Dynamic functional brain networks (DFBNs) are powerful tools in neuroscience research. Recent studies reveal that DFBNs contain heterogeneous neural nodes with more extensive connections and more drastic temporal changes, which play pivotal roles in coordinating the reorganization of the brain. Moreover, the spatio-temporal patterns of these nodes are modulated by the brain's historical states. However, existing methods not only ignore the spatio-temporal heterogeneity of neural nodes, but also fail to effectively encode the temporal propagation mechanism of heterogeneous activities. These limitations hinder the deep exploration of spatio-temporal relationships within DFBNs, preventing the capture of abnormal neural heterogeneity caused by brain diseases.

Despite the diversity of brain data acquired and advanced AI-based algorithms to analyze them, brain features are rarely used in clinics for diagnosis and prognosis. Here we argue that the field continues to rely on cohort comparisons to seek biomarkers, despite the well-established degeneracy of brain features. Using a thought experiment, we show that more data and more powerful algorithms will not be sufficient to identify biomarkers of brain diseases. We argue that instead of comparing patient versus healthy controls using single data type, we should use multimodal (e.g. brain activity, neurotransmitters, neuromodulators, brain imaging) and longitudinal brain data to guide the grouping before defining multidimensional biomarkers for brain diseases.

Analyzing connections between brain regions of interest (ROI) is vital to detect neurological disorders such as autism or schizophrenia. Recent advancements employ graph neural networks (GNNs) to utilize graph structures in brains, improving detection performances. Current methods use correlation measures between ROI's blood-oxygen-level-dependent (BOLD) signals to generate the graph structure. Other methods use the training samples to learn the optimal graph structure through end-to-end learning. However, implementing those methods independently leads to some issues with noisy data for the correlation graphs and overfitting problems for the optimal graph. In this work, we proposed Bargrain (balanced graph structure for brains), which models two graph structures: filtered correlation matrix and optimal sample graph using graph convolution networks (GCNs). This approach aims to get advantages from both graphs and address the limitations of only relying on a single type of structure. Based on our extensive experiment, Bargrain outperforms state-of-the-art methods in classification tasks on brain disease datasets, as measured by average F1 scores.

Cutting-edge advancements in neuroscience research have revealed the intricate relationship between brain structure and function, while the success of artificial neural networks highlights the importance of network architecture. Now is the time to bring them together to better unravel how intelligence emerges from the brain's multiscale repositories. In this review, we propose the Digital Twin Brain (DTB) as a transformative platform that bridges the gap between biological and artificial intelligence. It consists of three core elements: the brain structure that is fundamental to the twinning process, bottom-layer models to generate brain functions, and its wide spectrum of applications. Crucially, brain atlases provide a vital constraint, preserving the brain's network organization within the DTB. Furthermore, we highlight open questions that invite joint efforts from interdisciplinary fields and emphasize the far-reaching implications of the DTB. The DTB can offer unprecedented insights into the emergence of intelligence and neurological disorders, which holds tremendous promise for advancing our understanding of both biological and artificial intelligence, and ultimately propelling the development of artificial general intelligence and facilitating precision mental healthcare. 1 Introduction Demystifying the principles that account for human intelligent behaviors, such as recognizing faces and making decisions, has been attracting a tremendous amount of interdisciplinary effort and is also the driving force behind the boom in artificial intelligence. The closer we can approach the intrinsicality of intelligence, the higher the possibility that we could master the emergence of intelligence. As the biological recesses of intelligent behaviors, the multiscale characteristics of the human brain are specifically being identified to explain the remarkable neurobiological basis underlying intelligent abilities.

Making machines mimic or even surpass human intellectual behaviour and thinking methods has always been a scientific field full of rich imagination and great challenges. The recent great advances in Artificial Intelligence technology represented by driverless cars and the AlphaGo game have led to enthusiasm and a great deal of funding for the AI field. Considering the development bases, existing problems and opportunities of Chinese AI, strategic thinking on the progress of this industry is continuously proposed for discussion and decision-making reference. The Internet action guidance opinions issued by the State Council have clearly stated that AI is one of the key development areas for the creation of new industrial models. Four Departments, in addition to the National Development and Reform Commission and the Ministry of Science and Technology, have jointly issued implementation plans for Internet .

In recent years Alzheimer's disease has been on the rise throughout the world and is rarely diagnosed at an early stage when it can still be effectively controlled. Using artificial intelligence, KTU researchers conducted a study to identify whether human-computer interfaces could be adapted for people with memory impairments to recognize a visible object in front of them. Rytis Maskeliūnas, a researcher at the Department of Multimedia Engineering at Kaunas University of Technology (KTU), considers that the classification of information visible on the face is a daily human function: "While communicating, the face "tells" us the context of the conversation, especially from an emotional point of view, but can we identify visual stimuli based on brain signals?" The visual processing of the human face is complex. Information such as a person's identity or emotional state can be perceived by us, analyzing the faces.

Eye movements read by a new AI application can reveal thoughts, memories, goals -- and brain diseases. A new tool developed at the Kavli Institute for Systems Neuroscience in Norway and described in an article in Nature Neuroscience, predicts gaze direction and eye movement directly from magnetic resonance imaging (MRI) scans. The goal is to make eye tracking diagnostics a standard in brain imaging research and hospital clinics. Whenever you explore an environment or search for something, you scan the scene using continuous rapid eye movements. Your eyes also make short stops to fixate on certain elements of the scene that you want more detailed information about.

Altoida Inc. today announced a $6.3 million round of venture capital financing to bring its FDA-cleared and CE Mark-approved medical device and brain health data platform to patients, physicians and researchers around the globe. Led by a team of esteemed neuroscientists, physicians and computer scientists, Altoida uses digital biomarkers to drive better clinical outcomes for brain disease. The Series A round was led by M Ventures, the corporate venture capital arm of the science and technology company Merck KGaA, Darmstadt, Germany, with participation from Grey Sky Venture Partners, VI Partners AG, Alpana Ventures, and FYRFLY Venture Partners. The new capital will be used to further expand Altoida's global presence with an immediate focus on commercialization activities in the US and EU markets. "Altoida is at the forefront of a new era to leverage Artificial Intelligence and Machine Learning to assess brain health," said Alexander Hoffmann, Principal, New Businesses at M Ventures.

A highly concerning new study lays bare the danger of repeated head impacts for rugby players. After performing scans of 44 elite adult rugby players, experts found 23 per cent had abnormalities in brain structure, specifically in white matter and blood vessels of the brain. White matter mainly comprises the neural pathways, the long extensions of the nerve cells, and is crucial to our cognitive ability. The study also found 50 per cent of the rugby players had an unexpected reduction in brain volume. Non-profit the Drake Foundation, which backed the study, is now calling for immediate changes in rugby protocols to ensure long-term welfare of elite players.

One tough problem is the diagnosis, surgical treatment, and monitoring of brain diseases. The range of AI technologies available for dealing with brain disease is growing fast, and exciting new methods are being applied to brain problems as computer scientists gain a deeper understanding of the capabilities of advanced algorithms. In a paper published this week in APL Bioengineering, by AIP Publishing, Italian researchers conducted a systematic literature review to understand the state of the art in the use of AI for brain disease. Their search yielded 2,696 results, and they narrowed their focus to the top 154 most cited papers and took a closer look. For example, a generative adversarial network was used to synthetically create an aged brain in order to see how disease advances over time.