Correction of Motion Artifacts Using a Multiscale Fully Convolutional Neural Network.

BACKGROUND AND PURPOSE: Motion artifacts are a frequent source of image degradation in the clinical application of MR imaging (MRI). Here we implement and validate an MRI motion-artifact correction method using a multiscale fully convolutional neural network. MATERIALS AND METHODS: The network was trained to identify motion artifacts in axial T2-weighted spin-echo images of the brain. Using an extensive data augmentation scheme and a motion artifact simulation pipeline, we created a synthetic training dataset of 93,600 images based on only 16 artifact-free clinical MRI cases. A blinded reader study using a unique test dataset of 28 additional clinical MRI cases with real patient motion was conducted to evaluate the performance of the network. RESULTS: Application of the network resulted in notably improved image quality without the loss of morphologic information. For synthetic test data, the average reduction in mean squared error was 41.84%. The blinded reader study on the real-world test data resulted in significant reduction in mean artifact scores across all cases (P < .03). CONCLUSIONS: Retrospective correction of motion artifacts using a multiscale fully convolutional network is promising and may mitigate the substantial motion-related problems in the clinical MRI workflow.

FLAIR2 improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images.

BACKGROUND: Accurate segmentation of MS lesions on MRI is difficult and, if performed manually, time consuming. Automatic segmentations rely strongly on the image contrast and signal-to-noise ratio. Literature examining segmentation tool performances in real-world multi-site data acquisition settings is scarce. OBJECTIVE: FLAIR2, a combination of T2-weighted and fluid attenuated inversion recovery (FLAIR) images, improves tissue contrast while suppressing CSF. We compared the use of FLAIR and FLAIR2 in LesionTOADS, OASIS and the lesion segmentation toolbox (LST) when applied to non-homogenized, multi-center 2D-imaging data. METHODS: Lesions were segmented on 47 MS patient data sets obtained from 34 sites using LesionTOADS, OASIS and LST, and compared to a semi-automatically generated reference. The performance of FLAIR and FLAIR2 was assessed using the relative lesion volume difference (LVD), Dice coefficient (DSC), sensitivity (SEN) and symmetric surface distance (SSD). Performance improvements related to lesion volumes (LVs) were evaluated for all tools. For comparison, LesionTOADS was also used to segment lesions from 3 T single-center MR data of 40 clinically isolated syndrome (CIS) patients. RESULTS: Compared to FLAIR, the use of FLAIR2 in LesionTOADS led to improvements of 31.6% (LVD), 14.0% (DSC), 25.1% (SEN), and 47.0% (SSD) in the multi-center study. DSC and SSD significantly improved for larger LVs, while LVD and SEN were enhanced independent of LV. OASIS showed little difference between FLAIR and FLAIR2, likely due to its inherent use of T2w and FLAIR. LST replicated the benefits of FLAIR2 only in part, indicating that further optimization, particularly at low LVs is needed. In the CIS study, LesionTOADS did not benefit from the use of FLAIR2 as the segmentation performance for both FLAIR and FLAIR2 was heterogeneous. CONCLUSIONS: In this real-world, multi-center experiment, FLAIR2 outperformed FLAIR in its ability to segment MS lesions with LesionTOADS. The computation of FLAIR2 enhanced lesion detection, at minimally increased computational time or cost, even retrospectively. Further work is needed to determine how LesionTOADS and other tools, such as LST, can optimally benefit from the improved FLAIR2 contrast.

The impact of sex and language dominance on material-specific memory before and after left temporal lobe surgery.

Recent findings raised evidence that in early-onset left temporal lobe epilepsy, women show greater functional plasticity for verbal memory than men. In particular, women with lesion- or epilepsy-driven atypical language dominance show an advantage over men. The question asked in this study was whether there is evidence of sex- and language dominance-dependent late, i.e. adult age, plasticity for verbal memory when epilepsy surgery is performed in these patients. Pre- and 1-year postoperative memory performance was evaluated in 169 patients (94 males and 75 females) who underwent left temporal lobe surgery and who had WADA testing of hemispheric language dominance prior to surgery. Verbal memory and figural memory were assessed by list-learning paradigms. According to the Bonn intracarotid amobarbital test (IAT) protocol, patients were categorized into left dominant or atypically dominant (right, incomplete left or right, and bilateral dominant) groups. Results were controlled for the hypothesized sex differences. Thirty-four percent of men and 47% of women displayed patterns of atypical language dominance. Atypical dominance was related to an early onset of epilepsy. Men showed a larger time window for development of atypical dominance but, differently from women, the pattern of atypical dominance was more strictly determined by the age at onset of epilepsy. Atypically dominant women showed better verbal memory than typically dominant women or men. After surgery, right dominant patients had better verbal memory outcome than patients with bilateral or left language dominance who showed significant memory loss. No effect of sex on verbal memory change was found. Figural memory deteriorated in men and improved in women, when they were not left dominant. Seizure outcome had no effect on performance changes. It was concluded that better preserved verbal memory in atypically dominant women before surgery indicates greater benefit from atypical dominance in women than men with regard to the initial damage associated with left hemisphere epilepsy. Later in life, when epilepsy surgery causes additional damage, no such sex difference is observed, indicating that the women's advantage over men is fixed to an early time window in life. Postoperative changes in figural memory suggest dynamics in crowding and suppression patterns. Whether this reflects late plasticity and compensation needs further demonstration. For clinical practice, it is important to note that incomplete right hemisphere and bilateral language dominance do not protect against verbal memory loss after left-sided temporal lobe surgery.