Biomedical Physics & Engineering Express

Background: Independent end-to-end verification of adaptive radiotherapy on MR-Linac systems is limited by the lack of patient-specific phantoms able to reproduce imaging and dosimetric properties from CT and MRI scanners. We present a method for automated generation of 4D, patient-specific, multi-material 3D-printable phantoms for quality assurance of adaptive radiotherapy on a 1.5T MR-Linac. Methods: Patient images were automatically segmented using a pretrained deep learning model. The segmented structures were converted into high-resolution 3D meshes and assembled into printable phantoms. A dosimeter holder was inserted at user-defined anatomical locations, with orientation optimized to avoid traversal across heterogeneous tissue interfaces. Physiological motion was incorporated by generating phantoms from images at different timepoints and interpolating deformation fields to create continuous 4D models. Multi-material organs designed by mixing a set of six polymers at various proportions were used to reproduce tissue-specific imaging properties. The properties of material mixtures were evaluated in a clinical CT simulator and a 1.5T MR-Linac. Results: The proposed workflow enables automated generation of anatomically realistic phantoms with several types of embedded dosimeters. A discrete search method was designed for placement and immobilization of OSLD, film, and ion chamber dosimeters. Calibration curves for Hounsfield units were derived through variations in radiopaque material content, while MR signal intensity was modulated by gel and tissue matrix mixtures. Patient-derived abdominal phantoms were fabricated at multiple scales while replicating internal anatomical detail. Multi-dimensional phantom generation enabled continuous representation of motion states with consistent mesh topology across phases. Conclusions: We demonstrate an end-to-end workflow for automated generation of 4D patient-specific phantoms for MR-Linac quality assurance. The method combines realistic anatomy, embedded dosimetry, multimodal imaging properties, and physiological motion within a single fabrication framework. This approachmay enable an improved validation of adaptive radiotherapy workflows in MR-guided treatment devices.

Point-of-care ultrasound has transformed bedside diagnostics, yet current systems remain limited by rigid form factors, bulky external electronics and the need for skilled operators. Here we report a conformable ultrasound imaging patch that integrates a 1024-channel CMOS ultrasound application-specific integrated circuit (ASIC) directly beneath a conformable piezocomposite transducer array. The 10 mm X 8 mm, 1024-element ASIC contains on-chip transmit and receive beamforming, reducing the effective off-chip channel count by 16X while preserving image fidelity. Fabricated on a flexible polyimide substrate and bonded using anisotropic conductive film, the patch operates untethered from conventional ultrasound consoles and requires only a laptop for control and data acquisition. The device supports focused, plane-wave and diverging-wave transmission with steering over {+/-}30{degrees} in azimuth and {+/-}15{degrees} in elevation, achieving peak-to-peak acoustic pressures up to 7 MPa at a 4.4-MHz center frequency (mechanical index of 1.7), within diagnostic safety limits. Phantom experiments demonstrate three-dimensional imaging with axial and lateral resolutions (in both XZ and YZ planes) of 0.5 mm and 2 mm, respectively, and accurate contrast reproduction in tissue-mimicking phantoms. Human studies further demonstrate three-dimensional (3D) visualization of the internal jugular vein and carotid artery, as well as rib-shadow-free imaging of pleural motion during respiration. This work establishes a scalable architecture for chronic, wearable ultrasound imaging and highlights the potential of CMOS-integrated, conformable ultrasound systems for continuous physiological monitoring and remote diagnostics.

