia, Vancouver, BC, Canada; Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada; Department of Radiology, Johns Hopkins University, Baltimore, MD, USA. Electronic address:

Background: Given the increasing recognition of the significance of non-motor symptoms in Parkinson's disease, we investigate the optimal use of machine learning methods for the prediction of the Montreal Cognitive Assessment (MoCA) score at year 4 from longitudinal data obtained at years 0 and 1.

Methods: We selected n = 184 PD subjects from the Parkinson's Progressive Marker Initiative (PPMI) database (93 features). A range of robust predictor algorithms (accompanied with automated machine learning hyperparameter tuning) and feature subset selector algorithms (FSSAs) were selected. We utilized 65%, 5% and 30% of patients in each arrangement for training, training validation and final testing respectively (10 randomized arrangements). For further testing, we enrolled 308 additional patients.

Results: First, we employed 10 predictor algorithms, provided with all 93 features; an error of 1.83 ± 0.13 was obtained by LASSOLAR (Least Absolute Shrinkage and Selection Operator - Least Angle Regression). Subsequently, we used feature subset selection followed by predictor algorithms. GA (Genetic Algorithm) selected 18 features; subsequently LOLIMOT (Local Linear Model Trees) reached an error of 1.70 ± 0.10. DE (Differential evolution) also selected 18 features and coupled with Thiel-Sen regression arrived at a similar performance. NSGAII (Non-dominated sorting genetic algorithm) yielded the best performance: it selected six vital features, which combined with LOLIMOT reached an error of 1.68 ± 0.12. Finally, using this last approach on independent test data, we reached an error of 1.65.

Conclusion: By employing appropriate optimization tools (including automated hyperparameter tuning), it is possible to improve prediction of cognitive outcome. Overall, we conclude that optimal utilization of FSSAs and predictor algorithms can produce very good prediction of cognitive outcome in PD patients.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiomed.2019.103347DOI Listing
August 2019

Direct attenuation correction of brain PET images using only emission data via a deep convolutional encoder-decoder (Deep-DAC).

Eur Radiol 2019 Dec 21;29(12):6867-6879. Epub 2019 Jun 21.

Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran.

Objective: To obtain attenuation-corrected PET images directly from non-attenuation-corrected images using a convolutional encoder-decoder network.

Methods: Brain PET images from 129 patients were evaluated. The network was designed to map non-attenuation-corrected (NAC) images to pixel-wise continuously valued measured attenuation-corrected (MAC) PET images via an encoder-decoder architecture. Image quality was evaluated using various evaluation metrics. Image quantification was assessed for 19 radiomic features in 83 brain regions as delineated using the Hammersmith atlas (n30r83). Reliability of measurements was determined using pixel-wise relative errors (RE; %) for radiomic feature values in reference MAC PET images.

Results: Peak signal-to-noise ratio (PSNR) and structural similarity index metric (SSIM) values were 39.2 ± 3.65 and 0.989 ± 0.006 for the external validation set, respectively. RE (%) of SUV was - 0.10 ± 2.14 for all regions, and only 3 of 83 regions depicted significant differences. However, the mean RE (%) of this region was 0.02 (range, - 0.83 to 1.18). SUV had mean RE (%) of - 3.87 ± 2.84 for all brain regions, and 17 regions in the brain depicted significant differences with respect to MAC images with a mean RE of - 3.99 ± 2.11 (range, - 8.46 to 0.76). Homogeneity amongst Haralick-based radiomic features had the highest number (20) of regions with significant differences with a mean RE (%) of 7.22 ± 2.99.

Conclusions: Direct AC of PET images using deep convolutional encoder-decoder networks is a promising technique for brain PET images. The proposed deep learning method shows significant potential for emission-based AC in PET images with applications in PET/MRI and dedicated brain PET scanners.

Key Points: • We demonstrate direct emission-based attenuation correction of PET images without using anatomical information. • We performed radiomics analysis of 83 brain regions to show robustness of direct attenuation correction of PET images. • Deep learning methods have significant promise for emission-based attenuation correction in PET images with potential applications in PET/MRI and dedicated brain PET scanners.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00330-019-06229-1DOI Listing
December 2019

Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features.

Eur J Radiol 2019 Apr 8;113:101-109. Epub 2019 Feb 8.

