1
|
Zhang L, Fan M, Li L. Efficient estimation of pharmacokinetic parameters from breast dynamic contrast-enhanced MRI based on a convolutional neural network for predicting molecular subtypes. Phys Med Biol 2023; 68:245001. [PMID: 37983902 DOI: 10.1088/1361-6560/ad0e39] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2023] [Accepted: 11/20/2023] [Indexed: 11/22/2023]
Abstract
Objective. Tracer kinetic models allow for estimating pharmacokinetic (PK) parameters, which are related to pathological characteristics, from breast dynamic contrast-enhanced magnetic resonance imaging. However, existing tracer kinetic models subject to inaccuracy are time-consuming for PK parameters estimation. This study aimed to accurately and efficiently estimate PK parameters for predicting molecular subtypes based on convolutional neural network (CNN).Approach. A CNN integrating global and local features (GL-CNN) was trained using synthetic data where known PK parameters map was used as the ground truth, and subsequently used to directly estimate PK parameters (volume transfer constantKtransand flux rate constantKep) map. The accuracy assessed by the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and concordance correlation coefficient (CCC) was compared between the GL-CNN and Tofts-based PK parameters in synthetic data. Radiomic features were calculated from the PK parameters map in 208 breast tumors. A random forest classifier was constructed to predict molecular subtypes using a discovery cohort (n= 144). The diagnostic performance evaluated on a validation cohort (n= 64) using the area under the receiver operating characteristic curve (AUC) was compared between the GL-CNN and Tofts-based PK parameters.Main results. The average PSNR (48.8884), SSIM (0.9995), and CCC (0.9995) between the GL-CNN-basedKtransmap and ground truth were significantly higher than those between the Tofts-basedKtransmap and ground truth. The GL-CNN-basedKtransobtained significantly better diagnostic performance (AUCs = 0.7658 and 0.8528) than the Tofts-basedKtransfor luminal B and HER2 tumors. The GL-CNN method accelerated the computation by speed approximately 79 times compared to the Tofts method for the whole breast of all patients.Significance. Our results indicate that the GL-CNN method can be used to accurately and efficiently estimate PK parameters for predicting molecular subtypes.
Collapse
Affiliation(s)
- Liangliang Zhang
- School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, 310018, People's Republic of China
- School of Computer and Information, Anqing Normal University, Anqing, 246133, People's Republic of China
| | - Ming Fan
- Institute of Intelligent Biomedicine, Hangzhou Dianzi University, Hangzhou, 310018, People's Republic of China
| | - Lihua Li
- School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, 310018, People's Republic of China
- Institute of Intelligent Biomedicine, Hangzhou Dianzi University, Hangzhou, 310018, People's Republic of China
| |
Collapse
|
2
|
Hellström M, Löfstedt T, Garpebring A. Denoising and uncertainty estimation in parameter mapping with approximate Bayesian deep image priors. Magn Reson Med 2023; 90:2557-2571. [PMID: 37582257 DOI: 10.1002/mrm.29823] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2022] [Revised: 06/26/2023] [Accepted: 07/18/2023] [Indexed: 08/17/2023]
Abstract
PURPOSE To mitigate the problem of noisy parameter maps with high uncertainties by casting parameter mapping as a denoising task based on Deep Image Priors. METHODS We extend the concept of denoising with Deep Image Prior (DIP) into parameter mapping by treating the output of an image-generating network as a parametrization of tissue parameter maps. The method implicitly denoises the parameter mapping process by filtering low-level image features with an untrained convolutional neural network (CNN). Our implementation includes uncertainty estimation from Bernoulli approximate variational inference, implemented with MC dropout, which provides model uncertainty in each voxel of the denoised parameter maps. The method is modular, so the specifics of different applications (e.g., T1 mapping) separate into application-specific signal equation blocks. We evaluate the method on variable flip angle T1 mapping, multi-echo T2 mapping, and apparent diffusion coefficient mapping. RESULTS We found that deep image prior adapts successfully to several applications in parameter mapping. In all evaluations, the method produces noise-reduced parameter maps with decreased uncertainty compared to conventional methods. The downsides of the proposed method are the long computational time and the introduction of some bias from the denoising prior. CONCLUSION DIP successfully denoise the parameter mapping process and applies to several applications with limited hyperparameter tuning. Further, it is easy to implement since DIP methods do not use network training data. Although time-consuming, uncertainty information from MC dropout makes the method more robust and provides useful information when properly calibrated.
Collapse
Affiliation(s)
- Max Hellström
- Department of Radiation Sciences, Umeå University, Umeå, Sweden
| | - Tommy Löfstedt
- Department of Radiation Sciences, Umeå University, Umeå, Sweden
- Department of Computing Science, Umeå University, Umeå, Sweden
| | | |
Collapse
|
3
|
Ottens T, Barbieri S, Orton MR, Klaassen R, van Laarhoven HW, Crezee H, Nederveen AJ, Zhen X, Gurney-Champion OJ. Deep learning DCE-MRI parameter estimation: application in pancreatic cancer. Med Image Anal 2022; 80:102512. [DOI: 10.1016/j.media.2022.102512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2021] [Revised: 05/04/2022] [Accepted: 06/06/2022] [Indexed: 10/18/2022]
|
4
|
van Herten RLM, Chiribiri A, Breeuwer M, Veta M, Scannell CM. Physics-informed neural networks for myocardial perfusion MRI quantification. Med Image Anal 2022; 78:102399. [PMID: 35299005 PMCID: PMC9051528 DOI: 10.1016/j.media.2022.102399] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2020] [Revised: 01/07/2022] [Accepted: 02/18/2022] [Indexed: 11/19/2022]
Abstract
Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data with multi-compartment exchange models is desirable, as they are physiologically plausible and resolve directly for blood flow and microvascular function. However, the reliability of model fitting is limited by the low signal-to-noise ratio, temporal resolution, and acquisition length. This may result in inaccurate parameter estimates. This study introduces physics-informed neural networks (PINNs) as a means to perform myocardial perfusion MR quantification, which provides a versatile scheme for the inference of kinetic parameters. These neural networks can be trained to fit the observed perfusion MR data while respecting the underlying physical conservation laws described by a multi-compartment exchange model. Here, we provide a framework for the implementation of PINNs in myocardial perfusion MR. The approach is validated both in silico and in vivo. In the in silico study, an overall decrease in mean-squared error with the ground-truth parameters was observed compared to a standard non-linear least squares fitting approach. The in vivo study demonstrates that the method produces parameter values comparable to those previously found in literature, as well as providing parameter maps which match the clinical diagnosis of patients.
Collapse
Affiliation(s)
- Rudolf L M van Herten
- Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom
| | - Marcel Breeuwer
- Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands; Philips Healthcare, Best, the Netherlands
| | - Mitko Veta
- Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Cian M Scannell
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| |
Collapse
|
5
|
Meyer‐Base A, Morra L, Tahmassebi A, Lobbes M, Meyer‐Base U, Pinker K. AI-Enhanced Diagnosis of Challenging Lesions in Breast MRI: A Methodology and Application Primer. J Magn Reson Imaging 2021; 54:686-702. [PMID: 32864782 PMCID: PMC8451829 DOI: 10.1002/jmri.27332] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2020] [Revised: 07/30/2020] [Accepted: 07/31/2020] [Indexed: 12/11/2022] Open
Abstract
Computer-aided diagnosis (CAD) systems have become an important tool in the assessment of breast tumors with magnetic resonance imaging (MRI). CAD systems can be used for the detection and diagnosis of breast tumors as a "second opinion" review complementing the radiologist's review. CAD systems have many common parts, such as image preprocessing, tumor feature extraction, and data classification that are mostly based on machine-learning (ML) techniques. In this review article, we describe applications of ML-based CAD systems in MRI covering the detection of diagnostically challenging lesions of the breast such as nonmass enhancing (NME) lesions, and furthermore discuss how multiparametric MRI and radiomics can be applied to the study of NME, including prediction of response to neoadjuvant chemotherapy (NAC). Since ML has been widely used in the medical imaging community, we provide an overview about the state-of-the-art and novel techniques applied as classifiers to CAD systems. The differences in the CAD systems in MRI of the breast for several standard and novel applications for NME are explained in detail to provide important examples, illustrating: 1) CAD for detection and diagnosis, 2) CAD in multiparametric imaging, 3) CAD in NAC, and 4) breast cancer radiomics. We aim to provide a comparison between these CAD applications and to illustrate a global view on intelligent CAD systems based on machine and deep learning in MRI of the breast. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 2.