Accurate segmentation of thin-wall organs-at-risk (OARs)-the cochlea, vestibular semicircular canals, internal auditory canal, tympanic cavity, and middle ear-is clinically relevant for head-and-neck radiotherapy planning, yet these small, thin-wall structures remain among the most challenging targets for automated delineation. Dual-frequency feature fusion is a promising direction for boundary-sensitive representation, but under the investigated FP16 FFT-FcaNet setting, we observe an approximately 863-fold activation-scale mismatch between the FFT and FcaNet branches, causing a nominal 5 percent residual coefficient to behave as an approximately 43-fold dominant term. We propose FreqFuseNet, which resolves this mismatch by normalizing the FcaNet branch to the FFT activation scale before residual injection with a fixed low-amplitude coefficient (beta = 0.05), restoring beta as an interpretable 5 percent residual-amplitude coefficient relative to the FFT feature scale. Under a controlled binary per-OAR ROI protocol on the SegRap2023 head-and-neck CT benchmark across 10 clinically prioritized thin-wall OARs, FreqFuseNet achieves Dice of 0.849, HD95 of 0.824 mm, and SDice@1mm of 0.959 in the primary seed, with comparable performance in an independent second seed (Dice 0.843, HD95 0.823 mm). FreqFuseNet yields statistically significant case-level aggregate improvements over 3D U-Net and MedNeXt-S (Wilcoxon p < 0.01 and p < 0.05, respectively), using only 29.7 million parameters versus 414.6 million for the full wavelet baseline.

Purpose: To develop and evaluate a deep learning model for automated quantification of breast arterial calcification (BAC) on screening mammography and to assess whether AI-derived BAC burden predicts major adverse cardiovascular events (MACE) in women. Methods: In this retrospective study, 202,006 women who underwent screening mammography without history of MACE were included. A BAC segmentation model was trained on an expert-annotated dataset using a multi-task U-Net with a ResNet-18 encoder to detect and segment BAC. BAC burden was quantified as area (mm{superscript 2}) from model-generated masks using DICOM pixel spacing and categorized by tertiles into low, intermediate, and high. The PREVENT score and incident MACE were identified from electronic health records. Cox proportional hazards models were developed to evaluate AI-derived BAC burden and PREVENT score alone, and combined models for 5 - and 10-year cardiovascular risk prediction. Results: Among 202,006 women (mean age 54.8{+/-}11.7 years), 23.1% had AI-detected BAC, and 7,701 (3.8%) developed incident MACE during a median follow - up of 7.5 years. On the geographically held-out test set, the BAC model achieved an AUROC of 0.97, Dice score of 0.6678, and Pearson correlation of 0.961 between AI-derived and manually annotated BAC burden. BAC burden increased with age and was higher among women who developed MACE. Five - year MACE incidence increased across BAC categories from 1.5% in women without BAC to 6.9% in those with high BAC burden. BAC burden alone showed modest prediction of MACE, with 5-year and 10-year AUROCs of 0.661 and 0.650, respectively, while PREVENT achieved AUROCs of 0.781 and 0.771. Adding BAC to PREVENT produced minimal improvement in discrimination. Conclusion: Deep learning-based BAC quantification from routine mammography is feasible, accurate, and associated with future cardiovascular risk. Although BAC added little to PREVENT for overall discrimination, it may serve as a scalable opportunistic imaging biomarker to identify women at elevated cardiovascular risk and support preventive care.

Recent NCCN guideline highlighted AI-based mammographic risk prediction, but AI-based breast cancer detection remains questionable to translation. One barrier is current models often do not match routine clinical reasoning, which may add decision burden than benefits. In practice, radiologists compare current and prior mammograms while assessing breast density, bilateral symmetry, and lesion laterality. To align AI with this reasoning, we developed MuSTAF, a multi-task spatiotemporal attention fusion model for patient-level breast cancer classification from longitudinal full-field digital mammography. MuSTAF uses up to three recent mammograms, integrates temporal and cross-view information, refines suspicious-region features, and jointly predicts cancer status, breast density, and bilateral symmetry, with a separate laterality classifier for cancer-positive cases. In an internal case-control cohort (n = 351), MuSTAF achieved a cancer classification (AUC=0.84) exceeding all architecture-level baselines and published mammography AI models adapted to the same task (AUC [&le;] 0.81). Simultaneously, it achieved AUCs of 0.83/0.80 for density/laterality assessments, and removing these auxiliary tasks reduced cancer detection performance. On the external CSAW-CC dataset (n = 8,723), model performance improved from 0.72 to 0.88 when restricting cancer cases to those with latest exams within 60 days before diagnosis, showing that temporally distant labels may shift detection evaluation toward risk prediction. Longitudinal analysis further showed that three recent exams outperformed five exams internally (AUC = 0.84 vs 0.80) and externally (0.72 vs 0.66), indicating recent imaging evidence mattered more than remote history. Overall, MuSTAF model improved longitudinal mammographic cancer classification while providing auxiliary outputs, and clarified temporal factors for applying AI to screening detection.

