The advent of large-scale artificial intelligence (AI) models has a transformative effect on neuroscience research, which represents a paradigm shift from the traditional computational methods through the facilitation of end-to-end learning from raw brain signals and neural data. In this paper, we explore the transformative effects of large-scale AI models on five major neuroscience domains: neuroimaging and data processing, brain-computer interfaces and neural decoding, molecular neuroscience and genomic modeling, clinical assistance and translational frameworks, and disease-specific applications across neurological and psychiatric disorders. These models are demonstrated to address major computational neuroscience challenges, including multimodal neural data integration, spatiotemporal pattern interpretation, and the derivation of translational frameworks for clinical deployment. Moreover, the interaction between neuroscience and AI has become increasingly reciprocal, as biologically informed architectural constraints are now incorporated to develop more interpretable and computationally efficient models. This review highlights both the notable promise of such technologies and key implementation considerations, with particular emphasis on rigorous evaluation frameworks, effective domain knowledge integration, and comprehensive ethical guidelines for clinical use. Finally, a systematic listing of critical neuroscience datasets used to derive and validate large-scale AI models across diverse research applications is provided.

Background: There are many challenges and opportunities in the clinical deployment of AI tools in radiology. The current study describes a radiology software platform called NeoMedSys that can enable efficient deployment and refinements of AI models. We evaluated the feasibility and effectiveness of running NeoMedSys for three months in real-world clinical settings and focused on improvement performance of an in-house developed AI model (VIOLA-AI) designed for intracranial hemorrhage (ICH) detection. Methods: NeoMedSys integrates tools for deploying, testing, and optimizing AI models with a web-based medical image viewer, annotation system, and hospital-wide radiology information systems. A prospective pragmatic investigation was deployed using clinical cases of patients presenting to the largest Emergency Department in Norway (site-1) with suspected traumatic brain injury (TBI) or patients with suspected stroke (site-2). We assessed ICH classification performance as VIOLA-AI encountered new data and underwent pre-planned model retraining. Performance metrics included sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). Results: NeoMedSys facilitated iterative improvements in the AI model, significantly enhancing its diagnostic accuracy. Automated bleed detection and segmentation were reviewed in near real-time to facilitate re-training VIOLA-AI. The iterative refinement process yielded a marked improvement in classification sensitivity, rising to 90.3% (from 79.2%), and specificity that reached 89.3% (from 80.7%). The bleed detection ROC analysis for the entire sample demonstrated a high area-under-the-curve (AUC) of 0.949 (from 0.873). Model refinement stages were associated with notable gains, highlighting the value of real-time radiologist feedback.

Motion disorders pose a significant global health concern and are often managed with pharmacological treatments that may lead to undesirable long-term effects. Current therapeutic strategies lack differentiation between healthy and unhealthy muscles in a patient, necessitating a targeted approach to distinguish between musculature. There is still no motion analyzer application for this purpose. Additionally, there is a deep gap in motion analysis software as some studies prioritize simulation, neglecting software needs, while others concentrate on computational aspects, disregarding simulation nuances. We introduce a comprehensive five-phase methodology to analyze the neuromuscular system of the lower body during gait. The first phase employs an innovative IoT-based method for motion signal capture. The second and third phases involve an agent-driven biomechanical model of the lower body skeleton and a model of human voluntary muscle. Thus, using an agent-driven approach, motion-captured signals can be converted to neural stimuli. The simulation results are then analyzed by our proposed ensemble neural network framework in the fourth step in order to detect abnormal motion in each joint. Finally, the results are shown by a userfriendly graphical interface which promotes the usability of the method. Utilizing the developed application, we simulate the neuromusculoskeletal system of some patients during the gait cycle, enabling the classification of healthy and pathological muscle activity through joint-based analysis. This study leverages cloud computing to create an infrastructure-independent application which is globally accessible. The proposed application enables experts to differentiate between healthy and unhealthy muscles in a patient by simulating his gait.

Localizing oneself during endoscopic procedures can be problematic due to the lack of distinguishable textures and landmarks, as well as difficulties due to the endoscopic device such as a limited field of view and challenging lighting conditions. Expert knowledge shaped by years of experience is required for localization within the human body during endoscopic procedures. In this work, we present a deep learning method based on anatomy recognition, that constructs a surgical path in an unsupervised manner from surgical videos, modelling relative location and variations due to different viewing angles. At inference time, the model can map an unseen video's frames on the path and estimate the viewing angle, aiming to provide guidance, for instance, to reach a particular destination. We test the method on a dataset consisting of surgical videos of transsphenoidal adenomectomies, as well as on a synthetic dataset.