Collapse
Affiliation(s)
- Anke Meyer‐Base
- Department of Scientific ComputingFlorida State UniversityTallahasseeFloridaUSA
- Department of Radiology, Maastricht Medical CenterUniversity of MaastrichtMaastrichtNetherlands
| | - Lia Morra
- Department of Control and Computer EngineeringPolitecnico di TorinoTorinoItaly
| | | | - Marc Lobbes
- Department of Radiology, Maastricht Medical CenterUniversity of MaastrichtMaastrichtNetherlands
- GROW School for Oncology and Developmental BiologyMaastrichtNetherlands
- Zuyderland Medical Center, dep of Medical ImagingSittard‐GeleenNetherlands
| | - Uwe Meyer‐Base
- Department of Electrical and Computer EngineeringFlorida A&M University and Florida State UniversityTallahasseeFloridaUSA
| | - Katja Pinker
- Department of Radiology, Breast Imaging ServiceMemorial Sloan‐Kettering Cancer CenterNew YorkNew YorkUSA
- Department of Biomedical Imaging and Image‐Guided Therapy, Division of Molecular and Gender ImagingMedical University of ViennaViennaAustria
| |
Collapse
|
6
|
Lee JH, Yoo GS, Yoon YC, Park HC, Kim HS. Diffusion-weighted and dynamic contrast-enhanced magnetic resonance imaging after radiation therapy for bone metastases in patients with hepatocellular carcinoma. Sci Rep 2021; 11:10459. [PMID: 34001997 PMCID: PMC8128906 DOI: 10.1038/s41598-021-90065-1] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2020] [Accepted: 05/04/2021] [Indexed: 12/24/2022] Open
Abstract
The objectives of this study were to assess changes in apparent diffusion coefficient (ADC) and dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) parameters after radiation therapy (RT) for bone metastases from hepatocellular carcinoma (HCC) and to evaluate their prognostic value. This prospective study was approved by the Institutional Review Board. Fourteen patients with HCC underwent RT (30 Gy in 10 fractions once daily) for bone metastases. The ADC and DCE-MRI parameters and the volume of the target lesions were measured before (baseline) and one month after RT (post-RT). The Wilcoxon signed-rank test was used to compare the parameters between the baseline and post-RT MRI. The parameters were compared between patients with or without disease progression in RT fields using the Mann–Whitney test. Intraclass correlation coefficients were used to evaluate the interobserver agreement. The medians of the ADC, rate constant [kep], and volume fraction of the extravascular extracellular matrix [ve] in the baseline and post-RT MRI were 0.67 (range 0.61–0.72) and 0.75 (range 0.63–1.43) (× 10–3 mm2/s) (P = 0.027), 836.33 (range 301.41–1082.32) and 335.80 (range 21.86–741.87) (× 10–3/min) (P = 0.002), and 161.54 (range 128.38–410.13) and 273.99 (range 181.39–1216.95) (× 10–3) (P = 0.027), respectively. The medians of the percent change in the ADC of post-RT MRI in patients with progressive disease and patients without progressive disease were − 1.35 (range − 6.16 to 6.79) and + 46.71 (range 7.71–112.81) (%) (P = 0.011), respectively. The interobserver agreements for all MRI parameters were excellent (intraclass correlation coefficients > 0.8). In conclusion, the ADC, kep, and ve of bone metastases changed significantly after RT. The percentage change in the ADC was closely related to local tumor progression.
Collapse
Affiliation(s)
- Ji Hyun Lee
- Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Gyu Sang Yoo
- Department of Radiation Oncology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Young Cheol Yoon
- Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea.
| | - Hee Chul Park
- Department of Radiation Oncology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea.
| | - Hyun Su Kim
- Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea
| |
Collapse
|
7
|
Daviller C, Boutelier T, Giri S, Ratiney H, Jolly MP, Vallée JP, Croisille P, Viallon M. Direct Comparison of Bayesian and Fermi Deconvolution Approaches for Myocardial Blood Flow Quantification: In silico and Clinical Validations. Front Physiol 2021; 12:483714. [PMID: 33912066 PMCID: PMC8072361 DOI: 10.3389/fphys.2021.483714] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2019] [Accepted: 03/08/2021] [Indexed: 11/13/2022] Open
Abstract
Cardiac magnetic resonance myocardial perfusion imaging can detect coronary artery disease and is an alternative to single-photon emission computed tomography or positron emission tomography. However, the complex, non-linear MR signal and the lack of robust quantification of myocardial blood flow have hindered its widespread clinical application thus far. Recently, a new Bayesian approach was developed for brain imaging and evaluation of perfusion indexes (Kudo et al., 2014). In addition to providing accurate perfusion measurements, this probabilistic approach appears more robust than previous approaches, particularly due to its insensitivity to bolus arrival delays. We assessed the performance of this approach against a well-known and commonly deployed model-independent method based on the Fermi function for cardiac magnetic resonance myocardial perfusion imaging. The methods were first evaluated for accuracy and precision using a digital phantom to test them against the ground truth; next, they were applied in a group of coronary artery disease patients. The Bayesian method can be considered an appropriate model-independent method with which to estimate myocardial blood flow and delays. The digital phantom comprised a set of synthetic time-concentration curve combinations generated with a 2-compartment exchange model and a realistic combination of perfusion indexes, arterial input dynamics, noise and delays collected from the clinical dataset. The myocardial blood flow values estimated with the two methods showed an excellent correlation coefficient (r2 > 0.9) under all noise and delay conditions. The Bayesian approach showed excellent robustness to bolus arrival delays, with a similar performance to Fermi modeling when delays were considered. Delays were better estimated with the Bayesian approach than with Fermi modeling. An in vivo analysis of coronary artery disease patients revealed that the Bayesian approach had an excellent ability to distinguish between abnormal and normal myocardium. The Bayesian approach was able to discriminate not only flows but also delays with increased sensitivity by offering a clearly enlarged range of distribution for the physiologic parameters.
