Search

The annotation of brain lesion images is a key step in clinical diagnosis and treatment of a wide spectrum of brain diseases. In recent years, segmentation methods based on deep learning have gained unprecedented popularity, leveraging a large amount of data with high-quality voxel-level annotations. However, due to the limited time clinicians can provide for the cumbersome task of manual image segmentation, semi-supervised medical image segmentation methods present an alternative solution as they require only a few labeled samples for training. In this paper, we propose a novel semi-supervised segmentation framework that combines improved mean teacher and adversarial network. Specifically, our framework consists of (i) a student model and a teacher model for segmenting the target and generating the signed distance maps of object surfaces, and (ii) a discriminator network for extracting hierarchical features and distinguishing the signed distance maps of labeled and unlabeled data. Besides, based on two different adversarial learning processes, a multi-scale feature consistency loss derived from the student and teacher models is proposed, and a shape-aware embedding scheme is integrated into our framework. We evaluated the proposed method on the public brain lesion datasets from ISBI 2015, ISLES 2015, and BRATS 2018 for the multiple sclerosis lesion, ischemic stroke lesion, and brain tumor segmentation respectively. Experiments demonstrate that our method can effectively leverage unlabeled data while outperforming the supervised baseline and other state-of-the-art semi-supervised methods trained with the same labeled data. The proposed framework is suitable for joint training of limited labeled data and additional unlabeled data, which is expected to reduce the effort of obtaining annotated images. [ABSTRACT FROM AUTHOR]

Abstract: One of the key aspects of neuronal differentiation is the array of neurotransmitters and neurotransmitter receptors that each neuron possesses. One important goal of developmental neuroscience is to understand how these differentiated properties are established during development. In this paper, we use fluorescence activated cell sorting and RNA-seq to determine the transcriptome of the Drosophila CNS midline cells, which consist of a small number of well-characterized neurons and glia. These data revealed that midline cells express 9 neuropeptide precursor genes, 13 neuropeptide receptor genes, and 31 small-molecule neurotransmitter receptor genes. In situ hybridization and high-resolution confocal analyses were carried-out to determine the midline cell identity for these neuropeptides and the neuropeptide receptors. The results revealed a surprising level of diversity. Neuropeptide genes are expressed in a variety of midline cell types, including motoneurons, GABAergic interneurons, and midline glia. These data revealed previously unknown functional differences among the highly-related iVUM neurons. There also exist segmental differences in expression for the same neuronal sub-type. Similar experiments on midline-expressed neuropeptide receptor genes reveal considerable diversity in synaptic inputs. Multiple receptor types were expressed in midline interneurons and motoneurons, and, in one case, link feeding behavior to gut peristalsis and locomotion. There were also segmental differences, variations between the 3 iVUMs, and three hormone receptor genes were broadly expressed in most midline cells. The Drosophila Castor transcription factor is present at high levels in iVUM5, which is both GABAergic and expresses the short neuropeptide F precursor gene. Genetic and misexpression experiments indicated that castor specifically controls expression of the short neuropeptide F precursor gene, but does not affect iVUM cell fate or expression of Gad1. This indicates a novel function for castor in regulating neuropeptide gene expression. [Copyright &y& Elsevier]

• Value of fMRI localizer protocols to NHP & cross-species neuroscience research. • Commonly used or novel localizers within NHPs, & keys implementation criteria. • Open access repository of well-established localizer on PRIME-RE platform. Functional localizers are invaluable as they can help define regions of interest, provide cross-study comparisons, and most importantly, allow for the aggregation and meta-analyses of data across studies and laboratories. To achieve these goals within the non-human primate (NHP) imaging community, there is a pressing need for the use of standardized and validated localizers that can be readily implemented across different groups. The goal of this paper is to provide an overview of the value of localizer protocols to imaging research and we describe a number of commonly used or novel localizers within NHPs, and keys to implement them across studies. As has been shown with the aggregation of resting-state imaging data in the original PRIME-DE submissions, we believe that the field is ready to apply the same initiative for task-based functional localizers in NHP imaging. By coming together to collect large datasets across research group, implementing the same functional localizers, and sharing the localizers and data via PRIME-DE, it is now possible to fully test their robustness, selectivity and specificity. To do this, we reviewed a number of common localizers and we created a repository of well-established localizer that are easily accessible and implemented through the PRIME-RE platform. [ABSTRACT FROM AUTHOR]