Extended reality technologies are transforming fields such as healthcare, entertainment, and education, with Smart Eye-Wears (SEWs) and Artificial Intelligence (AI) playing a crucial role. However, SEWs face inherent limitations in computational power, memory, and battery life, while offloading computations to external servers is constrained by network conditions and server workload variability. To address these challenges, we propose a Federated Reinforcement Learning (FRL) framework, enabling multiple agents to train collaboratively while preserving data privacy. We implemented synchronous and asynchronous federation strategies, where models are aggregated either at fixed intervals or dynamically based on agent progress. Experimental results show that federated agents exhibit significantly lower performance variability, ensuring greater stability and reliability. These findings underscore the potential of FRL for applications requiring robust real-time AI processing, such as real-time object detection in SEWs.

Oran Knowlson, a British teenager with a severe type of epilepsy called Lennox-Gastaut syndrome, became the first person in the world to trial a new brain implant last October, with phenomenal results – his daytime seizures were reduced by 80%. "It's had a huge impact on his life and has prevented him from having the falls and injuring himself that he was having before," says Martin Tisdall, a consultant paediatric neurosurgeon at Great Ormond Street Hospital (Gosh) in London, who implanted the device. "His mother was talking about how he's had such a improvement in his quality of life, but also in his cognition: he's more alert and more engaged." Oran's neurostimulator sits under the skull and sends constant electrical signals deep into his brain with the aim of blocking abnormal impulses that trigger seizures. The implant, called a Picostim and about the size of a mobile phone battery, is recharged via headphones and operates differently between day and night. "The device has the ability to record from the brain, to measure brain activity, and that allows us to think about ways in which we could use that information to improve the efficacy of the stimulation that the kids are getting," says Tisdall. "What we really want to do is to deliver this treatment on the NHS."

Over the last two decades, augmented reality (AR) has led to the rapid development of new interfaces in various fields of social and technological application domains. One such domain is medicine, and to a higher extent surgery, where these visualization techniques help to improve the effectiveness of preoperative and intraoperative procedures. Following this trend, this paper presents SLIMBRAIN, a real-time acquisition and processing AR system suitable to classify and display brain tumor tissue from hyperspectral (HS) information. This system captures and processes HS images at 14 frames per second (FPS) during the course of a tumor resection operation to detect and delimit cancer tissue at the same time the neurosurgeon operates. The result is represented in an AR visualization where the classification results are overlapped with the RGB point cloud captured by a LiDAR camera. This representation allows natural navigation of the scene at the same time it is captured and processed, improving the visualization and hence effectiveness of the HS technology to delimit tumors. The whole system has been verified in real brain tumor resection operations.

There's a lot to like about brain-computer interfaces, those sci-fi-sounding devices that jack into your skull and turn neural signals into software commands. Experimental BCIs help paralyzed people communicate, use the internet, and move prosthetic limbs. In recent years, the devices have even gone wireless. If mind-reading computers become part of everyday life, we'll need doctors to install the tiny electrodes and transmitters that make them work. So if you have steady hands and don't mind a little blood, being a BCI surgeon might be a job for you. Shahram Majidi, a neurosurgeon at Mount Sinai Hospital in New York, began operating in clinical trials for a BCI called the Stentrode in 2022.

The edge intelligence (EI) has been widely applied recently. Spliting the model between device, edge server, and cloud can improve the performance of EI greatly. The model segmentation without user mobility has been investigated deeply by previous works. However, in most use cases of EI, the end devices are mobile. Only a few works have been carried out on this aspect. These works still have many issues, such as ignoring the energy consumption of mobile device, inappropriate network assumption, and low effectiveness on adaptiving user mobility, etc. Therefore, for addressing the disadvantages of model segmentation and resource allocation in previous works, we propose mobility and cost aware model segmentation and resource allocation algorithm for accelerating the inference at edge (MCSA). Specfically, in the scenario without user mobility, the loop interation gradient descent (Li-GD) algorithm is provided. When the mobile user has a large model inference task needs to be calculated, it will take the energy consumption of mobile user, the communication and computing resource renting cost, and the inference delay into account to find the optimal model segmentation and resource allocation strategy. In the scenario with user mobility, the mobiity aware Li-GD (MLi-GD) algorithm is proposed to calculate the optimal strategy. Then, the properties of the proposed algorithms are investigated, including convergence, complexity, and approximation ratio. The experimental results demonstrate the effectiveness of the proposed algorithms.