Collapse
Affiliation(s)
- Clément Daviller
- Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS, UMR 5220, U1294, Lyon, France
| | - Timothé Boutelier
- Department of Research and Innovation, Olea Medical, La Ciotat, France
| | - Shivraman Giri
- Siemens Medical Solutions USA, Inc., Boston, MA, United States
| | - Hélène Ratiney
- Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS, UMR 5220, U1294, Lyon, France
| | | | - Jean-Paul Vallée
- Division of Radiology, Faculty of Medicine, Geneva University Hospitals, University of Geneva, Geneva, Switzerland
| | - Pierre Croisille
- Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS, UMR 5220, U1294, Lyon, France.,Department of Radiology, CHU de Saint-Etienne, University of Lyon, UJM-Saint-Etienne, Saint-Étienne, France
| | - Magalie Viallon
- Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS, UMR 5220, U1294, Lyon, France.,Department of Radiology, CHU de Saint-Etienne, University of Lyon, UJM-Saint-Etienne, Saint-Étienne, France
| |
Collapse
|
8
|
Löfstedt T, Hellström M, Bylund M, Garpebring A. Bayesian non-linear regression with spatial priors for noise reduction and error estimation in quantitative MRI with an application in T1 estimation. Phys Med Biol 2020; 65:225036. [PMID: 32947277 DOI: 10.1088/1361-6560/abb9f5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
PURPOSE To develop a method that can reduce and estimate uncertainty in quantitative MR parameter maps without the need for hand-tuning of any hyperparameters. METHODS We present an estimation method where uncertainties are reduced by incorporating information on spatial correlations between neighbouring voxels. The method is based on a Bayesian hierarchical non-linear regression model, where the parameters of interest are sampled, using Markov chain Monte Carlo (MCMC), from a high-dimensional posterior distribution with a spatial prior. The degree to which the prior affects the model is determined by an automatic hyperparameter search using an information criterion and is, therefore, free from manual user-dependent tuning. The samples obtained further provide a convenient means to obtain uncertainties in both voxels and regions. The developed method was evaluated on T 1 estimations based on the variable flip angle method. RESULTS The proposed method delivers noise-reduced T 1 parameter maps with associated error estimates by combining MCMC sampling, the widely applicable information criterion, and total variation-based denoising. The proposed method results in an overall decrease in estimation error when compared to conventional voxel-wise maximum likelihood estimation. However, this comes with an increased bias in some regions, predominately at tissue interfaces, as well as an increase in computational time. CONCLUSIONS This study provides a method that generates more precise estimates compared to the conventional method, without incorporating user subjectivity, and with the added benefit of uncertainty estimation.
Collapse
Affiliation(s)
- Tommy Löfstedt
- Department of Radiation Sciences, Umeå University, Umeå, Sweden. Department of Computing Science, Umeå University, Umeå, Sweden. Equally contributing authors
| | | | | | | |
Collapse
|
9
|
Ghodasara S, Chen Y, Pahwa S, Griswold MA, Seiberlich N, Wright KL, Gulani V. Quantifying Perfusion Properties with DCE-MRI Using a Dictionary Matching Approach. Sci Rep 2020; 10:10210. [PMID: 32576843 PMCID: PMC7311534 DOI: 10.1038/s41598-020-66985-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2019] [Accepted: 05/25/2020] [Indexed: 12/18/2022] Open
Abstract
Perfusion properties can be estimated from pharmacokinetic models applied to DCE-MRI data using curve fitting algorithms; however, these suffer from drawbacks including the local minimum problem and substantial computational time. Here, a dictionary matching approach is proposed as an alternative. Curve fitting and dictionary matching were applied to simulated data using the dual-input single-compartment model with known perfusion property values and 5 in vivo DCE-MRI datasets. In simulation at SNR 60 dB, the dictionary estimate had a mean percent error of 0.4-1.0% for arterial fraction, 0.5-1.4% for distribution volume, and 0.0% for mean transit time. The curve fitting estimate had a mean percent error of 1.1-2.1% for arterial fraction, 0.5-1.3% for distribution volume, and 0.2-1.8% for mean transit time. In vivo, dictionary matching and curve fitting showed no statistically significant differences in any of the perfusion property measurements in any of the 10 ROIs between the methods. In vivo, the dictionary method performed over 140-fold faster than curve fitting, obtaining whole volume perfusion maps in just over 10 s. This study establishes the feasibility of using a dictionary matching approach as a new and faster way of estimating perfusion properties from pharmacokinetic models in DCE-MRI.
Collapse
Affiliation(s)
- Satyam Ghodasara
- School of Medicine, Case Western Reserve University, Cleveland, Ohio, USA
| | - Yong Chen
- Department of Radiology, University of North Carolina, Chapel Hill, North Carolina, USA
| | - Shivani Pahwa
- School of Medicine, Case Western Reserve University, Cleveland, Ohio, USA
- Department of Radiology, Case Western Reserve University, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Mark A Griswold
- School of Medicine, Case Western Reserve University, Cleveland, Ohio, USA
- Department of Radiology, Case Western Reserve University, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA
| | - Nicole Seiberlich
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| | - Katherine L Wright
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| | - Vikas Gulani
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA.
| |
Collapse
|
10
|
Bliesener Y, Acharya J, Nayak KS. Efficient DCE-MRI Parameter and Uncertainty Estimation Using a Neural Network. IEEE TRANSACTIONS ON MEDICAL IMAGING 2020; 39:1712-1723. [PMID: 31794389 PMCID: PMC8887912 DOI: 10.1109/tmi.2019.2953901] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Quantitative DCE-MRI provides voxel-wise estimates of tracer-kinetic parameters that are valuable in the assessment of health and disease. These maps suffer from many known sources of variability. This variability is expensive to compute using current methods, and is typically not reported. Here, we demonstrate a novel approach for simultaneous estimation of tracer-kinetic parameters and their uncertainty due to intrinsic characteristics of the tracer-kinetic model, with very low computation time. We train and use a neural network to estimate the approximate joint posterior distribution of tracer-kinetic parameters. Uncertainties are estimated for each voxel and are specific to the patient, exam, and lesion. We demonstrate the methods' ability to produce accurate tracer-kinetic maps. We compare predicted parameter ranges with uncertainties introduced by noise and by differences in post-processing in a digital reference object. The predicted parameter ranges correlate well with tracer-kinetic parameter ranges observed across different noise realizations and regression algorithms. We also demonstrate the value of this approach to differentiate significant from insignificant changes in brain tumor pharmacokinetics over time. This is achieved by enforcing consistency in resolving model singularities in the applied tracer-kinetic model.
Collapse
|
11
|
Scannell CM, Chiribiri A, Villa ADM, Breeuwer M, Lee J. Hierarchical Bayesian myocardial perfusion quantification. Med Image Anal 2020; 60:101611. [PMID: 31760191 PMCID: PMC6880627 DOI: 10.1016/j.media.2019.101611] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2018] [Revised: 11/07/2019] [Accepted: 11/08/2019] [Indexed: 01/25/2023]
Abstract
Myocardial blood flow can be quantified from dynamic contrast-enhanced magnetic resonance (MR) images through the fitting of tracer-kinetic models to the observed imaging data. The use of multi-compartment exchange models is desirable as they are physiologically motivated and resolve directly for both blood flow and microvascular function. However, the parameter estimates obtained with such models can be unreliable. This is due to the complexity of the models relative to the observed data which is limited by the low signal-to-noise ratio, the temporal resolution, the length of the acquisitions and other complex imaging artefacts. In this work, a Bayesian inference scheme is proposed which allows the reliable estimation of the parameters of the two-compartment exchange model from myocardial perfusion MR data. The Bayesian scheme allows the incorporation of prior knowledge on the physiological ranges of the model parameters and facilitates the use of the additional information that neighbouring voxels are likely to have similar kinetic parameter values. Hierarchical priors are used to avoid making a priori assumptions on the health of the patients. We provide both a theoretical introduction to Bayesian inference for tracer-kinetic modelling and specific implementation details for this application. This approach is validated in both in silico and in vivo settings. In silico, there was a significant reduction in mean-squared error with the ground-truth parameters using Bayesian inference as compared to using the standard non-linear least squares fitting. When applied to patient data the Bayesian inference scheme returns parameter values that are in-line with those previously reported in the literature, as well as giving parameter maps that match the independant clinical diagnosis of those patients.
