Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions.

Head motion during MRI acquisition presents significant challenges for neuroimaging analyses. In this work, we present a retrospective motion correction framework built on a Fourier domain motion simulation model combined with established 3D convolutional neural network (CNN) architectures. Quantitative evaluation metrics were used to validate the method on three separate multi-site datasets. The 3D CNN was trained using motion-free images that were corrupted using simulated artifacts. CNN based correction successfully diminished the severity of artifacts on real motion affected data on a separate test dataset as measured by significant improvements in image quality metrics compared to a minimal motion reference image. On the test set of 13 image pairs, the mean peak signal-to-noise-ratio was improved from 31.7 to 33.3 dB. Furthermore, improvements in cortical surface reconstruction quality were demonstrated using a blinded manual quality assessment on the Parkinson's Progression Markers Initiative (PPMI) dataset. Upon applying the correction algorithm, out of a total of 617 images, the number of quality control failures was reduced from 61 to 38. On this same dataset, we investigated whether motion correction resulted in a more statistically significant relationship between cortical thickness and Parkinson's disease. Before correction, significant cortical thinning was found to be restricted to limited regions within the temporal and frontal lobes. After correction, there was found to be more widespread and significant cortical thinning bilaterally across the temporal lobes and frontal cortex. Our results highlight the utility of image domain motion correction for use in studies with a high prevalence of motion artifacts, such as studies of movement disorders as well as infant and pediatric subjects.

The Challenge of Tightening Door-to-Needle Timings in a Telestroke Setting: An Emergency Medicine Driven Initiative.

Introduction Administering intravenous thrombolytic therapy within 60 minutes on arrival in any healthcare facility is challenging, especially when done by Emergency Medicine Physicians (EMP) via telemedicine in centres without onsite neurology cover. Prior quality improvement interventions have improved median Door-to-Needle (DTN) timings in our centre; however, it still falls short of the DTN target of 60 minutes.  Methods Various quality improvement interventions were implemented over four months by a multi-disciplinary telestroke workgroup led by EMPs to improve DTN timings for patients presenting with acute ischaemic strokes. A retrospective observational study was conducted to review if these interventions resulted in an improvement in DTN timings while keeping the rates of stroke mimics given thrombolytic therapy, haemorrhagic conversions and 30-day mortality rates low.  Results A total of 279 patients were evaluated. Median DTN timings significantly improved from 71.0 minutes pre-intervention to 62.0 minutes post-intervention (p=0.012). Correspondingly, the proportion of patients with DTN ≤ 60 minutes increased from 31.7% pre-intervention to 47.0% post-intervention, giving an odds ratio of 1.91 (95% CI 1.17 - 3.11, p=0.009). There were no significant differences found in the rates of stroke mimics, haemorrhagic conversions and 30-day mortality pre and post-intervention. Conclusion The implementation of EMP led to systemic quality improvement interventions is associated with improved DTN timings without compromising clinical quality outcome measures like haemorrhagic conversion rates and 30-day mortality rates. EMPs, with a broad knowledge base and familiarity, interacting with various specialities and co-ordinating care, are uniquely suited in this role to drive change. More work in the public health sector would also have to be done to improve the population's response to acute stroke symptoms.

Differences in clinical outcomes of paediatric cystic fibrosis patients with and without meconium ileus.

BACKGROUND: Meconium ileus (MI) affects up to 20% of newborns with cystic fibrosis (CF). We compared clinical outcomes between Australian paediatric CF patients with and without meconium ileus (non-MI). METHODS: This was a retrospective case-control study of MI and non-MI patients in New South Wales, Australia, from 1988 to 2010. MI patients were matched 1:1 with pancreatic insufficient non-MI patients for age, sex and CF clinic. Clinical measurements, nutrition and gastrointestinal outcomes over this period were compared between groups using linear mixed models for continuous variables to account for age. RESULTS: There were 162 matched pairs (N=324, 52% female) with mean (SD) age of 15.3 (8.2) and 14.9 (7.9) years for MI and non-MI patients respectively (P=0.6). MI patients aged 5-23 had poorer FEV1% compared to non-MI patients (estimate -0.070 SE [0.02], P=0.003). There were no significant differences in P. aeruginosa isolation rates; however S. aureus isolation rates were lower in MI patients (72%) compared to non-MI (82%) (OR 0.6 [0.3-1.0], P=0.03). Chronic colonisation rates for P. aeruginosa and S. aureus were not significantly different between groups. MI patients aged 2-20 had significantly lower BMI Z-scores over time (estimate -0.25 SE [0.1], P=0.02). MI patients were more likely to receive oral feed supplements (OR 2.8 [1.4-6.1], P=0.003) and gastrostomy formation (OR 4.4 [1.1-24.6], P=0.02). CONCLUSIONS: CF patients with MI may have worse lung function, growth and nutrition than non-MI patients over time. Meconium ileus may be an early poor prognostic factor for CF.