Department of Nuclear Medicine and PET Center, Aarhus University Hospital, Aarhus, Denmark.

Objective: We aimed to improve prediction of outcome for patients with colorectal liver metastases, via prognostic models incorporating PET-derived measures, including radiomic features that move beyond conventional standard uptake value (SUV) measures.

Patients And Methods: A range of parameters including volumetric and heterogeneity measures were derived from FDG PET images of 52 patients with colorectal intrahepatic-only metastases (29 males and 23 females; mean age 62.9 years [SD 9.8; range 32-82]). The patients underwent PET/CT imaging as part of the clinical workup prior to final decision on treatment. Univariate and multivariate models were implemented, which included statistical considerations (to discourage false discovery and overfitting), to predict overall survival (OS), progression-free survival (PFS) and event-free survival (EFS). Kaplan-Meier survival analyses were performed, where the subjects were divided into high-risk and low-risk groups, from which the hazard ratios (HR) were computed via Cox proportional hazards regression.

Results: Commonly-invoked SUV metrics performed relatively poorly for different prediction tasks (SUVmax HR = 1.48, 0.83 and 1.16; SUVpeak HR = 2.05, 1.93, and 1.64, for OS, PFS and EFS, respectively). By contrast, the number of liver metastases and metabolic tumor volume (MTV) each performed well (with respective HR values of 2.71, 2.61 and 2.42, and 2.62, 1.96 and 2.29, for OS, PFS and EFS). Total lesion glycolysis (TLG) also resulted in similar performance as MTV. Multivariate prognostic modeling incorporating different features (including those quantifying intra-tumor heterogeneity) resulted in further enhanced prediction. Specifically, HR values of 4.29, 4.02 and 3.20 (p-values = 0.00004, 0.0019 and 0.0002) were obtained for OS, PFS and EFS, respectively.

Conclusions: PET-derived measures beyond commonly invoked SUV parameters hold significant potential towards improved prediction of clinical outcome in patients with liver metastases, especially when utilizing multivariate models.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejrad.2019.02.006DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7507885PMC
April 2019

Artificial Neural Network-Based Prediction of Outcome in Parkinson's Disease Patients Using DaTscan SPECT Imaging Features.

Mol Imaging Biol 2019 12;21(6):1165-1173

Department of Radiology, Johns Hopkins University, Baltimore, MD, USA.

Purpose: Quantitative analysis of dopamine transporter (DAT) single-photon emission computed tomography (SPECT) images can enhance diagnostic confidence and improve their potential as a biomarker to monitor the progression of Parkinson's disease (PD). In the present work, we aim to predict motor outcome from baseline DAT SPECT imaging radiomic features and clinical measures using machine learning techniques.

Procedures: We designed and trained artificial neural networks (ANNs) to analyze the data from 69 patients within the Parkinson's Progressive Marker Initiative (PPMI) database. The task was to predict the unified PD rating scale (UPDRS) part III motor score in year 4 from 92 imaging features extracted on 12 different regions as well as 6 non-imaging measures at baseline (year 0). We first performed univariate screening (including the adjustment for false discovery) to select 4 regions each having 10 features with significant performance in classifying year 4 motor outcome into two classes of patients (divided by the UPDRS III threshold of 30). The leave-one-out strategy was then applied to train and test the ANNs for individual and combinations of features. The prediction statistics were calculated from 100 rounds of experiments, and the accuracy in appropriate prediction (classification of year 4 outcome) was quantified.

Results: Out of the baseline non-imaging features, only the UPDRS III (at year 0) was predictive, while multiple imaging features depicted significance. The different selected features reached a predictive accuracy of 70 % if used individually. Combining the top imaging features from the selected regions significantly improved the prediction accuracy to 75 % (p < 0.01). The combination of imaging features with the year 0 UPDRS III score also improved the prediction accuracy to 75 %.

Conclusion: This study demonstrated the added predictive value of radiomic features extracted from DAT SPECT images in serving as a biomarker for PD progression tracking.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11307-019-01334-5DOI Listing
December 2019

Economic sanctions are against basic human rights on health.

Eur J Nucl Med Mol Imaging 2019 May 28;46(5):1046-1047. Epub 2019 Jan 28.

Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00259-019-4269-3DOI Listing
May 2019