Collapse
Affiliation(s)
- Cian M Scannell
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom; The Alan Turing Institute London, United Kingdom.
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| | - Adriana D M Villa
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| | - Marcel Breeuwer
- Philips Healthcare, Best, the Netherlands; Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands.
| | - Jack Lee
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| |
Collapse
|
12
|
Bartoš M, Rajmic P, Šorel M, Mangová M, Keunen O, Jiřík R. Spatially regularized estimation of the tissue homogeneity model parameters in DCE-MRI using proximal minimization. Magn Reson Med 2019; 82:2257-2272. [PMID: 31317577 DOI: 10.1002/mrm.27874] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2019] [Revised: 04/24/2019] [Accepted: 05/29/2019] [Indexed: 12/26/2022]
Abstract
PURPOSE The Tofts and the extended Tofts models are the pharmacokinetic models commonly used in dynamic contrast-enhanced MRI (DCE-MRI) perfusion analysis, although they do not provide two important biological markers, namely, the plasma flow and the permeability-surface area product. Estimates of such markers are possible using advanced pharmacokinetic models describing the vascular distribution phase, such as the tissue homogeneity model. However, the disadvantage of the advanced models lies in biased and uncertain estimates, especially when the estimates are computed voxelwise. The goal of this work is to improve the reliability of the estimates by including information from neighboring voxels. THEORY AND METHODS Information from the neighboring voxels is incorporated in the estimation process through spatial regularization in the form of total variation. The spatial regularization is applied on five maps of perfusion parameters estimated using the tissue homogeneity model. Since the total variation is not differentiable, two proximal techniques of convex optimization are used to solve the problem numerically. RESULTS The proposed algorithm helps to reduce noise in the estimated perfusion-parameter maps together with improving accuracy of the estimates. These conclusions are proved using a numerical phantom. In addition, experiments on real data show improved spatial consistency and readability of perfusion maps without considerable lowering of the quality of fit. CONCLUSION The reliability of the DCE-MRI perfusion analysis using the tissue homogeneity model can be improved by employing spatial regularization. The proposed utilization of modern optimization techniques implies only slightly higher computational costs compared to the standard approach without spatial regularization.
Collapse
Affiliation(s)
- Michal Bartoš
- The Czech Academy of Sciences, Institute of Information Theory and Automation, Prague, Czech Republic
| | - Pavel Rajmic
- SPLab, Department of Telecommunications, FEEC, Brno University of Technology, Brno, Czech Republic
| | - Michal Šorel
- The Czech Academy of Sciences, Institute of Information Theory and Automation, Prague, Czech Republic
| | - Marie Mangová
- SPLab, Department of Telecommunications, FEEC, Brno University of Technology, Brno, Czech Republic
| | - Olivier Keunen
- Norlux Neuro-Oncology Laboratory, Department of Oncology, Luxembourg Institute of Health, Luxembourg, Luxembourg
| | - Radovan Jiřík
- The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic
| |
Collapse
|
13
|
Ulas C, Das D, Thrippleton MJ, Valdés Hernández MDC, Armitage PA, Makin SD, Wardlaw JM, Menze BH. Convolutional Neural Networks for Direct Inference of Pharmacokinetic Parameters: Application to Stroke Dynamic Contrast-Enhanced MRI. Front Neurol 2019; 9:1147. [PMID: 30671015 PMCID: PMC6331464 DOI: 10.3389/fneur.2018.01147] [Citation(s) in RCA: 30] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2018] [Accepted: 12/11/2018] [Indexed: 12/12/2022] Open
Abstract
Background and Purpose: The T1-weighted dynamic contrast enhanced (DCE)-MRI is an imaging technique that provides a quantitative measure of pharmacokinetic (PK) parameters characterizing microvasculature of tissues. For the present study, we propose a new machine learning (ML) based approach to directly estimate the PK parameters from the acquired DCE-MRI image-time series that is both more robust and faster than conventional model fitting. Materials and Methods: We specifically utilize deep convolutional neural networks (CNNs) to learn the mapping between the image-time series and corresponding PK parameters. DCE-MRI datasets acquired from 15 patients with clinically evident mild ischaemic stroke were used in the experiments. Training and testing were carried out based on leave-one-patient-out cross- validation. The parameter estimates obtained by the proposed CNN model were compared against the two tracer kinetic models: (1) Patlak model, (2) Extended Tofts model, where the estimation of model parameters is done via voxelwise linear and nonlinear least squares fitting respectively. Results: The trained CNN model is able to yield PK parameters which can better discriminate different brain tissues, including stroke regions. The results also demonstrate that the model generalizes well to new cases even if a subject specific arterial input function (AIF) is not available for the new data. Conclusion: A ML-based model can be used for direct inference of the PK parameters from DCE image series. This method may allow fast and robust parameter inference in population DCE studies. Parameter inference on a 3D volume-time series takes only a few seconds on a GPU machine, which is significantly faster compared to conventional non-linear least squares fitting.
Collapse
Affiliation(s)
- Cagdas Ulas
- Department of Computer Science, Technische Universität München, Munich, Germany
| | - Dhritiman Das
- Department of Computer Science, Technische Universität München, Munich, Germany.,GE Global Research, Munich, Germany
| | - Michael J Thrippleton
- Department of Neuroimaging Sciences, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom
| | - Maria Del C Valdés Hernández
- Department of Neuroimaging Sciences, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom
| | - Paul A Armitage
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, United Kingdom
| | - Stephen D Makin
- Department of Neuroimaging Sciences, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom
| | - Joanna M Wardlaw
- Department of Neuroimaging Sciences, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom
| | - Bjoern H Menze
- Department of Computer Science, Technische Universität München, Munich, Germany.,Institute of Advanced Study, Technische Universität München, Munich, Germany
| |
Collapse
|
14
|
Kim HS, Yoon YC, Kwon S, Lee JH, Ahn S, Ahn HS. Dynamic Contrast-enhanced MR Imaging Parameters in Bone Metastases from Non–Small Cell Lung Cancer: Comparison between Lesions with and Lesions without Epidermal Growth Factor Receptor Mutation in Primary Lung Cancer. Radiology 2017; 284:815-823. [DOI: 10.1148/radiol.2017162336] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Affiliation(s)
- Hyun Su Kim
- From the Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Ilwon-Ro, Gangnam-gu, Seoul 135-710, Korea (H.S.K., Y.C.Y., S.K., J.H.L.); Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, Korea (Y.C.Y.); and Statistics and Data Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Korea (S.A., H.S.A.)
| | - Young Cheol Yoon
- From the Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Ilwon-Ro, Gangnam-gu, Seoul 135-710, Korea (H.S.K., Y.C.Y., S.K., J.H.L.); Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, Korea (Y.C.Y.); and Statistics and Data Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Korea (S.A., H.S.A.)
| | - Soyi Kwon
- From the Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Ilwon-Ro, Gangnam-gu, Seoul 135-710, Korea (H.S.K., Y.C.Y., S.K., J.H.L.); Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, Korea (Y.C.Y.); and Statistics and Data Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Korea (S.A., H.S.A.)
| | - Ji Hyun Lee
- From the Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Ilwon-Ro, Gangnam-gu, Seoul 135-710, Korea (H.S.K., Y.C.Y., S.K., J.H.L.); Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, Korea (Y.C.Y.); and Statistics and Data Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Korea (S.A., H.S.A.)
