Stroke is a major global health problem that causes mortality and morbidity. Predicting the outcomes of stroke intervention can facilitate clinical decision-making and improve patient care. Engaging and developing deep learning techniques can help to analyse large and diverse medical data, including brain scans, medical reports, and other sensor information, such as EEG, ECG, EMG, and so on. Despite the common data standardisation challenge within the medical image analysis domain, the future of deep learning in stroke outcome prediction lies in using multimodal information, including final infarct data, to achieve better prediction of long-term functional outcomes. This article provides a broad review of recent advances and applications of deep learning in the prediction of stroke outcomes, including (i) the data and models used, (ii) the prediction tasks and measures of success, (iii) the current challenges and limitations, and (iv) future directions and potential benefits. This comprehensive review aims to provide researchers, clinicians, and policy makers with an up-to-date understanding of this rapidly evolving and promising field.

PurposeGiven objective benefits of robotic-assisted sacrocolpopexy (RSCP) to the voiding function/deficit of patients with pelvic organ prolapse (POP) waits to be clarified, this study investigated if RSCP modifies voiding functions of POP patients by focusing on its impact on the outlet resistance-dependent voiding workload using pressure-volume analysis (PVA), a protocol thermodynamically assaying work expenditure by the bladder in voiding cycles.MethodsPre- and post-operative cystometry and PVA of 22 female patients, who underwent RSCP for POP (stage ≥ II), were reviewed. Mean voiding resistance (Rvod), mean voiding pressure (Pvod), mean voiding flow (Fvod), voided volume (Vvod), voiding time (Tvod), and the trajectory-enclosed area (Apv) were analyzed.ResultsThe PVA, in which trajectory shaped an enclosed loop representing a voiding cycle, was established by adapting from the time-domain cystometry. Compared to the pre-operative control, RSCP decreased Rvod, Pvod, and Tvod (p = 0.003, 0.042, and 0.040, respectively. All N = 22) but increased Fvod (p = 0.036, N = 22) without markedly affecting Vvod (p = 0.580, N = 22). Apv was decreased after RSCP (p = 0.017, N = 22). The RSCP-decreased Rvod (ΔRvod) displayed a moderate correlation with both the decreased Pvod (ΔPvod, r = 0.551, p = 0.007, N = 22) and the increased Fvod (ΔFvod, r=-0.625, p = 0.001, N = 22). The ΔFvod moderately correlated with the decreased Tvod (ΔTvod, r=-0.620, p = 0.002, N = 22). Moreover, the RSCP-decreased Apv (ΔApv) displayed correlation with the ΔPvod (r = 0.385, p = 0.047, N = 22).ConclusionsThrough diminishing outlet resistance of POP patients, RSCP not only prompted urine emission thereby increased voiding efficacy but also decreased the pressure developed for driving urine flow that lessened voiding workload.Clinical Trial Registration ClinicalTrials.gov (NCT05682989).

Stereotactic systems have traditionally used Cartesian coordinate combined with linear algebraic mathematical models to navigate the brain. Previously, the development of a novel stereotactic system allowed for improved patient comfort, reduced size, and carried through a simplified interface for surgeons. The system was designed with a work envelope and trajectory range optimized for deep brain stimulation applications only. However, it could be applied in multiple realms of neurosurgery by spanning the entire brain. To this end, a system of translational and rotational adapters was developed to allow total brain navigation capabilities. Adapters were designed to fit onto a Skull Anchor Key of a stereotactic frame system to allow for rotation and translation of the work envelope. Mathematical formulas for the rotations and translations associated with each adapter were developed. Mechanical and image-guided accuracies were examined using a ground truth imaging phantom. The system's clinical workflow and its ability to reliably and accurately be used in a surgical scenario were investigated using a cadaver head and computed tomography guidance. Eight adapters designed and 3D-printed allowed the work envelope to be expanded to the entire head. The mechanical error was 1.75 ± 0.09mm (n = 20 targets), and the cadaver surgical targeting error was 1.18 ± 0.28mm (n = 10 implantations). The novel application of conventional and geometric algebra in conjunction with hardware modifications significantly expands the work envelope of the stereotactic system to the entire cranial cavity. This approach greatly extends the clinical applications by the system.

The limited imaging depth of optical endoscope restrains the identification of tissues under surface during the minimally invasive spine surgery (MISS), thus increasing the risk of critical tissue damage. This study is proposed to improve the accuracy and effectiveness of automatic spinal soft tissue identification using a forward-oriented ultrasound endoscopic system. Total 758 ex-vivo soft tissue samples were collected from ovine spines to create a dataset with four categories including spinal cord, nucleus pulposus, adipose tissue, and nerve root. Three conventional methods including Gray-level co-occurrence matrix (GLCM), Empirical Wavelet Transform (EWT), Variational Mode Decomposition (VMD) and two deep-learning based methods including Densely Connected Neural Network (DenseNet) model, one-dimensional Vision Transformer (ViT) model, were applied to identify the spinal tissues. The two deep learning methods outperformed the conventional methods with both accuracy over 95%. Especially the signal-based method (ViT) achieved an accuracy of 98.31% and a specificity of 99.2%, and the inference latency was only 0.0025s. It illustrated the feasibility of applying the forward-oriented ultrasound endoscopic system for real-time intraoperative recognition of critical spinal tissues to enhance the precision and safety of minimally invasive spine surgery.

