KEYWORDS: Education and training, Positron emission tomography, Magnetic resonance imaging, Multiple sclerosis, White matter, Scanners, Neurological disorders, In vivo imaging, Gallium nitride, Design and modelling
Multiple sclerosis (MS) is a demyenalinating inflammatory neurological disease. In vivo biomarkers of myelin content are of major importance for patient care and clinical trials. Positron Emission Tomography (PET) with Pittsburgh Compound B (PiB) provides a specific myelin marker. However, it is not available in clinical routine. In this paper, we propose a method to generate myelin maps by synthesizing PiB PET from clinical routine MRI sequences (T1-weighted and FLAIR). To that purpose, we introduce a new curriculum learning strategy for training generative adversarial networks (GAN). Specifically, we design a curricular approach for training the discriminator: training starts with only lesion patches and random patches (from anywhere in the white matter) are progressively introduced. We relied on two distinct cohorts of MS patients acquired each on a different scanner and in a different country. One cohort was used for training/validation and the other one for testing. We found that the synthetic PiB PET was strongly correlated to the ground-truth both at the lesion level (r = 0.70, p < 10−5) and the patient level (r = 0.74, p < 10−5). Moreover, the correlations were stronger when using the curricular learning strategy compared to starting the discriminator training from random patches. Our results demonstrate the interest of this new curriculum learning strategy for PET image synthesis. Even though further evaluations are needed, our approach has the potential to provide a useful biomarker for clinical routine follow-up of patients with MS.
Contrast Enhanced Ultrasound (CEUS) is a sensitive imaging technique to assess tissue vascularity, that can be useful in
the quantification of different perfusion patterns. This can be particularly important in the early detection and staging of
arthritis. In a recent study we have shown that a Gamma-variate can accurately quantify synovial perfusion and it is
flexible enough to describe many heterogeneous patterns. Moreover, we have shown that through a pixel-by-pixel
analysis the quantitative information gathered characterizes more effectively the perfusion. However, the SNR ratio of
the data and the nonlinearity of the model makes the parameter estimation difficult. Using classical non-linear-leastsquares
(NLLS) approach the number of unreliable estimates (those with an asymptotic coefficient of variation greater
than a user-defined threshold) is significant, thus affecting the overall description of the perfusion kinetics and of its
heterogeneity.
In this work we propose to solve the parameter estimation at the pixel level within a Bayesian framework using
Variational Bayes (VB), and an automatic and data-driven prior initialization.
When evaluating the pixels for which both VB and NLLS provided reliable estimates, we demonstrated that the
parameter values provided by the two methods are well correlated (Pearson’s correlation between 0.85 and 0.99).
Moreover, the mean number of unreliable pixels drastically reduces from 54% (NLLS) to 26% (VB), without increasing
the computational time (0.05 s/pixel for NLLS and 0.07 s/pixel for VB). When considering the efficiency of the
algorithms as computational time per reliable estimate, VB outperforms NLLS (0.11 versus 0.25 seconds per reliable
estimate respectively).
Contrast Enhanced Ultrasound (CEUS) is a sensitive imaging technique to assess tissue vascularity, that can be useful in the quantification of different perfusion patterns. This can particularly important in the early detection and differentiation of different types of arthritis. A Gamma-variate can accurately quantify synovial perfusion and it is flexible enough to describe many heterogeneous patterns. However, in some cases the heterogeneity of the kinetics can be such that even the Gamma model does not properly describe the curve, especially in presence of recirculation or of an additional slowflow component.
In this work we apply to CEUS data both the Gamma-variate and the single compartment recirculation model (SCR) which takes explicitly into account an additional component of slow flow. The models are solved within a Bayesian framework.
We also employed the perfusion estimates obtained with SCR to train a support vector machine classifier to distinguish different types of arthritis. When dividing the patients into two groups (rheumatoid arthritis and polyarticular RA-like psoriatic arthritis vs. other arthritis types), the slow component amplitude was significantly different across groups: mean values of a1 and its variability were statistically higher in RA and RA-like patients (131% increase in mean, p = 0.035 and 73% increase in standard deviation, p = 0.049 respectively). The SVM classifier achieved a balanced accuracy of 89%, with a sensitivity of 100% and a specificity of 78%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.