Purpose: RF-induced heating remains a major barrier to MRI access for patients with epicardial cardiac implantable electronic devices (CIEDs). Although ISO/TS 10974 Tier-3 transfer function (TF) methods are established for unbranched leads, no analogous framework exists for bifurcated leads, in which branch asymmetry and inter-branch coupling may substantially alter heating. We developed and validated a cumulative transfer function (cTF) framework to address this gap. Methods: Following ISO/TS 10974 Tier-3 formalism, we measured, calibrated, and validated cTFs for a commercial 35 cm bipolar epicardial lead at 1.5 T. The framework explicitly accounts for branch-specific response and cross-branch coupling. Validation was performed with 24 canonical lead configurations in a homogeneous phantom and, without recalibration, in a heterogeneous anthropomorphic pediatric phantom with clinically derived trajectories. A single-branch TF approximation served as a comparator. The validated cTF was applied to predict RF heating across adult and pediatric human models at multiple imaging landmarks. Results: Compared with the single-branch TF approximation, the cTF reduced prediction error by nearly 70% in the primary validation dataset. In secondary validation, the cTF maintained low error across clinically relevant trajectories and imaging landmarks. In human models, the framework revealed marked anatomy- and landmark-dependent variation in predicted heating for the tested 35 cm lead, with low predicted heating in pediatric models and substantially higher heating in selected adult chest and upper abdominal imaging scenarios. Conclusion: The cTF provides a validated framework for RF-heating assessment of bifurcated leads and substantially improves prediction accuracy over single-branch TF approximations that neglect branch coupling.

Fine-tuning can adapt pretrained medical imaging models to new clinical datasets, but device-specific domain shifts may limit generalizability. We evaluated Mirai, a mammography-based deep learning model for breast cancer risk prediction, in a large screening cohort containing Hologic and General Electric (GE) full-field digital mammography systems, including GE Premium View (GE PV) and Tissue Equalization (GE TE) post-processing software. Native Mirai showed lower performance on TE images than on Hologic or PV images. Fine-tuning on TE images improved TE performance, particularly for short-term risk prediction, but substantially reduced performance on Hologic images, consistent with catastrophic forgetting. To mitigate this effect, we developed a device-invariant model using interleaved multi-device sampling and conditional adversarial training. This approach largely restored Hologic performance while maintaining improved TE performance, providing better robustness across heterogeneous imaging platforms. Comparison of cumulative and annual risk AUCs over a five-year time horizon further showed that performance gains were driven mainly by short- and intermediate-term predictions. These findings highlight both the value and dangers of device-specific fine-tuning and support balanced domain-adaptation strategies for deploying mammography-based risk models across diverse clinical imaging environments.

ABSTRACT: Most breast cancer prediction studies skip calibration reporting entirely. Fewer still examine calibration by demographic subgroup. Predicted probabilities that are systematically off for specific racial or gender groups produce biased clinical decisions, and aggregate statistics will not catch that. Objective: To introduce the Demographic Calibration Gap Score (DCGS), a metric that measures how much calibration error varies across demographic subgroups, and to show how it performs across five classifiers, four calibration conditions, and two datasets. Methods: Five classifiers were trained on the Wisconsin Diagnostic Breast Cancer dataset (n=569) and evaluated on a breast cancer cohort from MIMIC-IV (n=1,316). Three global calibration methods were applied: no calibration, Platt scaling, and isotonic regression. A fourth condition, subgroup-targeted Platt scaling, was applied to the MIMIC cohort. DCGS was computed as across racial and gender subgroups, with 95% bootstrap confidence intervals. Conformal prediction coverage and Demographic Coverage Gap (DCG) were reported. Results: On Wisconsin, all five models achieved AUROC above 0.98 and ECE below 0.12. Performance fell sharply on the MIMIC external cohort: AUROC dropped to 0.45-0.57 for base and globally calibrated variants, confirming distributional shift. DCGS exceeded the 0.05 clinical significance threshold in 28 of 40 model-calibration combinations on the race axis. Neither global Platt nor isotonic calibration reliably reduced DCGS below that threshold. Conformal coverage collapsed to roughly 25% on MIMIC, and racial DCG exceeded 0.15 for all 20 model-variant combinations. Conclusions: Reducing population-level ECE through global recalibration does not reliably close demographic calibration gaps. DCGS gives researchers a direct, standardized way to detect and report those disparities. Code and the DCGS computation library are released as open-source Python under the MIT License.