The online version contains supplementary material available at 10.1007/s13534-024-00433-9.

Inter-crystal scattering (ICS) events in Positron Emission Tomography (PET) present challenges affecting system sensitivity and image quality. Understanding the physics and factors influencing ICS occurrence is crucial for developing strategies to mitigate its impact. This review paper explores the physics behind ICS events and their occurrence within PET detectors. Various methodologies, including energy-based comparisons, Compton kinematics-based approaches, statistical methods, and Artificial Intelligence (AI) techniques, which have been proposed for identifying and recovering ICS events accurately are introduced. Energy-based methods offer simplicity by comparing energy depositions in crystals. Compton kinematics-based approaches utilize trajectory information for first interaction position estimation, yielding reasonably good results. Additionally, statistical approach and AI algorithms contribute by optimizing likelihood analysis and neural network models for improved positioning accuracy. Experimental validations and simulation studies highlight the potential of recovering ICS events and enhancing PET sensitivity and image quality. Especially, AI technologies offers a promising avenue for addressing ICS challenges and improving PET image accuracy and resolution. These methods offer promising solutions for overcoming the challenges posed by ICS events and enhancing the accuracy and resolution of PET imaging, ultimately improving diagnostic capabilities and patient outcomes. Further studies applying these approaches to real PET systems are needed to validate theoretical results and assess practical implementation feasibility.

Artificial intelligence (AI) has had a significant impact on human life because of its pervasiveness across industries and its rapid development. Although AI has achieved superior performance in learning and reasoning, it encounters challenges such as substantial computational demands, privacy concerns, communication delays, and high energy consumption associated with cloud-based models. These limitations have facilitated a paradigm change in on-device AI processing, which offers enhanced privacy, reduced latency, and improved power efficiency through the direct execution of computations on devices. With advancements in neuromorphic systems, spiking neural networks (SNNs), often referred to as the next generation of AI, are currently in focus as on-device AI. These technologies aim to mimic the human brain efficiency and provide promising real-time processing with minimal energy. This study reviewed the application of SNNs in the analysis of biomedical signals (electroencephalograms, electrocardiograms, and electromyograms), and consequently, investigated the distinctive attributes and prospective future paths of SNNs models in the field of biomedical signal analysis.

[This corrects the article DOI: 10.1007/s13534-024-00386-z.].

Multiclass classification of brain tumors from magnetic resonance (MR) images is challenging due to high inter-class similarities. To this end, convolution neural networks (CNN) have been widely adopted in recent studies. However, conventional CNN architectures fail to capture the small lesion patterns of brain tumors. To tackle this issue, in this paper, we propose a global transformer network dubbed GT-Net for multiclass brain tumor classification. The GT-Net mainly comprises a global transformer module (GTM), which is introduced on the top of a backbone network. A generalized self-attention block (GSB) is proposed to capture the feature inter-dependencies not only across spatial dimension but also channel dimension, thereby facilitating the extraction of the detailed tumor lesion information while ignoring less important information. Further, multiple GSB heads are used in GTM to leverage global feature dependencies. We evaluate our GT-Net on a benchmark dataset by adopting several backbone networks, and the results demonstrate the effectiveness of GTM. Further, comparison with state-of-the-art methods validates the superiority of our model.

Despite holding valuable information, unstructured data pose challenges for efficient recognition due to the difficulties in feature extraction using traditional Von-Neumann architecture systems, which are limited by power and time bottlenecks. Although biological neural signals offer crucial insights, they require more effective recognition solutions due to inherent noise and the vast volumes of data. Inspired by the human brain, neuromorphic systems have emerged as promising alternatives because of their parallelism, low power consumption, and error tolerance. By leveraging deep neural networks (DNNs), these systems can recognize imprecise data through two key processes: learning (feature extraction) and testing (feature matching and recognition). During the learning phase, DNNs extract and store unique features such as weight changes in synapse units. In the testing phase, new data are compared with the stored features for recognition. The parallelization of the neuromorphic system enables the efficient processing of large, imprecise datasets with minimal energy consumption. Nevertheless, the hardware implementation is essential for determining the full potential of DNNs. This paper focuses on synapse devices, which are the core units for hardware DNN implementations, and presents a biomedical application example: a rat neural signal recognition system implemented using a synapse device-based neuromorphic system.