Practices and ethical concerns regarding preimplantation diagnosis. Who regulates preimplantation genetic diagnosis in Brazil?

Preimplantation genetic diagnosis (PGD) was originally developed to diagnose embryo-related genetic abnormalities for couples who present a high risk of a specific inherited disorder. Because this technology involves embryo selection, the medical, bioethical, and legal implications of the technique have been debated, particularly when it is used to select features that are not related to serious diseases. Although several initiatives have attempted to achieve regulatory harmonization, the diversity of healthcare services available and the presence of cultural differences have hampered attempts to achieve this goal. Thus, in different countries, the provision of PGD and regulatory frameworks reflect the perceptions of scientific groups, legislators, and society regarding this technology. In Brazil, several texts have been analyzed by the National Congress to regulate the use of assisted reproduction technologies. Legislative debates, however, are not conclusive, and limited information has been published on how PGD is specifically regulated. The country requires the development of new regulatory standards to ensure adequate access to this technology and to guarantee its safe practice. This study examined official documents published on PGD regulation in Brazil and demonstrated how little direct oversight of PGD currently exists. It provides relevant information to encourage reflection on a particular regulation model in a Brazilian context, and should serve as part of the basis to enable further reform of the clinical practice of PGD in the country.     

A new approach to prevent HIV transmission: Project Protect intervention for recently infected individuals

Past research suggests that as many as 50% of onward human immunodeficiency virus (HIV) transmissions occur during acute and recent HIV infection. It is clearly important to develop interventions which focus on this highly infectious stage of HIV infection to prevent further transmission in the risk networks of acutely and recently infected individuals. Project Protect tries to find recently and acutely infected individuals and prevents HIV transmission in their risk networks. Participants are recruited by community health outreach workers at community-based HIV testing sites and drug users' community venues, by coupon referrals and through referrals from AIDS clinics. When a network with acute/recent infection is identified, network members are interviewed about their risky behaviors, network information is collected, and blood is drawn for HIV testing. Participants are also educated and given prevention materials (condoms, syringes, educational materials); HIV-infected participants are referred to AIDS clinics and are assisted with access to care. Community alerts about elevated risk of HIV transmission are distributed within the risk networks of recently infected. Overall, 342 people were recruited to the project and screened for acute/recent HIV infection. Only six index cases of recent infection (2.3% of all people screened) were found through primary screening at voluntary counseling and testing (VCT) sites, but six cases of recent infection were found through contact tracing of these recently infected participants (7% of network members who came to the interview). Combining screening at VCT sites and contact tracing the number of recently infected people we located as compared to VCT screening alone. No adverse events were encountered. These first results provide evidence for the theory behind the intervention, i.e., in the risk networks of recently infected people there are other people with recent HIV infection and they can be successfully located without increasing stigma for project participants.     

Impact of β-glucan on the Fecal Water Genotoxicity of Polypectomized Patients

The aim of the study was to determine the effect of β-glucan on the cytotoxicity and genotoxicity of polypectomized patient's fecal water (FW). Polypectomized volunteers (n = 69) were randomly assigned to consume bread with or without β-glucan, for 3 months. FW was collected at the beginning (t = 0), the 30th and 90th day and 2 wk after the intervention. Cytotoxicity and genotoxicity were estimated on Caco-2 cells, using trypan blue exclusion test and comet assay, respectively. Gastrointestinal symptoms were recorded and subjects kept a 3-day food diary at baseline and after completion. Trypan blue exclusion test revealed cell survival of approximately 87% after incubation with FW. The FW samples showed 49% genotoxicity at the baseline. Genotoxicity in the intervention group decreased during the trial reaching statistical significance on the 90th day compared to control. An increase was noticed 2 wk after the trial, but it still remained significantly lower compared to control. Group-specific analysis for β-glucan also revealed significant decrease in the genotoxicity on the 90th day compared to baseline. β-glucan ingestion in polypectomized patients significantly decreased the genotoxicity of their FW. Our findings suggest that β-glucan consumption could possibly provide protection against colon cancer development.     

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.