Objective: To develop and evaluate a deep learning model for five-year breast cancer risk prediction from screening breast ultrasound (BUS) examinations. Methods: This retrospective study included 295,298 breast ultrasound examinations from 122,072 women imaged between 2012 and 2020. Patients were split into training, validation, and test sets; the test set included screening examinations only. BUS-Risk-Net aggregated image features using attention-based multiple instance learning and combined them with age and ultrasound-estimated breast density to predict 2- to 5-year risk. Performance was compared with the full Tyrer-Cuzick model in a matched case-control cohort and with a reduced Tyrer-Cuzick model in the held-out test set. Risk stratification was evaluated within BI-RADS density categories. Results: In the matched case-control cohort (n = 240 women), BUS-Risk-Net achieved a 5-year AUC of 0.632 (95% CI, 0.562-0.702), versus 0.514 for the full Tyrer-Cuzick model (95% CI, 0.440-0.588; p = 0.04). Among 19,548 examinations from 9,015 women eligible for 5-year evaluation in the test set, BUS-Risk-Net achieved an AUC of 0.679 (95% CI, 0.653-0.706), versus 0.594 for the reduced Tyrer-Cuzick model (95% CI, 0.564-0.623; P < .001). Observed 5-year cancer incidence increased across AI-defined risk tiers within each BI-RADS density category, ranging from 0.0% to 5.8% after AI stratification, compared with 2.1% to 3.6% across density categories alone. Discussion: Deep learning models applied to screening breast ultrasound could enable long-term breast cancer risk prediction and stratify risk beyond breast density alone. External and prospective validation is needed before clinical use.

ObjectiveTo preserve the encoding of visual information in prosthetic vision as close to natural as possible, subretinal photovoltaic implants, which replace the lost photoreceptors, strive to stimulate the second-order retinal neurons, the bipolar cells, while avoiding direct activation of the downstream retinal ganglion cells. To assess the range of such selective subretinal activation, we implanted the devices in rodent models of retinal degeneration and measured the stimulation thresholds based on the visually evoked potentials. After assessment of the bipolar cell-mediated thresholds, direct activation of retinal ganglion cells was measured following intraocular injection of synaptic blockers. Since these chemicals are toxic to the retina, this procedure can only be done once in each animal. ApproachWe developed a machine-learning model that identifies the stimulation pathway directly from the recorded visually evoked potentials, eliminating the need for synaptic blockers. The model was trained on recordings from rats implanted with PRIMA subretinal arrays and evaluated on two additional implant architectures, a second rat species, and a different anesthesia protocol. Main ResultsThe classifier achieved a balanced accuracy of 92% in cross-validation on the training data. Generalization to all unseen experimental conditions yielded an average balanced accuracy of 91%. Integrated Gradients analysis showed that combined bipolar and ganglion cell responses were driven by the early P1 component, while bipolar cell responses relied on later waveform components, consistent with thalamocortical processing dynamics. SignificanceThe described computational alternative to pharmacological blockers should improve the experimental throughput, allow multiple recordings over the lifetime of the same animal, and might be applicable to optimization of the stimulation settings in patients.