Computed Tomography (CT) image guidance enables accurate and safe minimally invasive treatment of diseases, including cancer and chronic pain, with needle-like tools via a percutaneous approach. The physician incrementally inserts and adjusts the needle with intermediate images due to the accuracy limitation of free-hand adjustment and patient physiological motion. Scanning frequency is limited to minimize ionizing radiation exposure for the patient and physician. Robots can provide high positional accuracy and compensate for physiological motion with fewer scans. To accomplish this, the robots must operate within the confined imaging bore while retaining sufficient dexterity to insert and manipulate the needle. This paper presents CRANE: CT Robotic Arm and Needle Emplacer, a CT-compatible robot with a design focused on system dexterity that enables physicians to manipulate and insert needles within the scanner bore as naturally as they would be able to by hand. We define abstract and measurable clinically motivated metrics for in-bore dexterity applicable to general-purpose intra-bore image-guided needle placement robots, develop an automatic robot planning and control method for intra-bore needle manipulation and device setup, and demonstrate the redundant linkage design provides dexterity across various human morphology and meets the clinical requirements for target accuracy during an in-situ evaluation.

Department of Radiology, Case Western Reserve University, Cleveland, OH, 44106, USA Abstract Background: Recent studies have used basic epicardial adipose tissue (EAT) assessments (e.g., volume and mean HU) to predict risk of atherosclerosis-related, major adverse cardiovascular events (MACE). Objectives: Create novel, hand-crafted EAT features, "fat-omics", to capture the pathophysiology of EAT and improve MACE prediction. We extracted 148 radiomic features (morphological, spatial, and intensity) and used Cox elastic-net for feature reduction and prediction of MACE. Results: Traditional fat features gave marginal prediction (EAT-volume/EAT-mean-HU/ BMI gave C-index 0.53/0.55/0.57, Significant improvement was obtained with 15 fat-omics features (C-index=0.69, Other high-risk features include kurtosis-of-EAT-thickness, reflecting the heterogeneity of thicknesses, and EATvolume-in-the-top-25%-of-the-heart, emphasizing adipose near the proximal coronary arteries. Kaplan-Meyer plots of Cox-identified, high-and low-risk patients were well separated with the median of the fat-omics risk, while high-risk group having HR 2.4 times that of the low-risk group (P<0.001). Conclusion: Preliminary findings indicate an opportunity to use more finely tuned, explainable assessments on EAT for improved cardiovascular risk prediction. Introduction Cardiovascular disease is a major cause of morbidity and mortality worldwide (1), leading to 17.9 million deaths globally each year (2). Numerous risk score methodologies have been developed to predict risks from cardiovascular disease, but these methods often lack sufficient discrimination (3). Accurate explainable risk prediction models will provide useful information to patients and physicians for more personalized medications and interventions. Previous studies have determined the usefulness of coronary calcification Agatston score as obtained from CT calcium score (CTCS) images for cardiovascular risk prediction.

Heart failure (HF) is a leading cause of death. Early intervention is the key to reduce HF-related morbidity and mortality. Data from the baseline visits (1987–89) of the Atherosclerosis Risk in Communities (ARIC) study was used. Incident hospitalized HF events were ascertained by ICD codes. Participants with good quality baseline ECGs were included. Participants with prevalent HF were excluded. ECG-artificial intelligence (AI) model to predict HF was created as a deep residual convolutional neural network (CNN) utilizing standard 12-lead ECG. The area under the receiver operating characteristic curve (AUC) was used to evaluate prediction models including (CNN), light gradient boosting machines (LGBM), and Cox proportional hazards regression. A total of 14 613 (45% male, 73% of white, mean age standard deviation of 54 5) participants were eligible.

Face recognition is a stark example of a technology that is being deployed faster than society and the law can adopt new norms and rules. It lets governments and private enterprise track citizens anywhere there is a camera, even if they're not carrying any devices. In general, people who are in public don't have any legal expectation of privacy and can be photographed or recorded. Because of this, the technology has the potential to be more intrusive than phone tracking, the legality of which the U.S. Supreme Court will soon decide. There are only two states, Texas and Illinois, that limit private companies' ability to track people via their faces.

The trucking industry scored a victory this week when Republican lawmakers effectively blocked Obama administration safety rules aimed at keeping tired truckers off the highway. The American Trucking Associations is pledging to come back next month, when Republicans will control the White House and Congress, and try to block state laws that require additional rest breaks for truckers beyond what federal rules require. The group says there should be one uniform national rule on work hours for interstate truckers. The trucking industry's latest triumph has caused concern among safety advocates that it may signal the start of a broad rollback of transportation safety regulations once there's no longer a Democratic president to check the tendency of Republican lawmakers to side with industry. "Unfortunately, it's going to be an open season on safety in this coming Congress."