Validation of a Denoising Method Using Deep Learning-Based Reconstruction to Quantify Multiple Sclerosis Lesion Load on Fast FLAIR Imaging.

BACKGROUND AND PURPOSE: Accurate quantification of WM lesion load is essential for the care of patients with multiple sclerosis. We tested whether the combination of accelerated 3D-FLAIR and denoising using deep learning-based reconstruction could provide a relevant strategy while shortening the imaging examination. MATERIALS AND METHODS: Twenty-eight patients with multiple sclerosis were prospectively examined using 4 implementations of 3D-FLAIR with decreasing scan times (4 minutes 54 seconds, 2 minutes 35 seconds, 1 minute 40 seconds, and 1 minute 15 seconds). Each FLAIR sequence was reconstructed without and with denoising using deep learning-based reconstruction, resulting in 8 FLAIR sequences per patient. Image quality was assessed with the Likert scale, apparent SNR, and contrast-to-noise ratio. Manual and automatic lesion segmentations, performed randomly and blindly, were quantitatively evaluated against ground truth using the absolute volume difference, true-positive rate, positive predictive value, Dice similarity coefficient, Hausdorff distance, and F1 score based on the lesion count. The Wilcoxon signed-rank test and 2-way ANOVA were performed. RESULTS: Both image-quality evaluation and the various metrics showed deterioration when the FLAIR scan time was accelerated. However, denoising using deep learning-based reconstruction significantly improved subjective image quality and quantitative performance metrics, particularly for manual segmentation. Overall, denoising using deep learning-based reconstruction helped to recover contours closer to those from the criterion standard and to capture individual lesions otherwise overlooked. The Dice similarity coefficient was equivalent between the 2-minutes-35-seconds-long FLAIR with denoising using deep learning-based reconstruction and the 4-minutes-54-seconds-long reference FLAIR sequence. CONCLUSIONS: Denoising using deep learning-based reconstruction helps to recognize multiple sclerosis lesions buried in the noise of accelerated FLAIR acquisitions, a possibly useful strategy to efficiently shorten the scan time in clinical practice.

Deep correction of breathing-related artifacts in real-time MR-thermometry.

Real-time MR-imaging has been clinically adapted for monitoring thermal therapies since it can provide on-the-fly temperature maps simultaneously with anatomical information. However, proton resonance frequency based thermometry of moving targets remains challenging since temperature artifacts are induced by the respiratory as well as physiological motion. If left uncorrected, these artifacts lead to severe errors in temperature estimates and impair therapy guidance. In this study, we evaluated deep learning for on-line correction of motion related errors in abdominal MR-thermometry. For this, a convolutional neural network (CNN) was designed to learn the apparent temperature perturbation from images acquired during a preparative learning stage prior to hyperthermia. The input of the designed CNN is the most recent magnitude image and no surrogate of motion is needed. During the subsequent hyperthermia procedure, the recent magnitude image is used as an input for the CNN-model in order to generate an on-line correction for the current temperature map. The method's artifact suppression performance was evaluated on 12 free breathing volunteers and was found robust and artifact-free in all examined cases. Furthermore, thermometric precision and accuracy was assessed for in vivo ablation using high intensity focused ultrasound. All calculations involved at the different stages of the proposed workflow were designed to be compatible with the clinical time constraints of a therapeutic procedure.

Effect of cognitive rehabilitation on neuropsychological and semiecological testing and on daily cognitive functioning in multiple sclerosis: The REACTIV randomized controlled study.