Background: Nuclear medicine and radiopharmaceutical development require coordinated radiochemistry, dosimetry, molecular imaging, radiation-safety and clinical decision processes. Current workflows remain fragmented, difficult to audit and poorly standardised for evaluating domain-specific AI support. Methods: We developed RadGuide AI, a nuclear medicine agent built around a traceable data-model-tool loop. Patent, literature and clinical-trial records were converted into 15,596 initial QA items; relevance screening, completeness checks, semantic deduplication and cross-validation retained 5,474 core QA items. MedGemma-27B-Instruct served as the foundation model and was adapted with LoRA. The system incorporated 55 MCP-wrapped tools covering radiopharmaceutical R&D, clinical decision support, imaging analysis and radiation-safety/dosimetry. Evaluation used a locked N=200 benchmark with predefined denominators, leakage control, expert scoring, statistical procedures, factuality audits and tool-execution metrics. Results: RadGuide-LLM achieved 88.5% answer accuracy (177/200; 95% CI, 83.3-92.2%) and a Macro-Average score of 21.5/25 (bootstrap 95% CI, 20.9-22.0), exceeding GPT-4o, DeepSeek-V3.2 and the base MedGemma model in this technical evaluation. Supplementary audits reported guideline compliance, terminology recall, knowledge coverage, tool-routing success and preclinical/phantom dosimetry agreement with explicit denominators and confidence intervals. Interpretation: RadGuide AI converts nuclear medicine queries into auditable retrieval, tool selection, calculation, verification and reporting workflows. The findings support technical feasibility, not definitive patient-level clinical validation; prospective multicentre studies and external benchmark release remain required before clinical deployment.

Cervical cancer represents a pressing global health challenge, emphasizing the critical need for accurate and timely diagnostic methods to facilitate effective treatment and improve survival rates. In response to this challenge, the study presents CerViX-Net, an innovative classification framework designed to advance cervical cancer detection through enhanced computational efficiency and diagnostic accuracy. The development of CerViX-Net is motivated by the limitations of traditional diagnostic models, particularly in handling the computational and memory demands of large-scale data, while ensuring precise feature extraction and classification. CerViX-Net employs a hybrid deep learning architecture that combines the capabilities of ResNet50, EfficientNet-B0, and a Modified Vision Transformer (ViT) module. The ResNet50 branch extracts hierarchical features through stacked convolutional and identity blocks. In another path, the modified ViT module transforms image patches via linear projection, augments them with positional and class embeddings, and processes them using Parallel Transformer Encoder layers to model contextual relationships. Concurrently, EfficientNet-B0 utilizes MBConv blocks to extract multi-scale representations. The feature outputs from all three branches are integrated and passed through a classification head consisting of dropout layers and dense layers to ensure robust and accurate predictions. The proposed framework is rigorously evaluated on the Mendeley LBC dataset, achieving exceptional performance metrics with an accuracy of 99.69%, precision of 99.28%, recall of 99.48%, and an F1-score of 99.52%. The robustness of CerViX-Net is further validated on the SIPaKMeD and Herlev Pap Smear datasets, where it demonstrates comparable excellence, underscoring its efficacy and adaptability across diverse cytology datasets. Statistical validation using Friedman's test further reinforces its superiority over competing methods.

A test technique for measuring high-frequency transient current components in deep brain tissue is presented. The technique applies a voltage pulse with a high value in dV/dt, generating a corresponding current pulse with high dI/dt that can elicit measurable transient current responses from the electrode/tissue interface and adjacent brain tissue; responses are analyzed in the frequency domain by Fast Fourier Transform at a 200 kHz sampling frequency. The method was motivated by prior evidence that ferritin and neuromelanin in catecholaminergic tissue may support high-frequency conduction properties that have not previously been characterized in vivo. The protocol was applied in 277 measurements across five Sprague Dawley rats at cortical and basal ganglia locations in different locations in the brain. Preliminary spectral results show differences between catecholaminergic regions and cortical tissue that support further development and validation of the method.

