A Stacked Generalization of 3D Orthogonal Deep Learning Convolutional Neural Networks for Improved Detection of White Matter Hyperintensities in 3D FLAIR Images

BACKGROUND AND PURPOSE:Accurate and reliable detection of white matter hyperintensities and their volume quantification can provide valuable clinical information to assess neurologic disease progression. In this work, a stacked generalization ensemble of orthogonal 3D convolutional neural networks, StackGen-Net, is explored for improving automated detection of white matter hyperintensities in 3D T2-FLAIR images.MATERIALS AND METHODS:Individual convolutional neural networks in StackGen-Net were trained on 2.5D patches from orthogonal reformatting of 3D-FLAIR (n = 21) to yield white matter hyperintensity posteriors. A meta convolutional neural network was trained to learn the functional mapping from orthogonal white matter hyperintensity posteriors to the final white matter hyperintensity prediction. The impact of training data and architecture choices on white matter hyperintensity segmentation performance was systematically evaluated on a test cohort (n = 9). The segmentation performance of StackGen-Net was compared with state-of-the-art convolutional neural network techniques on an independent test cohort from the Alzheimer’s Disease Neuroimaging Initiative-3 (n = 20).RESULTS:StackGen-Net outperformed individual convolutional neural networks in the ensemble and their combination using averaging or majority voting. In a comparison with state-of-the-art white matter hyperintensity segmentation techniques, StackGen-Net achieved a significantly higher Dice score (0.76 [SD, 0.08], F1-lesion (0.74 [SD, 0.13]), and area under precision-recall curve (0.84 [SD, 0.09]), and the lowest absolute volume difference (13.3% [SD, 9.1%]). StackGen-Net performance in Dice scores (median = 0.74) did not significantly differ (P = .22) from interobserver (median = 0.73) variability between 2 experienced neuroradiologists. We found no significant difference (P = .15) in white matter hyperintensity lesion volumes from StackGen-Net predictions and ground truth annotations.CONCLUSIONS:A stacked generalization of convolutional neural networks, utilizing multiplanar lesion information using 2.5D spatial context, greatly improved the segmentation performance of StackGen-Net compared with traditional ensemble techniques and some state-of-the-art deep learning models for 3D-FLAIR.

White matter hyperintensities (WMHs) correspond to pathologic features of axonal degeneration, demyelination, and gliosis observed within cerebral white matter.¹ Clinically, the extent of WMHs in the brain has been associated with cognitive impairment, Alzheimer’s disease and vascular dementia, and increased risk of stroke.^2,3 The detection and quantification of WMH volumes to monitor lesion burden evolution and its correlation with clinical outcomes have been of interest in clinical research.^4,5 Although the extent of WMHs can be visually scored,⁶ the categoric nature of such scoring systems makes quantitative evaluation of disease progression difficult. Manually segmenting WMHs is tedious, prone to inter- and intraobserver variability, and is, in most cases, impractical. Thus, there is an increased interest in developing fast, accurate, and reliable computer-aided automated techniques for WMH segmentation.Convolutional neural network (CNN)-based approaches have been successful in several semantic segmentation tasks in medical imaging.⁷ Recent works have proposed using deep learning–based methods for segmenting WMHs using 2D-FLAIR images.^8-11 More recently, a WMH segmentation challenge¹² was also organized (http://wmh.isi.uu.nl/) to facilitate comparison of automated segmentation of WMHs of presumed vascular origin in 2D multislice T2-FLAIR images. Architectures that used an ensemble of separately trained CNNs showed promising results in this challenge, with 3 of the top 5 winners using ensemble-based techniques.¹²Conventional 2D-FLAIR images are typically acquired with thick slices (3–4 mm) and possible slice gaps. Partial volume effects from a thick slice are likely to affect the detection of smaller lesions, both in-plane and out-of-plane. 3D-FLAIR images, with isotropic resolution, have been shown to achieve higher resolution and contrast-to-noise ratio¹³ and have shown promising results in MS lesion detection using 3D CNNs.¹⁴ Additionally, the isotropic resolution enables viewing and evaluation of the images in multiple planes. This multiplanar reformatting of 3D-FLAIR without the use of interpolating kernels is only possible due to the isotropic nature of the acquisition. Network architectures that use information from the 3 orthogonal views have been explored in recent works for CNN-based segmentation of 3D MR imaging data.¹⁵ The use of data from multiple planes allows more spatial context during training without the computational burden associated with full 3D training.¹⁶ The use of 3 orthogonal views simultaneously mirrors how humans approach this segmentation task.Ensembles of CNNs have been shown to average away the variances in the solution and the choice of model- and configuration-specific behaviors of CNNs.¹⁷ Traditionally, the solutions from these separately trained CNNs are combined by averaging or using a majority consensus. In this work, we propose the use of a stacked generalization framework (StackGen-Net) for combining multiplanar lesion information from 3D CNN ensembles to improve the detection of WMH lesions in 3D-FLAIR. A stacked generalization¹⁸ framework learns to combine solutions from individual CNNs in the ensemble. We systematically evaluated the performance of this framework and compared it with traditional ensemble techniques, such as averaging or majority voting, and state-of-the-art deep learning techniques.     

