Background: Programming Deep Brain Stimulation (DBS) for pediatric dystonia remains largely empirical, as no validated electrophysiological biomarker currently guides parameter selection, and most studies treat each signal modality separately rather than exploiting their joint structure. Methods: In a single pediatric patient with generalized dystonia and bilateral globus pallidus internus (GPi) DBS implantation, we synchronized electroencephalography (EEG), local field potential (LFP), and electromyography (EMG) recordings across seven sessions spanning stimulator-OFF and multiple stimulation intensities. Dystonic muscle activity labels were derived from a validated quantitative EMG pipeline. Regularized logistic regression classifiers, trained on EEG-only, LFP-only, and combined EEG-LFP feature sets, were evaluated under four validation schemes: within-OFF cross-validation, OFF-to-ON generalization, a mixed leave-one-recording-out (LORO) scheme, and generalization to unseen stimulation intensities. Results: The Combined model performed best in the mixed LORO scenario (balanced accuracy 0.74, sensitivity 0.78, specificity 0.70), inheriting a favorable trade-off from the complementary biases of EEG (sensitivity-dominated) and LFP (specificity-dominated). LFP-derived Hjorth mobility, the beta/gamma power ratio, EEG central alpha power, and central-temporal gamma coherence ranked among the most consistent candidate predictive features across scenarios. Generalization to unseen stimulation intensities preserved a similar, moderately degraded performance profile (balanced accuracy 0.66–0.70). Conclusions: These findings provide proof-of-concept evidence that multimodal EEG-LFP decoding can identify epochs of dystonic muscle activity in paediatric dystonia.
Deep learning supports many tasks in medical imaging, but most systems assume a fixed data source and a single training event. In clinical practice, new scanners arrive, protocols change, patient populations shift, and new diagnostic questions appear. A frozen model loses accuracy as the data shift, while a model retrained only on new data forgets what it knew (catastrophic forgetting). Continual learning updates a model on new data while keeping prior knowledge. Following PRISMA 2020, we searched five sources with database-specific search strings and included 77 primary studies. We formally define the task-, domain-, and class-incremental scenarios in one notation and organize methods into five families: regularization, replay, dynamic architectures, foundation-model adaptation, and hybrids. We appraise the design and reporting of every included study on ten items, and the main findings hold when preprints are excluded. Only 7 of the 77 studies test on an external source, and none reports a clinical evaluation. Evaluations differ too much to rank the families across studies; so, we match families to clinical constraints by mechanism and draw a practical decision guide from head-to-head results on public data. We relate the methods to the regulation of model updates and give specific recommendations.
Neuropsychiatric disorders including attention-deficit/hyperactivity disorder (ADHD), bipolar disorder (BD), and schizophrenia (SZ) exhibit significant clinical heterogeneity and overlapping symptom profiles, which severely limits the diagnostic specificity of conventional symptom-based assessments. While structural magnetic resonance imaging (sMRI) provides objective insights into anatomical brain alterations, existing computational frameworks often rely on single-plane or binary patient-control analyses, lack anatomical interpretability, or risk data leakage through inconsistent validation protocols. To address these challenges, this study proposes a segmentation-guided AI framework for medical image processing and recognition that fuses FastSurfer-derived regional handcrafted features encompassing Fourier shape descriptors, two-dimensional wavelet and second-order local directional gradient pattern (LDGP) textures, and ROI-filtered XFeat keypoints with complementary multi-view (axial, sagittal, coronal) EfficientNetB0 deep representations extracted from whole-brain T1-weighted sMRI. The segmentation stage provides anatomically defined regions for radiomic feature extraction, while explainable representations maintain anatomical traceability. A key contribution of this work is its dual evaluation strategy within a unified structural feature space: it addresses both broad transdiagnostic four-class classification (Healthy Control (HC) vs. ADHD vs. BD vs. SZ) and focused binary patient-control contrasts (SZ vs. HC and BD vs. HC). To ensure rigorous evaluation, feature fusion, feature standardisation, Salp Swarm Optimizer (SSO) feature selection, hyperparameter selection, and early stopping are performed exclusively within the training partitions of a participant-level nested cross-validation (five outer and three inner folds), and held-out participants are used only once for evaluation. Evaluated on the UCLA Consortium for Neuropsychiatric Phenomics (CNP) dataset, the framework achieved 79.3% accuracy in four-class transdiagnostic classification. In focused binary tasks, the framework reached 84.3% accuracy for SZ versus HC and 82.7% accuracy for BD versus HC. These results indicate that combining segmentation-guided radiomic descriptors with multi-view deep representations provides a promising research framework for structural MRI analysis of neuropsychiatric disorders, while external validation is required before clinical application.