ObjectiveOur prior studies have demonstrated that lateral spinal cord stimulation can evoke somatosensory percepts in the missing foot in individuals with a lower-limb amputation. However, subjects reported concurrent sensations in their residual limb. In this study, we evaluate the hypothesis that using high-density paddle electrodes with smaller contact sizes, and multipolar stimulation configurations could evoke more focal sensations in the foot over a wide range of stimulation amplitudes. ApproachWe used a combination of electrophysiology and computational modelling methods to investigate the selective activation of distal nerve branches in response to lateral spinal cord stimulation in cats. In six acute feline experiments, we performed an L3-S1 laminectomy and placed custom 32-electrode paddles laterally over the dura of the spinal cord. We recorded antidromic action potentials in the distal branches of the sciatic and femoral nerve trunks in response to stimulation using three contact diameters (150, 500 and 1000 {micro}m) and two stimulation configurations - monopolar and bipolar stimulation. We replicated the neural recruitment patterns from those experiments in a computational model of the feline lumbar spinal cord. We then used the model to examine neural recruitment with 1.8 mm and 2.5 mm contacts, as well as a tripolar guarded-cathode configuration. Main resultsIn the electrophysiology experiments, the 500 {micro}m-diameter electrodes achieved the most selective nerve activation (68%) compared to 62% for both 150 and 1000 {micro}m-diameter electrodes. The minimum amplitudes for recruiting nerve branches (i.e., threshold) as well as the dynamic ranges were largely similar for the different contact diameters (median: 35 {micro}A) and stimulation configurations (30 {micro}A for bipolar stimulation; 35 {micro}A for monopolar stimulation). The computational model reproduced the finding that selectivity did not differ significantly among the three contact sizes tested in cat experiments, though it revealed that increasing contact diameter above 1000 {micro}m raised the minimum amplitude required for selective activation and reduced spinal root selectivity. Across both approaches, we consistently recruited large-diameter afferents that are critical for somatosensory applications of spinal cord stimulation. SignificanceOur results indicate that, relative to clinical electrodes, reducing the contact diameter of stimulation electrodes can evoke focal sensations, but further reductions below 1000 {micro}m may fail to improve selectivity. This study highlights potential constraints with achieving focal selectivity that are not dependent on the design of the electrodes.

CT perfusion (CTP) is central to acute-stroke and oncologic imaging, yet quantitative outputs vary substantially across vendor software, undermining reproducibility. We present an open, transparent core (ctp-core) that fits first-pass time-attenuation curves with a gamma-variate model, derives perfusion indices (peak enhancement, time-to-peak, bolus-arrival time, and area under the curve) analytically from the fitted parameters, and renders parametric maps with the ASIST-Japan standardized lookup table (a-LUT) so that visualization is comparable across sites. Every parameter, bound, and processing step is exposed. The method is validated on Monte-Carlo synthetic curves with known ground truth; no confidential or patient data are used. Across signal-to-noise ratio (SNR) levels 5 to 100 (200 independent runs per level) the pipeline recovers peak time to within 0.03-0.52 s and peak amplitude to within 0.4-8.1% (mean absolute error), degrading monotonically with noise; at a representative SNR of 20 it recovers peak time within 0.13 s, peak amplitude within 2.0%, and bolus-arrival time within 0.51 s, with fit quality R-squared = 0.98. The reproducibility demonstration is deterministic (fixed seed) and re-runs to bit-stable metrics. All code, the synthetic-data generator, the standardized-visualization module, evaluation scripts, and a 34-test suite are released openly for independent verification. The contribution is a fully open, parameter-transparent gamma-variate plus standardized-visualization pipeline with reproducible synthetic benchmarks: a reference others can audit, reuse, and build on.