| | - Soohyun Ahn
- From the Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Ilwon-Ro, Gangnam-gu, Seoul 135-710, Korea (H.S.K., Y.C.Y., S.K., J.H.L.); Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, Korea (Y.C.Y.); and Statistics and Data Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Korea (S.A., H.S.A.)
| | - Hyeon Seon Ahn
- From the Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Ilwon-Ro, Gangnam-gu, Seoul 135-710, Korea (H.S.K., Y.C.Y., S.K., J.H.L.); Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, Korea (Y.C.Y.); and Statistics and Data Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Korea (S.A., H.S.A.)
| |
Collapse
|
15
|
Li Z, Ai T, Hu Y, Yan X, Nickel MD, Xu X, Xia L. Application of whole-lesion histogram analysis of pharmacokinetic parameters in dynamic contrast-enhanced MRI of breast lesions with the CAIPIRINHA-Dixon-TWIST-VIBE technique. J Magn Reson Imaging 2017; 47:91-96. [PMID: 28577335 DOI: 10.1002/jmri.25762] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2017] [Accepted: 04/26/2017] [Indexed: 12/23/2022] Open
Abstract
PURPOSE To investigate the application of whole-lesion histogram analysis of pharmacokinetic parameters for differentiating malignant from benign breast lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS In all, 92 women with 97 breast lesions (26 benign and 71 malignant lesions) were enrolled in this study. Patients underwent dynamic breast MRI at 3T using a prototypical CAIPIRINHA-Dixon-TWIST-VIBE (CDT-VIBE) sequence and a subsequent surgery or biopsy. Inflow rate of the agent between plasma and interstitium (Ktrans ), outflow rate of agent between interstitium and plasma (Kep ), extravascular space volume per unit volume of tissue (ve ) including mean value, 25th/50th/75th/90th percentiles, skewness, and kurtosis were then calculated based on the whole lesion. A single-sample Kolmogorov-Smirnov test, paired t-test, and receiver operating characteristic curve (ROC) analysis were used for statistical analysis. RESULTS Malignant breast lesions had significantly higher Ktrans , Kep , and lower ve in mean values, 25th/50th/75th/90th percentiles, and significantly higher skewness of ve than benign breast lesions (all P < 0.05). There was no significant difference in kurtosis values between malignant and benign breast lesions (all P > 0.05). The 90th percentile of Ktrans , the 90th percentile of Kep , and the 50th percentile of ve showed the greatest areas under the ROC curve (AUC) for each pharmacokinetic parameter derived from DCE-MRI. The 90th percentile of Kep achieved the highest AUC value (0.927) among all histogram-derived values. CONCLUSION The whole-lesion histogram analysis of pharmacokinetic parameters can improve the diagnostic accuracy of breast DCE-MRI with the CDT-VIBE technique. The 90th percentile of Kep may be the best indicator in differentiation between malignant and benign breast lesions. LEVEL OF EVIDENCE 4 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2018;47:91-96.
Collapse
Affiliation(s)
- Zhiwei Li
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, P.R. China
| | - Tao Ai
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, P.R. China
| | - Yiqi Hu
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, P.R. China
| | - Xu Yan
- MR Collaboration NE Asia, Siemens Healthcare, Shanghai, P.R. China
| | | | - Xiao Xu
- GE Healthcare Life Science, Shanghai, P.R. China
| | - Liming Xia
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, P.R. China
| |
Collapse
|
16
|
Ramos-Llorden G, den Dekker AJ, Sijbers J. Partial Discreteness: A Novel Prior for Magnetic Resonance Image Reconstruction. IEEE TRANSACTIONS ON MEDICAL IMAGING 2017; 36:1041-1053. [PMID: 28026759 DOI: 10.1109/tmi.2016.2645122] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/22/2023]
Abstract
An important factor influencing the quality of magnetic resonance (MR) images is the reconstruction method that is employed, and specifically, the type of prior knowledge that is exploited during reconstruction. In this work, we introduce a new type of prior knowledge, partial discreteness (PD), where a small number of regions in the image are assumed to be homogeneous and can be well represented by a constant magnitude. In particular, we mathematically formalize the partial discreteness property based on a Gaussian Mixture Model (GMM) and derive a partial discreteness image representation that characterizes the salient features of partially discrete images: a constant intensity in homogeneous areas and texture in heterogeneous areas. The partial discreteness representation is then used to construct a novel prior dedicated to the reconstruction of partially discrete MR images. The strength of the proposed prior is demonstrated on various simulated and real k-space data-based experiments with partially discrete images. Results demonstrate that the PD algorithm performs competitively with state-of-the-art reconstruction methods, being flexible and easy to implement.
Collapse
|
17
|
A comparative simulation study of bayesian fitting approaches to intravoxel incoherent motion modeling in diffusion-weighted MRI. Magn Reson Med 2017; 78:2373-2387. [DOI: 10.1002/mrm.26598] [Citation(s) in RCA: 47] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2016] [Revised: 12/08/2016] [Accepted: 12/13/2016] [Indexed: 01/27/2023]
|
18
|
Farsani ZA, Schmid VJ. Maximum Entropy Approach in Dynamic Contrast-Enhanced Magnetic Resonance Imaging. Methods Inf Med 2017; 56:461-468. [PMID: 29582918 DOI: 10.3414/me17-01-0027] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
BACKGROUND In the estimation of physiological kinetic parameters from Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) data, the determination of the arterial input function (AIF) plays a key role. OBJECTIVES This paper proposes a Bayesian method to estimate the physiological parameters of DCE-MRI along with the AIF in situations, where no measurement of the AIF is available. METHODS In the proposed algorithm, the maximum entropy method (MEM) is combined with the maximum a posterior approach (MAP). To this end, MEM is used to specify a prior probability distribution of the unknown AIF. The ability of this method to estimate the AIF is validated using the Kullback-Leibler divergence. Subsequently, the kinetic parameters can be estimated with MAP. The proposed algorithm is evaluated with a data set from a breast cancer MRI study. RESULTS The application shows that the AIF can reliably be determined from the DCE-MRI data using MEM. Kinetic parameters can be estimated subsequently. CONCLUSIONS The maximum entropy method is a powerful tool to reconstructing images from many types of data. This method is useful for generating the probability distribution based on given information. The proposed method gives an alternative way to assess the input function from the existing data. The proposed method allows a good fit of the data and therefore a better estimation of the kinetic parameters. In the end, this allows for a more reliable use of DCE-MRI.
Collapse
|
19
|
Khalifa F, Soliman A, El-Baz A, Abou El-Ghar M, El-Diasty T, Gimel'farb G, Ouseph R, Dwyer AC. Models and methods for analyzing DCE-MRI: a review. Med Phys 2015; 41:124301. [PMID: 25471985 DOI: 10.1118/1.4898202] [Citation(s) in RCA: 199] [Impact Index Per Article: 22.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Abstract
PURPOSE To present a review of most commonly used techniques to analyze dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), discusses their strengths and weaknesses, and outlines recent clinical applications of findings from these approaches. METHODS DCE-MRI allows for noninvasive quantitative analysis of contrast agent (CA) transient in soft tissues. Thus, it is an important and well-established tool to reveal microvasculature and perfusion in various clinical applications. In the last three decades, a host of nonparametric and parametric models and methods have been developed in order to quantify the CA's perfusion into tissue and estimate perfusion-related parameters (indexes) from signal- or concentration-time curves. These indexes are widely used in various clinical applications for the detection, characterization, and therapy monitoring of different diseases. RESULTS Promising theoretical findings and experimental results for the reviewed models and techniques in a variety of clinical applications suggest that DCE-MRI is a clinically relevant imaging modality, which can be used for early diagnosis of different diseases, such as breast and prostate cancer, renal rejection, and liver tumors. CONCLUSIONS Both nonparametric and parametric approaches for DCE-MRI analysis possess the ability to quantify tissue perfusion.
