A deep learning approach for synthetic MRI based on two routine sequences and training with synthetic data.

BACKGROUND AND OBJECTIVE: Synthetic magnetic resonance imaging (MRI) is a low cost procedure that serves as a bridge between qualitative and quantitative MRI. However, the proposed methods require very specific sequences or private protocols which have scarcely found integration in clinical scanners. We propose a learning-based approach to compute T1, T2, and PD parametric maps from only a pair of T1- and T2-weighted images customarily acquired in the clinical routine. METHODS: Our approach is based on a convolutional neural network (CNN) trained with synthetic data; specifically, a synthetic dataset with 120 volumes was constructed from the anatomical brain model of the BrainWeb tool and served as the training set. The CNN learns an end-to-end mapping function to transform the input T1- and T2-weighted images to their underlying T1, T2, and PD parametric maps. Then, conventional weighted images unseen by the network are analytically synthesized from the parametric maps. The network can be fine tuned with a small database of actual weighted images and maps for better performance. RESULTS: This approach is able to accurately compute parametric maps from synthetic brain data achieving normalized squared error values predominantly below 1%. It also yields realistic parametric maps from actual MR brain acquisitions with T1, T2, and PD values in the range of the literature and with correlation values above 0.95 compared to the T1 and T2 maps obtained from relaxometry sequences. Further, the synthesized weighted images are visually realistic; the mean square error values are always below 9% and the structural similarity index is usually above 0.90. Network fine tuning with actual maps improves performance, while training exclusively with a small database of actual maps shows a performance degradation. CONCLUSIONS: These results show that our approach is able to provide realistic parametric maps and weighted images out of a CNN that (a) is trained with a synthetic dataset and (b) needs only two inputs, which are in turn obtained from a common full-brain acquisition that takes less than 8 min of scan time. Although a fine tuning with actual maps improves performance, synthetic data is crucial to reach acceptable performance levels. Hence, we show the utility of our approach for both quantitative MRI in clinical viable times and for the synthesis of additional weighted images to those actually acquired.

Alternative Microstructural Measures to Complement Diffusion Tensor Imaging in Migraine Studies with Standard MRI Acquisition.

The white matter state in migraine has been investigated using diffusion tensor imaging (DTI) measures, but results using this technique are conflicting. To overcome DTI measures, we employed ensemble average diffusion propagator measures obtained with apparent measures using reduced acquisitions (AMURA). The AMURA measures were return-to-axis (RTAP), return-to-origin (RTOP) and return-to-plane probabilities (RTPP). Tract-based spatial statistics was used to compare fractional anisotropy, mean diffusivity, axial diffusivity and radial diffusivity from DTI, and RTAP, RTOP and RTPP, between healthy controls, episodic migraine and chronic migraine patients. Fifty healthy controls, 54 patients with episodic migraine and 56 with chronic migraine were assessed. Significant differences were found between both types of migraine, with lower axial diffusivity values in 38 white matter regions and higher RTOP values in the middle cerebellar peduncle in patients with a chronic migraine (p < 0.05 family-wise error corrected). Significantly lower RTPP values were found in episodic migraine patients compared to healthy controls in 24 white matter regions (p < 0.05 family-wise error corrected), finding no significant differences using DTI measures. The white matter microstructure is altered in a migraine, and in chronic compared to episodic migraine. AMURA can provide additional results with respect to DTI to uncover white matter alterations in migraine.

Integration of an intelligent tutoring system in a magnetic resonance simulator for education: Technical feasibility and user experience.

BACKGROUND AND OBJECTIVE: In this paper we propose to include an intelligent tutoring system (ITS) within a magnetic resonance (MR) simulator that has been developed in house. With this, we intend to measure the impact, in terms of user experience, of including an ITS in our simulator. METHODS: We thoroughly describe the integration procedure and we have tested the benefits of this integration by means of two actual educational experiences, with one of them using the simulator as a standalone tool, and the other with the joint use of simulator+ITS. The experiences have consisted of two online courses with a number of students around 180 in both of them, where measurements of usability, perceived utility and likelihood to recommend were collected. RESULTS: We have observed that the three measurements improved noticeably in the second course with respect to the first one; specifically, overall usability improved by 22.3%, perceived utility by an average of 55.1% and likelihood to recommend by 13.7%. In addition, quantitative measurements are complemented with comments in free text format directly provided by the students. Results show evidence on the benefits of integrating an ITS in terms of quantitative user experience, as well as qualitative comparative comments directly by students of both courses. CONCLUSIONS: This is the first time that an ITS is used within the scope of MR simulation for training purposes. Benefits of integrating an ITS within an MR simulator have been evaluated in terms of user experience, with satisfactory comparative results.

Scalar diffusion-MRI measures invariant to acquisition parameters: A first step towards imaging biomarkers.

An imaging biomarker is a biologic feature in an image that is relevant to a patient's diagnosis or prognosis. In order to qualify as a biomarker, a measure must be robust and reproducible. However, the usual scalar measures derived from diffusion tensor imaging are known to be highly dependent on the variation of the acquisition parameters, which prevents their possible use as biomarkers. In this work, we propose a new set of quantitative measures based on diffusion magnetic resonance imaging from single-shell acquisitions that are designed to be robust to the variations of several acquisition parameters (number of gradient directions, b-value and SNR) while keeping a high discrimination power on differences in the diffusion characteristics of the tissue. These new scalar measures are analytically obtained from a generic diffusion function that does not require the calculation of a diffusion tensor. This way, on one hand, we avoid the use of a specific diffusion model and, on the other hand, we make easier the statistical characterization of the measures. Accordingly, the analysis of the measures bias is carried out and it is used to minimize their dependency with respect to the acquisition noise for different SNRs. The robustness and discrimination power of the measures are tested for different number of gradients, b-values and SNRs using a realistic phantom and three real datasets: (1) 13 control subjects and different acquisition parameters; (2) a public data set from a single subject acquired using multiple shells and (3) 32 schizophrenia patients and 32 age and sex-matched healthy controls with a varying number of gradient directions. The proposed quantitative measures exhibit low variability to the changes of the acquisition parameters, while at the same time they preserve a discrimination power that is able to detect significant changes in the anisotropy of the diffusion.