Purpose: To implement a comprehensive knowledge-based algorithm (KBA) for pancreatic cancer staging based on the current Japanese guidelines and to evaluate its performance as a clinical decision support system in comparison with a retrieval-augmented large language model (LLM) system. Materials and methods: A KBA covering TNM classification, stage classification, and resectability classification was implemented as a web application. The correctness of the system outputs was exhaustively verified for all possible inputs. Subsequently, six non-board-certified radiologists performed pancreatic cancer staging for 12 simulated cases with imaging findings under three conditions: unassisted, LLM-assisted, and KBA-assisted. Staging accuracy and staging time were compared among the three conditions using pairwise proportion z-tests and Welch's t-tests, respectively. Results: In the comparative experiment, staging accuracy was 81.9%, 80.6%, and 98.6% in the unassisted, LLM-assisted, and KBA-assisted conditions, respectively. Mean staging time was 229.2, 401.9, and 196.2 s, respectively. The KBA-assisted condition showed higher accuracy than both the unassisted and LLM-assisted conditions (both p<0.001). Staging time was longer in the LLM-assisted condition than in the other two conditions (both p<0.001). Conclusion: A comprehensive KBA for pancreatic cancer staging based on the current Japanese guidelines was implemented and exhaustively verified. In a preliminary comparative experiment, KBA assistance improved staging accuracy without increasing staging time, whereas LLM assistance increased staging time without improving staging accuracy. These findings suggest that verified KBA systems may be feasible and useful for clinical tasks governed by explicit guideline-based rules.

Over the last decade, pre-clinical research has witnessed the advancement of human induced pluripotent stem-cell derived 3D brain organoid models and their differentiation into specific brain regions. In the realm of Parkinsons disease research, development of midbrain-specific organoids has enabled studies of this neurodegenerative disorder in patient derived 3D organoid models that attempt to recapitulate the human brain complexity. Within this line of research, neural functionality of the organoid models is established through electrophysiology. As a novel methodological approach, this study aimed to establish whether clustering of electrophysiological activity originating from midbrain organoids would aid in identifying different types of action-potential waveforms exhibited by neurons within the organoid model. Long-term extracellular electrophysiological recordings were conducted by use of a multi-electrode array device. The local field potential signal was spike-sorted, and the extracted putative neuron units were clustered into groups of spike waveform profiles. After establishing this methodological analysis pipeline, the clusters of waveform types were further analyzed in terms of electrophysiology. Results revealed that the clustering approach was successful at identifying three types of spike waveforms categories. Furthermore, it was proposed that one spike waveform profile potentially originated from dopaminergic neurons, which were one on the neural cells populating the organoid models. Overall, this study has successfully established a new methodological clustering approach to analyze electrophysiological data recoded from 3D organoid models in the context of Parkinsons disease modelling and organoid model development research.

Background: Artificial intelligence (AI), including generative and foundation-based methods, has rapidly expanded within medical imaging research. However, the structure, citation impact, collaboration patterns, and thematic orientation of national research ecosystems remain incompletely characterised. Objectives: To evaluate global research trends in AI applied to medical imaging between 2017 and 2025, with detailed analysis of United Kingdom (UK)-affiliated output, citation performance, collaboration structure, funding landscape, and thematic evolution, with emphasis on generative and foundation-based methodologies. Materials and Methods: A bibliometric analysis of Scopus-indexed publications (2017-2025) was performed using a predefined search strategy targeting AI and medical imaging concepts, with emphasis on generative and foundation-based terms. Records were analysed globally and filtered for UK affiliation. Descriptive indicators including total publications (TP), total citations (TC), citations per paper (CPP), and year-on-year growth were calculated. Co-authorship and keyword co-occurrence networks were generated using VOSviewer (v1.6.19). Results: A total of 13,452 publications were identified globally (194,650 citations; global CPP 14.47), of which 889 (6.61%) were UK-affiliated. The UK ranked fourth by publication volume yet demonstrated higher citation efficiency (CPP 21.00) than several higher-volume countries. UK output increased approximately 18-fold between 2017 and 2025, with evidence of a citation-lag effect in recent years. Research activity was concentrated within a small number of institutions accounting for nearly half of national output, although citation impact varied independently of volume. Journal-dominant dissemination was associated with higher average citation impact compared with conference-centric models. Keyword analysis identified three principal thematic clusters: generative/deep learning methodologies, MRI- and diffusion-focused applications, and broader diagnostic imaging workflows. Highly cited publications were initially dominated by generative adversarial network-based reconstruction and synthesis, with recent rapid citation growth observed in diffusion and foundation-model architectures. Conclusion: UK-affiliated research represents a rapidly expanding and highly cited component of the global AI medical imaging literature, with increasing emphasis on generative, diffusion-based, and foundation-model approaches. These findings provide a reproducible bibliometric baseline for monitoring research activity, collaboration patterns, and potential translational priorities, while recognising that citation-based indicators do not directly measure clinical implementation, methodological quality, or real-world impact.