BACKGROUND: Specific cognitive rehabilitation (SCR) has been suggested for multiple sclerosis (MS). A randomized controlled trial (RCT) evaluating the therapeutic effects of SCR is necessary. OBJECTIVE: To demonstrate the superiority of a SCR program (REACTIV) over nonspecific intervention (NSI) for neuropsychological (NP) assessment, virtual reality (VR) cognitive testing and daily cognitive functioning. METHODS: A single-blind RCT compared SCR and NSI in patients with MS with cognitive complaint. Both programs included 50 individual sessions, 3 times a week for 17 weeks in a real-world setting. The primary end-point was NP assessment. Secondary end-points included semiecological VR tasks (Urban Daily Cog®) and daily cognitive functioning assessment. Maintenance of the effects at 8 months was studied. RESULTS: Of the 35 patients, 18 completed the SCR, and 17 completed the NSI. Several NP and semiecological scores improved significantly more after SCR than after NSI. More NP scores improved significantly after SCR than after NSI. SCR improved daily cognitive functioning. Most improvements were maintained at 8 months. CONCLUSION: SCR performed in a real-world setting is superior to NSI for improving performance in specific cognitive domains and information processing speed, and for improving cognitive functioning, as evaluated by ecological tools close to daily life and a daily cognitive functioning questionnaire.

Cerebellar parcellation in schizophrenia and bipolar disorder.

OBJECTIVE: The cerebellum is involved in cognitive processing and emotion control. Cerebellar alterations could explain symptoms of schizophrenia spectrum disorder (SZ) and bipolar disorder (BD). In addition, literature suggests that lithium might influence cerebellar anatomy. Our aim was to study cerebellar anatomy in SZ and BD, and investigate the effect of lithium. METHODS: Participants from 7 centers worldwide underwent a 3T MRI. We included 182 patients with SZ, 144 patients with BD, and 322 controls. We automatically segmented the cerebellum using the CERES pipeline. All outputs were visually inspected. RESULTS: Patients with SZ showed a smaller global cerebellar gray matter volume compared to controls, with most of the changes located to the cognitive part of the cerebellum (Crus II and lobule VIIb). This decrease was present in the subgroup of patients with recent-onset SZ. We did not find any alterations in the cerebellum in patients with BD. However, patients medicated with lithium had a larger size of the anterior cerebellum, compared to patients not treated with lithium. CONCLUSION: Our multicenter study supports a distinct pattern of cerebellar alterations in SZ and BD.

Bullous pemphigoid and dipeptidyl peptidase IV inhibitors: a case-noncase study in the French Pharmacovigilance Database.

BACKGROUND: Inhibitors of dipeptidyl peptidase (DPP)-IV have been suspected in the onset of bullous pemphigoid for several years now. However, comparative studies assessing the link between DPP-IV inhibitor exposure and bullous pemphigoid have not yet been performed. OBJECTIVES: To detect, from the French Pharmacovigilance Database (FPVD), a signal of risk of bullous pemphigoid during DPP-IV inhibitor exposure by comparative study. METHODS: All spontaneous reports of DPP-IV inhibitor-related bullous pemphigoid recorded in the FPVD between April 2008 and August 2014 were described. We conducted disproportionality analyses (case-noncase method) to assess the link between DPP-IV inhibitors and bullous pemphigoid, calculating reporting odds ratios (RORs). We also compared DPP-IV inhibitor-induced bullous pemphigoid reports rated per million defined daily doses dispensed during the study period. RESULTS: Among 217 331 spontaneous adverse drug reaction reports registered in the FPVD, 1297 involved DPP-IV inhibitors. Among these observations, 42 were bullous pemphigoid (vildagliptin, n = 31; sitagliptin, n = 10; saxagliptin, n = 1). The ROR for pooled DPP-IV inhibitors was 67·5 [95% confidence interval (CI) 47·1-96·9]. Disproportionality was also observed for each DPP-IV inhibitor: vildagliptin (ROR 225·3, 95% CI 148·9-340·9), sitagliptin (ROR 17·0, 95% CI 8·9-32·5) and saxagliptin (ROR 16·5, 95% CI 2·3-119·1). Analyses adjusted on dispensing data led to similar results. CONCLUSIONS: These data confirm a strong signal for an increased risk of bullous pemphigoid during DPP-IV inhibitor exposure. This adverse drug reaction is observed for each DPP-IV inhibitor, suggesting a class effect. The signal was higher with vildagliptin than with the other DPP-IV inhibitors.