Efficacy and Feasibility of Allogeneic Hematopoietic Stem-Cell Transplantation in the Treatment of Refractory Acute Myeloid Leukemia

Background

Refractory acute myeloid leukemia (AML) includes AML includes failure of disease to respond to standard induction chemotherapy, relapse within 6 months after first CR, and 2 or more relapses. The outcome of these patients is usually very poor; only a small proportion can be rescued by allogenic hematopoietic stem-cell transplantation (allo-HSCT). The aim of this study was to evaluate the efficacy and feasibility of allo-HSCT in patients with refractory AML.

Enhanced antitumour activity of doxorubicin and simvastatin combination loaded nanoemulsion treatment against a Swiss albino mouse model of Ehrlich ascites carcinoma

Doxorubicin (DOX) is the most commonly used anticancer drug; however, it has limited use because prolonged administration may result in severe cardiotoxicity. Simvastatin (SIM), generally prescribed for hypercholesterolaemia, has also shown salubrious results in the monotherapy or combinational drug therapy of different cancers in various models. Nanoparticle drug delivery systems are a novel way of improving therapeutics and also improving the absorption and specificity of drugs towards tumour cells. In this study, we exploited this technology to increase drug specificity and minimize imminent adverse effects. In this study, the antitumour activity of the combination formulas of DOX and SIM, either loaded in water (DOX‐SIM‐Solution) or nanoemulsions (NEs) (DOX‐SIM‐NE), was evaluated in a Swiss albino mouse model of Ehrlich ascites carcinoma. The anticancer effect was assessed by quantifying the change in body weight, mean survival time, and percent increase in lifespan (%ILS), determining haematological and serum biochemical parameters (liver function test, kidney function test and lipid profile parameters) as well as studying the histopathological alterations in liver tissues. We observed a clear increase in %ILS of the DOX‐SIM‐Solution group (265.30) that was double the %ILS of the DOX‐SIM‐NE group (134.70). However, DOX‐SIM‐NE had a non‐toxic effect on the haematological parameters, whereas DOX‐SIM‐Solution increased the levels of haemoglobin and lymphocytes. Furthermore, the encapsulation of SIM and DOX into NEs improved the levels of all serum biochemical parameters compared to the DOX‐SIM‐Solution. A reduction in the side effects of DOX‐SIM‐NE on the liver was also established using light microscopy, which revealed that the morphologies of the hepatocytes of the mice were less affected by administration of the DOX‐SIM‐NE treatment than with the DOX‐SIM‐Solution treatment. The study showed that incorporating SIM into the DOX‐loaded‐NE formulation remarkably improved its efficiency and simultaneously reduced its adverse effects.     

Left Ventricular Systolic Dysfunction and Cardiovascular Outcomes in Tetralogy of Fallot: Systematic Review and Meta-analysis

BackgroundAlthough there are robust data about the pathophysiology and prognostic implications of left ventricular (LV) systolic dysfunction in patients with acquired heart disease, similar prognostic data about LV systolic dysfunction are sparse in the tetralogy of Fallot (TOF) population. The purpose of this study was to perform a meta-analysis of all studies that assessed the relationship between LV ejection fraction (LVEF) and cardiovascular adverse events (CAEs) defined as death, aborted sudden death, or sustained ventricular tachycardia.MethodsWe used random-effects models to calculate hazard ratios (HRs) and 95% confidence intervals (CIs).ResultsOf the 1,809 citations, 7 studies with 2,854 patients (age 28 ± 4 years) were included. During 5.6 ± 3.4 years' follow-up, there were 82 deaths, 17 aborted sudden cardiac deaths, and 56 sustained ventricular tachycardia events. Overall, CAEs occurred in 5.1% (144 patients). As a continuous variable, LVEF was a predictor of CAE (HR 1.29, 95% CI, 1.09-1.53, P = 0.001) per 5% decrease in LVEF. Similarly, LVEF < 40% was also a predictor of CAE (HR 3.22, 95% CI, 2.16-4.80, P < 0.001).ConclusionsLV systolic dysfunction was an independent predictor of CAE, and we observed a 30% increase in the risk of CAE for every 5% decrease in LVEF, and a 3-fold increase in the risk of CAE in patients with LVEF <40% compared with other patients. These findings underscore the importance of incorporating LV systolic function in clinical risk stratification of patients with TOF and the need to explore new treatment options to address this problem.     

Computational and experimental studies on the interaction between butyrylcholinesterase and fluoxetine: implications in health and disease

1. Butyrylcholinesterase (BChE) is a serine esterase that plays a role in the detoxification of natural as well as synthetic ester-bond-containing compounds. Alterations in BChE activity are associated with a number of diseases. Cholinergic system abnormalities in particular are correlated with the formation of senile plaques in Alzheimer’s disease (AD), and administration of cholinesterase inhibitors is a common therapeutic approach used to treat AD.