Respiratory rate is a clinically and behaviourally informative signal, yet continuous monitoring outside quiet rest remains difficult. Wearable systems often infer breathing indirectly from cardiovascular or motion surrogates, while direct chest-wall sensing has typically depended on skin adhesion or controlled laboratory conditions. We evaluated Alveos One, a body-coupled acoustic and inertial chest-wall wearable, to test whether a reusable magnet-through-textile form factor can estimate respiratory rate across rest, controlled breathing, motion tasks, and graded exercise. In a single-session protocol, we analysed recordings from 20 healthy adults referenced to structured light plethysmography, breath-by-breath spirometry, and paced-breathing targets. Estimates fell within 2 breaths/min of the reference for 94.6% of valid windows during rest and controlled breathing and 79.3% during exercise; Bland-Altman bias was - 0.24 breaths/min during rest and controlled breathing and -1.07 breaths/min during exercise. Secondary analyses compared the magnet configuration with a skin-adhered patch and assessed airway-mode classification and motion-related operating limits. These findings support reusable, non-adhesive chest-wall acoustic sensing as a practical route to longitudinal respiratory-rate monitoring, and identify rising motion intensity and high ventilatory demand as the principal limits on confident reporting.

Surface electromyography (sEMG) is the most practical non-invasive interface for myoelectric prostheses, exoskeletons, and rehabilitation systems, but power-line interference (PLI) contamination and excessive digital pipeline group delay still limit its clinical adoption. This paper proposes a co-designed analog-digital correction system combining a high-CMRR front-end with an exponentially-windowed RMS (EMRMS) envelope estimator and a recursive single-tone PLI canceller. We present a closed-form CMRR model capturing the electrode-skin imbalance, and provide a complete stability analysis of the LMS canceller. The EMRMS estimator reduces the computational overhead from[O] (L) to strictly[O] (1) in both time and space complexities. Featuring no data-dependent branching, the algorithm achieves deterministic algorithmic execution time (zero jitter under an RTOS environment) and is natively compatible with fixed-point arithmetic on microcontrollers lacking a hardware Floating-Point Unit (FPU). A reference implementation reaches an 8.2 {micro}s median per-sample latency, yielding an end-to-end delay of[~] 30 ms -- leaving a generous >90 ms budget for electromechanical actuation -- while requiring an active CPU duty cycle of merely 1.6%, enabling prolonged deep-sleep intervals. Validation on the public Ninapro DB2 dataset demonstrates a 13.9 dB mean SNR improvement (averaged across 12 channels; single-channel comparison: 9.7 dB, Table 3) and a 70.0 {micro}V envelope RMSE against a length-200 rectangular reference. Paired Wilcoxon signed-rank tests confirm statistical significance (p < 0.001) over static baselines, and Pearson correlation analysis ({rho} = 0.993 {+/-} 0.0002) confirms strict morphological fidelity. The full open-source codebase and benchmarks are publicly released. O_TBL View this table: org.highwire.dtl.DTLVardef@299dc5org.highwire.dtl.DTLVardef@3519a0org.highwire.dtl.DTLVardef@2586aborg.highwire.dtl.DTLVardef@1ac5610org.highwire.dtl.DTLVardef@1465c46_HPS_FORMAT_FIGEXP M_TBL O_FLOATNOTable 3:C_FLOATNO O_TABLECAPTIONQuantitative comparison on a common 60 s segment of Ninapro-like synthetic sEMG (single channel) with a 3 mV 50.3 Hz mains tone slightly drifted from the static notchs design centre at 50.0 Hz, stress-testing the adaptive corrector under a frequency mismatch. The Ninapro multi-channel aggregate (13.9 dB) reported in Section 3.4 uses mains exactly at 50 Hz (matched notch) and so achieves a higher {Delta} SNR. "MAC/sample" excludes the EMRMS square root and the pre-computed LMS sine/cosine. C_TABLECAPTION C_TBL