A new method for structural volume analysis of longitudinal brain MRI data and its application in studying the growth trajectories of anatomical brain structures in childhood.

Cross-sectional analysis of longitudinal anatomical magnetic resonance imaging (MRI) data may be suboptimal as each dataset is analyzed independently. In this study, we evaluate how much variability can be reduced by analyzing structural volume changes in longitudinal data using longitudinal analysis. We propose a two-part pipeline that consists of longitudinal registration and longitudinal classification. The longitudinal registration step includes the creation of subject-specific linear and nonlinear templates that are then registered to a population template. The longitudinal classification step comprises a four-dimensional expectation-maximization algorithm, using a priori classes computed by averaging the tissue classes of all time points obtained cross-sectionally. To study the impact of these two steps, we apply the framework completely ("LL method": Longitudinal registration and Longitudinal classification) and partially ("LC method": Longitudinal registration and Cross-sectional classification) and compare these with a standard cross-sectional framework ("CC method": Cross-sectional registration and Cross-sectional classification). The three methods are applied to (1) a scan-rescan database to analyze reliability and (2) the NIH pediatric population to compare gray matter growth trajectories evaluated with a linear mixed model. The LL method, and the LC method to a lesser extent, significantly reduced the variability in the measurements in the scan-rescan study and gave the best-fitted gray matter growth model with the NIH pediatric MRI database. The results confirm that both steps of the longitudinal framework reduce variability and improve accuracy in comparison with the cross-sectional framework, with longitudinal classification yielding the greatest impact. Using the improved method to analyze longitudinal data, we study the growth trajectories of anatomical brain structures in childhood using the NIH pediatric MRI database. We report age- and gender-related growth trajectories of specific regions of the brain during childhood that could be used as a reference in studying the impact of neurological disorders on brain development.

An optimized blockwise nonlocal means denoising filter for 3-D magnetic resonance images.

A critical issue in image restoration is the problem of noise removal while keeping the integrity of relevant image information. Denoising is a crucial step to increase image quality and to improve the performance of all the tasks needed for quantitative imaging analysis. The method proposed in this paper is based on a 3-D optimized blockwise version of the nonlocal (NL)-means filter (Buades, et al., 2005). The NL-means filter uses the redundancy of information in the image under study to remove the noise. The performance of the NL-means filter has been already demonstrated for 2-D images, but reducing the computational burden is a critical aspect to extend the method to 3-D images. To overcome this problem, we propose improvements to reduce the computational complexity. These different improvements allow to drastically divide the computational time while preserving the performances of the NL-means filter. A fully automated and optimized version of the NL-means filter is then presented. Our contributions to the NL-means filter are: 1) an automatic tuning of the smoothing parameter; 2) a selection of the most relevant voxels; 3) a blockwise implementation; and 4) a parallelized computation. Quantitative validation was carried out on synthetic datasets generated with BrainWeb (Collins, et al., 1998). The results show that our optimized NL-means filter outperforms the classical implementation of the NL-means filter, as well as two other classical denoising methods [anisotropic diffusion (Perona and Malik, 1990)] and total variation minimization process (Rudin, et al., 1992) in terms of accuracy (measured by the peak signal-to-noise ratio) with low computation time. Finally, qualitative results on real data are presented .

Incest revisited: delayed post-traumatic stress disorder in mothers following the sexual abuse of their children.

The case histories of four women who developed symptoms of post-traumatic stress disorder following the disclosure of the sexual abuse of their daughters are presented. These individuals also exhibited comorbid symptoms of depression and personality disorders. Awareness of the sexual abuse of their daughters catalyzed a reliving of their own childhood victimization. The psychodynamics operating in these cases, as well as treatment strategies are also presented. A brief follow-up of three of the four cases is included.