Collapse
Affiliation(s)
- Fahmi Khalifa
- BioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, Kentucky 40292 and Electronics and Communication Engineering Department, Mansoura University, Mansoura 35516, Egypt
| | - Ahmed Soliman
- BioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, Kentucky 40292
| | - Ayman El-Baz
- BioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, Kentucky 40292
| | - Mohamed Abou El-Ghar
- Radiology Department, Urology and Nephrology Center, Mansoura University, Mansoura 35516, Egypt
| | - Tarek El-Diasty
- Radiology Department, Urology and Nephrology Center, Mansoura University, Mansoura 35516, Egypt
| | - Georgy Gimel'farb
- Department of Computer Science, University of Auckland, Auckland 1142, New Zealand
| | - Rosemary Ouseph
- Kidney Transplantation-Kidney Disease Center, University of Louisville, Louisville, Kentucky 40202
| | - Amy C Dwyer
- Kidney Transplantation-Kidney Disease Center, University of Louisville, Louisville, Kentucky 40202
| |
Collapse
|
20
|
Zhang G, Pu H, He W, Liu F, Luo J, Bai J. Bayesian Framework Based Direct Reconstruction of Fluorescence Parametric Images. IEEE TRANSACTIONS ON MEDICAL IMAGING 2015; 34:1378-1391. [PMID: 25622312 DOI: 10.1109/tmi.2015.2394476] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
Fluorescence imaging has been successfully used in the study of pharmacokinetic analysis, while dynamic fluorescence molecular tomography (FMT) is an attractive imaging technique for three-dimensionally resolving the metabolic process of fluorescent biomarkers in small animals in vivo. Parametric images obtained by combining dynamic FMT with compartmental modeling can provide quantitative physiological information for biological studies and drug development. However, images obtained with conventional indirect methods suffer from poor image quality because of failure in utilizing the temporal correlations of boundary measurements. Besides, FMT suffers from low spatial resolution due to its ill-posed nature, which further reduces the image quality. In this paper, we propose a novel method to directly reconstruct parametric images from boundary measurements based on maximum a posteriori (MAP) estimation with structural priors in a Bayesian framework. The proposed method can utilize structural priors obtained from an X-ray computed tomography system to mitigate the ill-posedness of dynamic FMT inverse problem, and use direct reconstruction strategy to make full use of temporal correlations of boundary measurements. The results of numerical simulations and in vivo mouse experiments demonstrate that the proposed method leads to significant improvements in the reconstruction quality of parametric images as compared with the conventional indirect method and a previously developed direct method.
Collapse
|
21
|
Zhang G, He W, Pu H, Liu F, Chen M, Bai J, Luo J. Acceleration of dynamic fluorescence molecular tomography with principal component analysis. BIOMEDICAL OPTICS EXPRESS 2015; 6:2036-55. [PMID: 26114027 PMCID: PMC4473742 DOI: 10.1364/boe.6.002036] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/30/2015] [Revised: 04/30/2015] [Accepted: 05/04/2015] [Indexed: 05/24/2023]
Abstract
Dynamic fluorescence molecular tomography (FMT) is an attractive imaging technique for three-dimensionally resolving the metabolic process of fluorescent biomarkers in small animal. When combined with compartmental modeling, dynamic FMT can be used to obtain parametric images which can provide quantitative pharmacokinetic information for drug development and metabolic research. However, the computational burden of dynamic FMT is extremely huge due to its large data sets arising from the long measurement process and the densely sampling device. In this work, we propose to accelerate the reconstruction process of dynamic FMT based on principal component analysis (PCA). Taking advantage of the compression property of PCA, the dimension of the sub weight matrix used for solving the inverse problem is reduced by retaining only a few principal components which can retain most of the effective information of the sub weight matrix. Therefore, the reconstruction process of dynamic FMT can be accelerated by solving the smaller scale inverse problem. Numerical simulation and mouse experiment are performed to validate the performance of the proposed method. Results show that the proposed method can greatly accelerate the reconstruction of parametric images in dynamic FMT almost without degradation in image quality.
Collapse
Affiliation(s)
- Guanglei Zhang
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China
- Department of Biomedical Engineering, School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
| | - Wei He
- China Institute of Sport Science, Beijing 100061, China
| | - Huangsheng Pu
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China
| | - Fei Liu
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China
- Tsinghua-Peking Center for Life Sciences, Beijing 100084, China
| | - Maomao Chen
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China
| | - Jing Bai
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China
| | - Jianwen Luo
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China
- Center for Biomedical Imaging Research, Tsinghua University, Beijing 100084, China
| |
Collapse
|
22
|
Mahrooghy M, Ashraf AB, Daye D, McDonald ES, Rosen M, Mies C, Feldman M, Kontos D. Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk. IEEE Trans Biomed Eng 2015; 62:1585-94. [PMID: 25622311 PMCID: PMC10870107 DOI: 10.1109/tbme.2015.2395812] [Citation(s) in RCA: 34] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
GOAL Heterogeneity in cancer can affect response to therapy and patient prognosis. Histologic measures have classically been used to measure heterogeneity, although a reliable noninvasive measurement is needed both to establish baseline risk of recurrence and monitor response to treatment. Here, we propose using spatiotemporal wavelet kinetic features from dynamic contrast-enhanced magnetic resonance imaging to quantify intratumor heterogeneity in breast cancer. METHODS Tumor pixels are first partitioned into homogeneous subregions using pharmacokinetic measures. Heterogeneity wavelet kinetic (HetWave) features are then extracted from these partitions to obtain spatiotemporal patterns of the wavelet coefficients and the contrast agent uptake. The HetWave features are evaluated in terms of their prognostic value using a logistic regression classifier with genetic algorithm wrapper-based feature selection to classify breast cancer recurrence risk as determined by a validated gene expression assay. RESULTS Receiver operating characteristic analysis and area under the curve (AUC) are computed to assess classifier performance using leave-one-out cross validation. The HetWave features outperform other commonly used features (AUC = 0.88 HetWave versus 0.70 standard features). The combination of HetWave and standard features further increases classifier performance (AUCs 0.94). CONCLUSION The rate of the spatial frequency pattern over the pharmacokinetic partitions can provide valuable prognostic information. SIGNIFICANCE HetWave could be a powerful feature extraction approach for characterizing tumor heterogeneity, providing valuable prognostic information.
Collapse
Affiliation(s)
- Majid Mahrooghy
- Computational Breast Imaging Group, Department of Radiology, University of Pennsylvania
| | - Ahmed B. Ashraf
- Computational Breast Imaging Group, Department of Radiology, University of Pennsylvania
| | - Dania Daye
- Computational Breast Imaging Group, Department of Radiology, University of Pennsylvania
| | - Elizabeth S. McDonald
- Computational Breast Imaging Group, Department of Radiology, University of Pennsylvania
| | - Mark Rosen
- Computational Breast Imaging Group, Department of Radiology, University of Pennsylvania
| | - Carolyn Mies
- Department of Pathology and Laboratory Medicine, University of Pennsylvania
| | - Michael Feldman
- Department of Pathology and Laboratory Medicine, University of Pennsylvania
| | - Despina Kontos
- Computational Breast Imaging Group, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104 USA
| |
Collapse
|
23
|
Romain B, Letort V, Lucidarme O, Rouet L, Dalché-Buc F. A multi-task learning approach for compartmental model parameter estimation in DCE-CT sequences. ACTA ACUST UNITED AC 2014; 16:271-8. [PMID: 24579150 DOI: 10.1007/978-3-642-40763-5_34] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/28/2023]
Abstract
Today's follow-up of patients presenting abdominal tumors is generally performed through acquisition of dynamic sequences of contrast-enhanced CT. Estimating parameters of appropriate models of contrast intake diffusion through tissues should help characterizing the tumor physiology, but is impeded by the high level of noise inherent to the acquisition conditions. To improve the quality of estimation, we consider parameter estimation in voxels as a multi-task learning problem (one task per voxel) that takes advantage from the similarity between two tasks. We introduce a temporal similarity between tasks based on a robust distance between observed contrast-intake profiles of intensity. Using synthetic images, we compare multi-task learning using this temporal similarity, a spatial similarity and a single-task learning. The similarities based on temporal profiles are shown to bring significant improvements compared to the spatial one. Results on real CT sequences also confirm the relevance of the approach.