Organ-on-chip (OoC) technology has emerged as a powerful class of microphysiological systems capable of recapitulating human tissue architecture, biochemical gradients, and dynamic cellular interactions with high fidelity. While OoC platforms have advanced rapidly in organs such as liver, heart, and lung, their application to the musculoskeletal system remains comparatively underdeveloped despite the central role of biomechanics in tissue function and disease. Musculoskeletal tissues, including skeletal muscle, bone, cartilage, and tendon, present unique challenges due to their hierarchical structure, anisotropic mechanical properties, and tightly coupled immune, vascular, and stromal interactions that govern repair and degeneration. In this review, we critically evaluate recent advances in musculoskeletal OoC platforms, including muscle, bone, cartilage, and tendon-on-chip systems, with emphasis on structural design, biomaterial composition, and integration of mechanical cues. We highlight how these systems enable precise control of microenvironmental conditions and support human-relevant disease modeling and drug testing. However, we identify key limitations that constrain their translational potential, including inadequate representation of physiologically relevant mechanical loading, incomplete vascular and immune integration, lack of standardization, and limited modeling of inter-tissue interfaces. Importantly, we propose a unifying framework for next-generation musculoskeletal OoC systems centered on three principles: mechanobiological fidelity, multicellular integration, and interface-level modeling of the muscle–tendon–bone axis. We further discuss emerging strategies, including advanced biomaterials, 3D bioprinting, multi-tissue integration, and artificial-intelligence-driven analysis that can address current limitations and enable scalable, predictive platforms. By bridging reductionist in vitro systems and complex in vivo physiology, musculoskeletal OoC technologies have the potential to transform mechanobiology research, accelerate drug discovery, and enable precision regenerative therapies. Realizing this potential will require coordinated advances in engineering, biology, and standardization to establish OoC platforms as robust, clinically relevant tools for musculoskeletal medicine.
Osteonecrosis of the femoral head (ONFH) is a progressive disorder characterized by impaired vascular supply, dysregulated bone remodeling, and loss of structural integrity that may ultimately lead to femoral-head collapse and total hip arthroplasty. This narrative review aimed to critically examine advanced bioactive and regenerative scaffold strategies for early-stage ONFH, with emphasis on biomaterial design, osteogenesis–angiogenesis coupling, microenvironment modulation, clinical translation, and functional recovery. A structured literature search of PubMed/MEDLINE, Scopus, and Web of Science was conducted from database inception to 14 August 2026, and relevant preclinical and clinical studies were synthesized qualitatively. Preclinical evidence demonstrates progressive development from osteoconductive matrices toward functionally graded, cell-assisted, bioactive-ion, oxygen-releasing, antioxidant, and immunomodulatory platforms, supporting biological plausibility and technological feasibility. In contrast, clinical evidence remains limited, heterogeneous, and predominantly observational or open-label. No randomized controlled trial specifically evaluating an advanced regenerative scaffold platform was identified among the studies included in this review. Advanced regenerative scaffolds therefore represent promising joint-preserving strategies, but their clinical value remains to be established through reproducible scaffold characterization, appropriate patient and lesion selection, standardized outcomes, long-term native-hip survival assessment, and well-designed comparative studies.