2. Here, our aim was to study the interaction between BChE and fluoxetine.

3. Molecular docking simulations revealed that fluoxetine penetrated deep into the active-site gorge of BChE and that it was engaged in stabilizing noncovalent interactions with multiple subsites. In substrate kinetic studies, the V_m, K_m, k_cat and k_cat/K_m values were found to be 20.59?±?0.36?U mg^?1 protein, 194?±?14?µM, 1.3?×?10⁸?s^?1 and 6.7?×?10⁵?µM^?1s^?1, respectively. Based on inhibitory studies, fluoxetine appeared to inhibit BChE competitively, with an IC₅₀ value of 104?µM and a K_i value of 36.3?±?4.7?µM.

4. Overall, both the low K_i value and the high number of BChE–fluoxetine interactions suggest that fluoxetine is a potent inhibitor of BChE, although in vivo mechanisms for the direct effects of BChE inhibition on various pathologies remain to be further investigated.

     

Esophageal Calibration with Soft Orogasrtric Tube During Laparoscopic Nissen Fundoplication may Reduce Postoperative Transient Dysphagia

Gastroesophageal reflux is the most common benign disorder of the esophagus and laparoscopic Nissen fundoplication has become the standard surgical treatment for its treatment. In our area, where the use of bougie calibration is debatable, postoperative dysphagia is encountered often after this surgery although it is usually not permanent. The aim of this study was to investigate the effect of using a soft silicone tube 39 F in diameter for esophageal calibration during laparoscopic Nissen fundoplication on the incidence of postoperative dysphagia. We divided cases scheduled to undergo laparoscopic Nissen fundoplication between January 2009 and November 2010 into two groups, each consisting 25 patients. Esophageal calibration with a 39 F silicone orogastric tube was used for the first group while there was no operative calibration in the second group. The surgical duration was recorded; the presence and severity of the postoperative dysphagia was calculated by using a dysphagia severity scoring system during the 1-year postoperative follow-up. The dysphagia severity scores were significantly lower in group 1 than group 2 on the postoperative second day and at the end of the first week and first month. We did not find a significant difference at the end of the 6-month and first year. There was also no significant difference regarding surgery duration. The use of a soft orogastric tube 39 F in diameter for esophagus calibration during laparoscopic Nissen fundoplication has significantly decreased the incidence of postoperative transient dysphagia without affecting the duration of surgery. Although dysphagia gradually resolves in the majority of patients, a safe and easy calibration method for its prevention is worth developing, and we believe that the use of our method in larger series could be beneficial.     

Management of asthma in patients supervised by primary care physicians or by specialists.

French asthma patients may be supervised by general practitioners (GPs) and/or specialists. Therefore, this study examined asthma management in patients exclusively supervised by specialists (SPE), GPs, (GP) and both (GP+SPE group), and compared the findings. Asthma patients were consecutively recruited in 348 pharmacies. Each patient completed a questionnaire providing data on personal characteristics, asthma management, perception of disease and asthma supervision. Asthma control was measured using the Asthma Control Test. Questionnaires were linked to computerised records of medications which had been dispensed before inclusion in the study. From the 1,256 patients (mean age = 36.1 yrs, 54.3% females), 11.4, 36.6, and 52.0% were placed in the SPE, GP, and GP+SPE groups, respectively. During the previous 4 weeks, most patients in the SPE group were properly controlled (52.2 versus 26.4 and 21.5% in GP and GP+SPE groups, respectively). The SPE group made more use of fixed combinations of long-acting beta agonist and inhaled corticosteroid, while receiving less short-acting beta agonists, antitussives and antibiotics. Striking differences in symptoms and asthma management were observed according to the type of asthma supervision. The current results strongly support the need to improve the management of asthma in primary care, and the coordination of care between general practitioners and specialists.     

The effect of metoclopramide on gastric emptying in traumatic brain injury.

OBJECTIVE: Gastric paresis in traumatic brain injury (TBI) hinders the effectiveness of enteral support in this patient group. In this study we have investigated the effect of metoclopramide on gastric emptying in TBI patients. METHOD: In this prospective, randomized, controlled, double-blind study, 19 TBI patients with Glasgow Coma Scale scores of 3-11 were included. In all patients, enteral nutrition was commenced with a nasogastric feeding tube within 48 hours of trauma. Patients were randomized into two groups. In the metoclopramide (M) group, 10 mg metoclopramide was delivered intravenously three times daily for 5 days. In the control (C) group, an equal volume of saline was administered. Besides demographics, gastric emptying according to a paracetamol absorption test at days 0 and 5, time to reach target nutritional requirements, gastric residues, intolerance to feeding, nutritional complications, and clinical outcomes were recorded for each patient. RESULTS: The gastric residue rates were 2.7+/-7.4 mL and 8.1+/-17.7 mL per 100 patient days for groups C and M respectively (p=0.408). Similarly, feeding intolerance and complication rates did not significantly differ between groups C and M, (respectively p=0.543 and 0.930). Gastric emptying parameters also were similar between the study groups. CONCLUSION: We were unable to document any advantage to using metoclopramide in TBI patients. Simple intragastric enteral feeding with close monitoring of the possible complications seems to be sufficient with acceptable morbidity rates.