Collapse
|
24
|
Sommer JC, Schmid VJ. Spatial two-tissue compartment model for dynamic contrast-enhanced magnetic resonance imaging. J R Stat Soc Ser C Appl Stat 2014. [DOI: 10.1111/rssc.12057] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
25
|
Cuenod C, Balvay D. Perfusion and vascular permeability: Basic concepts and measurement in DCE-CT and DCE-MRI. Diagn Interv Imaging 2013; 94:1187-204. [DOI: 10.1016/j.diii.2013.10.010] [Citation(s) in RCA: 138] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
|
26
|
Sommer JC, Gertheiss J, Schmid VJ. Spatially regularized estimation for the analysis of dynamic contrast-enhanced magnetic resonance imaging data. Stat Med 2013; 33:1029-41. [DOI: 10.1002/sim.5997] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2012] [Revised: 06/12/2013] [Accepted: 09/09/2013] [Indexed: 11/12/2022]
Affiliation(s)
- Julia C. Sommer
- Department of Statistics; Ludwig-Maximilians-Universität; Munich Germany
| | - Jan Gertheiss
- Department of Animal Sciences; Georg-August-Universität; Göttingen Germany
| | - Volker J. Schmid
- Department of Statistics; Ludwig-Maximilians-Universität; Munich Germany
| |
Collapse
|
27
|
Abstract
In this paper, we propose a new pharmacokinetic model for parameter estimation of dynamic contrast-enhanced (DCE) MRI by using Gaussian process inference. Our model is based on the Tofts dual-compartment model for the description of tracer kinetics and the observed time series from DCE-MRI is treated as a Gaussian stochastic process. The parameter estimation is done through a maximum likelihood approach and we propose a variant of the coordinate descent method to solve this likelihood maximization problem. The new model was shown to outperform a baseline method on simulated data. Parametric maps generated on prostate DCE data with the new model also provided better enhancement of tumors, lower intensity on false positives, and better boundary delineation when compared with the baseline method. New statistical parameter maps from the process model were also found to be informative, particularly when paired with the PK parameter maps.
Collapse
|
28
|
Reliable estimation of incoherent motion parametric maps from diffusion-weighted MRI using fusion bootstrap moves. Med Image Anal 2013; 17:325-36. [PMID: 23434293 DOI: 10.1016/j.media.2012.12.001] [Citation(s) in RCA: 52] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2012] [Revised: 12/03/2012] [Accepted: 12/10/2012] [Indexed: 11/23/2022]
Abstract
Diffusion-weighted MRI has the potential to provide important new insights into physiological and microstructural properties of the body. The Intra-Voxel Incoherent Motion (IVIM) model relates the observed DW-MRI signal decay to parameters that reflect blood flow in the capillaries (D*), capillaries volume fraction (f), and diffusivity (D). However, the commonly used, independent voxel-wise fitting of the IVIM model leads to imprecise parameter estimates, which has hampered their practical usage. In this work, we improve the precision of estimates by introducing a spatially-constrained Incoherent Motion (IM) model of DW-MRI signal decay. We also introduce an efficient iterative "fusion bootstrap moves" (FBM) solver that enables precise parameter estimates with this new IM model. This solver updates parameter estimates by applying a binary graph-cut solver to fuse the current estimate of parameter values with a new proposal of the parameter values into a new estimate of parameter values that better fits the observed DW-MRI data. The proposals of parameter values are sampled from the independent voxel-wise distributions of the parameter values with a model-based bootstrap resampling of the residuals. We assessed both the improvement in the precision of the incoherent motion parameter estimates and the characterization of heterogeneous tumor environments by analyzing simulated and in vivo abdominal DW-MRI data of 30 patients, and in vivo DW-MRI data of three patients with musculoskeletal lesions. We found our IM-FBM reduces the relative root mean square error of the D* parameter estimates by 80%, and of the f and D parameter estimates by 50% compared to the IVIM model with the simulated data. Similarly, we observed that our IM-FBM method significantly reduces the coefficient of variation of parameter estimates of the D* parameter by 43%, the f parameter by 37%, and the D parameter by 17% compared to the IVIM model (paired Student's t-test, p<0.0001). In addition, we found our IM-FBM method improved the characterization of heterogeneous musculoskeletal lesions by means of increased contrast-to-noise ratio of 19.3%. The IM model and FBM solver combined, provide more precise estimate of the physiological model parameter values that describing the DW-MRI signal decay and a better mechanism for characterizing heterogeneous lesions than does the independent voxel-wise IVIM model.
Collapse
|
29
|
Wang H, Cao Y. Spatially regularized T(1) estimation from variable flip angles MRI. Med Phys 2012; 39:4139-48. [PMID: 22830747 DOI: 10.1118/1.4722747] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE To develop efficient algorithms for fast voxel-by-voxel quantification of tissue longitudinal relaxation time (T(1)) from variable flip angles magnetic resonance images (MRI) to reduce voxel-level noise without blurring tissue edges. METHODS T(1) estimations regularized by total variation (TV) and quadratic penalty are developed to measure T(1) from fast variable flip angles MRI and to reduce voxel-level noise without decreasing the accuracy of the estimates. First, a quadratic surrogate for a log likelihood cost function of T(1) estimation is derived based upon the majorization principle, and then the TV-regularized surrogate function is optimized by the fast iterative shrinkage thresholding algorithm. A fast optimization algorithm for the quadratically regularized T(1) estimation is also presented. The proposed methods are evaluated by the simulated and experimental MR data. RESULTS The means of the T(1) values in the simulated brain data estimated by the conventional, TV-regularized, and quadratically regularized methods have less than 3% error from the true T(1) in both GM and WM tissues with image noise up to 9%. The relative standard deviations (SDs) of the T(1) values estimated by the conventional method are more than 12% and 15% when the images have 7% and 9% noise, respectively. In comparison, the TV-regularized and quadratically regularized methods are able to suppress the relative SDs of the estimated T(1) to be less than 2% and 3%, respectively, regardless of the image noise level. However, the quadratically regularized method tends to overblur the edges compared to the TV-regularized method. CONCLUSIONS The spatially regularized methods improve quality of T(1) estimation from multiflip angles MRI. Quantification of dynamic contrast-enhanced MRI can benefit from the high quality measurement of native T(1).
