Collaborating Authors

Developing brain atlas using deep learning algorithms


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.

Developing Brain Atlas through Deep Learning Artificial Intelligence

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.

Decoding Neural Responses in Mouse Visual Cortex through a Deep Neural Network Artificial Intelligence

Finding a code to unravel the population of neural responses that leads to a distinct animal behavior has been a long-standing question in the field of neuroscience. With the recent advances in machine learning, it is shown that the hierarchically Deep Neural Networks (DNNs) perform optimally in decoding unique features out of complex datasets. In this study, we utilize the power of a DNN to explore the computational principles in the mammalian brain by exploiting the Neuropixel data from Allen Brain Institute. We decode the neural responses from mouse visual cortex to predict the presented stimuli to the animal for natural (bear, trees, cheetah, etc.) and artificial (drifted gratings, orientated bars, etc.) classes. Our results indicate that neurons in mouse visual cortex encode the features of natural and artificial objects in a distinct manner, and such neural code is consistent across animals. We investigate this by applying transfer learning to train a DNN on the neural responses of a single animal and test its generalized performance across multiple animals. Within a single animal, DNN is able to decode the neural responses with as much as 100% classification accuracy. Across animals, this accuracy is reduced to 91%. This study demonstrates the potential of utilizing the DNN models as a computational framework to understand the neural coding principles in the mammalian brain.

Deep Learning in Neuroradiology


SUMMARY: Deep learning is a form of machine learning using a convolutional neural network architecture that shows tremendous promise for imaging applications. It is increasingly being adapted from its original demonstration in computer vision applications to medical imaging. Because of the high volume and wealth of multimodal imaging information acquired in typical studies, neuroradiology is poised to be an early adopter of deep learning. Compelling deep learning research applications have been demonstrated, and their use is likely to grow rapidly. This review article describes the reasons, outlines the basic methods used to train and test deep learning models, and presents a brief overview of current and potential clinical applications with an emphasis on how they are likely to change future neuroradiology practice. Facility with these methods among neuroimaging researchers and clinicians will be important to channel and harness the vast potential of this new method. Deep learning is a form of artificial intelligence, roughly modeled on the structure of neurons in the brain, which has shown tremendous promise in solving many problems in computer vision, natural language processing, and robotics.1 It has recently become the dominant form of machine learning, due to a convergence of theoretic advances, openly available computer software, and hardware with sufficient computational power. The current excitement in the field of deep learning stems from new data suggesting its excellent performance in a wide variety of tasks. One benchmark of machine learning performance is the ImageNet Challenge. In this annual competition, teams compete to classify millions of images into discrete categories (tens of different kinds of dogs, fish, cars, and so forth).

AI Surpasses Neuroscientists in Spotting Neurons


Ever wonder how neuroscientists are able to monitor and study what happens inside a living brain in action? One of the challenges in neuroscience is observing the activity of neurons intact in brain tissue that is taking place in a living organism--in vivo. One approach, two-photon calcium imaging, is a method developed circa 1990. In mammalian neurons, calcium is an intracellular messenger. This imaging approach involves the loading of calcium ions (Ca2) indicator dyes in the desired brain region for neuronal monitoring and a two-photon laser scanning microscope for visualization.