To uncover the organizational principles governing the human brain, neuroscientists are in need of developing high-throughput methods that can explore the structure and function of distinct brain regions using animal models. The first step towards this goal is to accurately register the regions of interest in a mouse brain, against a standard reference atlas, with minimum human supervision. The second step is to scale this approach to different animal ages, so as to also allow insights into normal and pathological brain development and aging. We introduce here a fully automated convolutional neural network-based method (SeBRe) for registration through Segmenting Brain Regions of interest in mice at different ages. We demonstrate the validity of our method on different mouse brain post-natal (P) developmental time points, across a range of neuronal markers. Our method outperforms the existing brain registration methods, and provides the minimum mean squared error (MSE) score on a mouse brain dataset. We propose that our deep learning-based registration method can (i) accelerate brain-wide exploration of region-specific changes in brain development and (ii) replace the existing complex brain registration methodology, by simply segmenting brain regions of interest for high-throughput brain-wide analysis.
A team of researchers from the Brain Research Institute of the University of Zurich and the Swiss Federal Institute of Technology (ETH) have developed a fully automated brain registration method that could be used to segment brain regions of interest in mice. Neuroscientists are always seeking out new methods of exploring the structure and function of different brain regions, which are initially applied on animals but could eventually lead to important discoveries about the organization of the human brain. "My lab aims to reveal how the mammalian brain develops its abilities to process and react to sensory stimuli," Theofanis Karayannis, one of the researchers who carried out the study told Tech Xplore. "Most of the work we do is on the experimental side, utilizing the mouse as a model system and techniques that range from molecular-genetic to functional and anatomical." This study is part of a larger project, which also includes "Exploring Brain-wide Development of Inhibition through Deep Learning," a study in which Karayannis and his colleagues use deep learning algorithms to comprehensively track the so-called inhibitory neurons over time in order to gauge the development of capabilities of the brain at specific points in time.
DeepMind's Demis Hassabis once pointed to the human brain as a paramount inspiration for building AI with human-like intelligence. The meteoric success of deep learning showcases how insights from neuroscience--memory, learning, decision-making, vision--can be distilled into algorithms that bestow silicon minds with a shadow of our cognitive prowess. This month, the prestigious journal Nature published an entire series highlighting the symbiotic growth between neuroscience and AI. It's been a long time coming. At their core, both disciplines are solving the same central problem--intelligence--but coming from different angles, and at different levels of abstraction.
Your brain is one enigmatic hunk of meat--a wildly complex web of neurons numbering in the tens of billions. But years ago, when you were in the womb, it began as little more than a scattering of undifferentiated stem cells. A series of genetic signals transformed those blank slates into the wrinkly, three-pound mass between your ears. Scientists think the way your brain looks and functions can be traced back to those first molecular marching orders--but precisely when and where these genetic signals occur has been difficult to pin down.
We present a novel approach to automatically segment magnetic resonance (MR) images of the human brain into anatomical regions. Our methodology is based on a deep artificial neural network that assigns each voxel in an MR image of the brain to its corresponding anatomical region. The inputs of the network capture information at different scales around the voxel of interest: 3D and orthogonal 2D intensity patches capture the local spatial context while large, compressed 2D orthogonal patches and distances to the regional centroids enforce global spatial consistency. Contrary to commonly used segmentation methods, our technique does not require any non-linear registration of the MR images. To benchmark our model, we used the dataset provided for the MICCAI 2012 challenge on multi-atlas labelling, which consists of 35 manually segmented MR images of the brain. We obtained competitive results (mean dice coefficient 0.725, error rate 0.163) showing the potential of our approach. To our knowledge, our technique is the first to tackle the anatomical segmentation of the whole brain using deep neural networks.