Collapse
Affiliation(s)
- Hesheng Wang
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI 48109, USA.
| | | |
Collapse
|
30
|
Freiman M, Voss SD, Mulkern RV, Perez-Rossello JM, Callahan MJ, Warfield SK. Reliable assessment of perfusivity and diffusivity from diffusion imaging of the body. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2012; 15:1-9. [PMID: 23285528 DOI: 10.1007/978-3-642-33415-3_1] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
Diffusion-weighted MRI of the body has the potential to provide important new insights into physiological and microstructural properties. The intra-voxel incoherent motion (IVIM) model relates the observed DW-MRI signal decay to parameters that reflect perfusivity (D*) and its volume fraction (f), and diffusivity (D). However, the commonly used voxel-wise fitting of the IVIM model leads to parameter estimates with poor precision, which has hampered their practical usage. In this work, we increase the estimates' precision by introducing a model of spatial homogeneity, through which we obtain estimates of model parameters for all of the voxels at once, instead of solving for each voxel independently. Furthermore, we introduce an efficient iterative solver which utilizes a model-based bootstrap estimate of the distribution of residuals and a binary graph cut to generate optimal model parameter updates. Simulation experiments show that our approach reduces the relative root mean square error of the estimated parameters by 80% for the D* parameter and by 50% for the f and D parameters. We demonstrated the clinical impact of our model in distinguishing between enhancing and nonenhancing ileum segments in 24 Crohn's disease patients. Our model detected the enhanced segments with 91%/92% sensitivity/specificity which is better than the 81%/85% obtained by the voxel-independent approach.
Collapse
Affiliation(s)
- M Freiman
- Computational Radiology Laboratory, Boston Children's Hospital, Harvard Medical School, MA, USA
| | | | | | | | | | | |
Collapse
|
31
|
Kelm BM, Kaster FO, Henning A, Weber MA, Bachert P, Boesiger P, Hamprecht FA, Menze BH. Using spatial prior knowledge in the spectral fitting of MRS images. NMR IN BIOMEDICINE 2012; 25:1-13. [PMID: 21538636 DOI: 10.1002/nbm.1704] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/26/2010] [Revised: 02/09/2011] [Accepted: 02/10/2011] [Indexed: 05/30/2023]
Abstract
We propose a Bayesian smoothness prior in the spectral fitting of MRS images which can be used in addition to commonly employed prior knowledge. By combining a frequency-domain model for the free induction decay with a Gaussian Markov random field prior, a new optimization objective is derived that encourages smooth parameter maps. Using a particular parameterization of the prior, smooth damping, frequency and phase maps can be obtained whilst preserving sharp spatial features in the amplitude map. A Monte Carlo study based on two sets of simulated data demonstrates that the variance of the estimated parameter maps can be reduced considerably, even below the Cramér-Rao lower bound, when using spatial prior knowledge. Long-TE (1)H MRSI at 1.5 T of a patient with a brain tumor shows that the use of the spatial prior resolves the overlapping peaks of choline and creatine when a single voxel method fails to do so. Improved and detailed metabolic maps can be derived from high-spatial-resolution, short-TE (1)H MRSI at 3 T. Finally, the evaluation of four series of long-TE brain MRSI data with various signal-to-noise ratios shows the general benefit of the proposed approach.
Collapse
Affiliation(s)
- B Michael Kelm
- Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Germany.
| | | | | | | | | | | | | | | |
Collapse
|
32
|
Chen L, Choyke PL, Chan TH, Chi CY, Wang G, Wang Y. Tissue-specific compartmental analysis for dynamic contrast-enhanced MR imaging of complex tumors. IEEE TRANSACTIONS ON MEDICAL IMAGING 2011; 30:2044-58. [PMID: 21708498 PMCID: PMC6309689 DOI: 10.1109/tmi.2011.2160276] [Citation(s) in RCA: 39] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/13/2023]
Abstract
Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) provides a noninvasive method for evaluating tumor vasculature patterns based on contrast accumulation and washout. However, due to limited imaging resolution and tumor tissue heterogeneity, tracer concentrations at many pixels often represent a mixture of more than one distinct compartment. This pixel-wise partial volume effect (PVE) would have profound impact on the accuracy of pharmacokinetics studies using existing compartmental modeling (CM) methods. We, therefore, propose a convex analysis of mixtures (CAM) algorithm to explicitly mitigate PVE by expressing the kinetics in each pixel as a nonnegative combination of underlying compartments and subsequently identifying pure volume pixels at the corners of the clustered pixel time series scatter plot simplex. The algorithm is supported theoretically by a well-grounded mathematical framework and practically by plug-in noise filtering and normalization preprocessing. We demonstrate the principle and feasibility of the CAM-CM approach on realistic synthetic data involving two functional tissue compartments, and compare the accuracy of parameter estimates obtained with and without PVE elimination using CAM or other relevant techniques. Experimental results show that CAM-CM achieves a significant improvement in the accuracy of kinetic parameter estimation. We apply the algorithm to real DCE-MRI breast cancer data and observe improved pharmacokinetic parameter estimation, separating tumor tissue into regions with differential tracer kinetics on a pixel-by-pixel basis and revealing biologically plausible tumor tissue heterogeneity patterns. This method combines the advantages of multivariate clustering, convex geometry analysis, and compartmental modeling approaches. The open-source MATLAB software of CAM-CM is publicly available from the Web.
Collapse
Affiliation(s)
- Li. Chen
- Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Arlington, VA 22203 USA
| | - Peter L. Choyke
- Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD 20892 USA
| | - Tsung-Han Chan
- Institute of Communications Engineering and Department of Electrical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan
| | - Chong-Yung Chi
- Institute of Communications Engineering and Department of Electrical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan
| | - Ge Wang
- School of Biomedical Engineering and Science, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061 USA
| | - Yue Wang
- Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Arlington, VA 22203 USA
| |
Collapse
|
33
|
An expectation-maximisation approach for simultaneous pixel classification and tracer kinetic modelling in dynamic contrast enhanced-magnetic resonance imaging. Med Biol Eng Comput 2010; 49:485-95. [DOI: 10.1007/s11517-010-0695-x] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2009] [Accepted: 09/25/2010] [Indexed: 11/26/2022]
|
34
|
Vlachos F, Tung YS, Konofagou EE. Permeability assessment of the focused ultrasound-induced blood-brain barrier opening using dynamic contrast-enhanced MRI. Phys Med Biol 2010; 55:5451-66. [PMID: 20736501 DOI: 10.1088/0031-9155/55/18/012] [Citation(s) in RCA: 68] [Impact Index Per Article: 4.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
Focused ultrasound (FUS) in conjunction with microbubbles has been shown to successfully open the blood-brain barrier (BBB) in the mouse brain. In this study, we compute the BBB permeability after opening in vivo. The spatial permeability of the BBB-opened region was assessed using dynamic contrast-enhanced MRI (DCE-MRI). The DCE-MR images were post-processed using the general kinetic model (GKM) and the reference region model (RRM). Permeability maps were generated and the K(trans) values were calculated for a predefined volume of interest in the sonicated and the control area for each mouse. The results demonstrated that K(trans) in the BBB-opened region (0.02 +/- 0.0123 for GKM and 0.03 +/- 0.0167 min(-1) for RRM) was at least two orders of magnitude higher when compared to the contra-lateral (control) side (0 and 8.5 x 10(-4) +/- 12 x 10(-4) min(-1), respectively). The permeability values obtained with the two models showed statistically significant agreement and excellent correlation (R(2) = 0.97). At histological examination, it was concluded that no macroscopic damage was induced. This study thus constitutes the first permeability assessment of FUS-induced BBB opening using DCE-MRI, supporting the fact that the aforementioned technique may constitute a safe, non-invasive and efficacious drug delivery method.
Collapse
Affiliation(s)
- F Vlachos
- Department of Biomedical Engineering, Columbia University, New York, NY 10027, USA
| | | | | |
Collapse
|