-- Splitting the inference model between device, edge server, and cloud can improve the performance of EI greatly. Additionally, the non - orthogonal multiple access (NOMA), which is the key supporting technologies of B5G/6G, ca n achieve massive connections and high spectrum efficiency. Motivated by the benefits of NOMA, integrating NOMA with model split in MEC to reduce the inference latency further becomes attractive. However, the NOMA based communication during split inference has not been properly considered in previous works. Therefore, in this paper, we integrate the NOMA into split inference in MEC, and p ropose the effective communication and computing resource allocation algorithm to accelerat e the model inference at edge . Specifically, when the mobile user has a large model inference task needed to be calculated in the NOMA - based MEC, it will take the energy consumption of both device and edge server and the inference latency into account to find the optimal model split s trategy, subchannel allocation strategy (uplink and downlink), and transmission power allocation strategy (uplink and downlink). Since the minimum inference delay and energy consumption cannot be satisfied simultaneously, and the variables of subchannel al location and model split are discrete, the gradient descent (GD) algorithm is adopted to find the optimal tradeoff between them. Moreover, the loop iteration GD approach (Li - GD) is proposed to reduce the complexity of GD algorithm that caused by the parame ter discrete. Additionally, the properties of the proposed algorithm are also investigated, which demonstrate the effectiveness of the proposed algorithms. The artificial intelligence has been widely used and changed our life greatly, such as metaverse [1 - 2], auto matic driving [2 - 4], image generation [5], etc. However, since the AI model is always large for achieving high accuracy, the computing resource that needed for these models are huge. Therefore, it is inappropriate to deploy these AI models on the mobile de vices, such as mobile phones and vehicles, in which the computing resource is quite limited.

Neurosurgeon Dr. Paul Saphier on the warning signs to look for. I am a neurosurgeon who specializes in the treatment of acute strokes, brain bleeds, and tumors. Every second counts for my patients, and I am determined to help as many as I can. This Thanksgiving dinner, I left my family to operate on a patient with a life-threatening stroke. This is what you need to know about strokes and how artificial intelligence is helping surgeons like me save even more patients.

Decoding language and facial expressions from brain signals using artificial intelligence means that scientists could soon "read minds," a neurosurgeon said. Providing vision to the blind and hearing to the deaf could become possible with a breakthrough, AI-powered surgical procedure that could even make "mind reading" a reality, a California neuroscientist told Fox News. Ann Johnson, a Canadian teacher who lost her ability to talk after a stroke left her paralyzed in 2005, was able to speak through a cloned version of her voice after undergoing a surgery that connected her brain to artificial intelligence. The procedure involved fixing over 250 electrodes to Johnson's brain and connecting those to an array of computers through a port on the back of her head. Those, in turn, translated her brain activity into English using an AI-generated avatar that spoke on her behalf. The surgery Johnson underwent is non-invasive and not very difficult to replicate, Chang said.

An advocacy group of more than 17,000 doctors has petitioned the Food and Drug Administration (FDA) to disqualify Elon Musk's Neuralink from receiving approval for its brain implant. The Physicians Committee for Responsible Medicine (PCRM) claims Neuralink has violated the'good laboratory practices' (GLP) regulations, which ensures the quality and integrity of non-clinical laboratory studies, with its'hack job' surgeries and staff'manipulating data.' Some of the animal's deaths were at the hands of Matthew McDougall, the head neurosurgeon, who administered nearly six times the amount of an unapproved'toxic' substance that led to a monkey's death, a former Neuralink employee told DailyMail.com. This was stated in messages written by John Morrison, the study director at the University of California, Davis (UC Davis), Merkley added. Elon Musk said his Neuralink is seeking FDA approval to start human trials, but a group is trying to block these efforts.

MIT engineers have developed a telerobotic system to help surgeons quickly and remotely treat patients experiencing a stroke or aneurysm. With a modified joystick, surgeons in one hospital may control a robotic arm at another location to safely operate on a patient during a critical window of time that could save the patient's life and preserve their brain function. The robotic system, whose movement is controlled through magnets, is designed to remotely assist in endovascular intervention -- a procedure performed in emergency situations to treat strokes caused by a blood clot. Such interventions normally require a surgeon to manually guide a thin wire to the clot, where it can physically clear the blockage or deliver drugs to break it up. One limitation of such procedures is accessibility: Neurovascular surgeons are often based at major medical institutions that are difficult to reach for patients in remote areas, particularly during the "golden hour" -- the critical period after a stroke's onset, during which treatment should be administered to minimize any damage to the brain.