During percutaneous coronary intervention (PCI), the contact force between the guidewire and the vessel wall is a key mechanical factor in vessel injury, yet it cannot be measured directly with conventional imaging. Although sensor-based methods measure the contact force directly, they increase both the complexity and the cost of the instrumentation. A sensorless guidewire contact force estimation method is therefore proposed, in which multi-scale feature extraction is combined with region mask mean pooling to learn an end-to-end mapping from conventional planar images to the contact force in each of the four predefined contact regions. The proposed method is evaluated on a dataset of 343 samples acquired on a 3D-printed vessel phantom, achieving a mean absolute error (MAE) of 0.861 g and a root mean square error (RMSE) of 1.036 g. Ablation experiments show that the region mask reduces the MAE by 79
Pattern electroretinography (PERG) is a non-invasive test of macular and retinal ganglion cell function, but its low amplitude and inter-subject variability limit its diagnostic use. This study compares three representations of the transient PERG waveform for the detection of six retinal and optic nerve conditions — Birdshot chorioretinopathy, cone-rod dystrophy, hereditary optic atrophy, macular dystrophy, retinitis pigmentosa and Stargardt disease — against healthy controls, using the publicly available PERG-IOBA dataset. A total of 672 recordings from 336 examinations of 304 participants were preprocessed in six stages, and three representations were evaluated under one identical protocol: the raw 255-point amplitude-preserving waveform; 60 engineered clinical, spectral, wavelet and complexity descriptors; and a hybrid representation of 343 variables combining both, with multi-wavelet features from db4, sym2 and coif3. Performance was estimated by 10 × 5-fold participant-grouped cross-validation, in which both eyes and all repeat visits of an individual were kept in the same partition, with nested hyperparameter selection and all data-derived preprocessing fitted inside each training fold. Under the pre-specified primary classifier, the raw waveform gave the highest pooled out-of-fold AUC in four of the six classes (0.906 in cone-rod dystrophy, 0.842 in retinitis pigmentosa, 0.755 in macular dystrophy, 0.673 in hereditary optic atrophy) and the engineered descriptors in the remaining two (0.803 in Stargardt disease, 0.657 in Birdshot chorioretinopathy). The hybrid representation was highest in none, falling below the raw waveform in five of six classes by 0.002 to 0.018, and no non-linear classifier showed a hybrid advantage above 0.006 in mean AUC. A sensitivity analysis identified what does matter: removing the absolute amplitude scale by per-signal z-scoring cost the raw representation 0.055 AUC on average but the engineered descriptors only 0.023, and reversed the ordering of the three representations. Engineered descriptors did not improve on the waveform, but they made the problem tractable for linear models, which gained 0.128 in mean AUC from the reduction in dimensionality. These internally validated findings indicate that absolute PERG amplitude should be preserved rather than normalised away; participant-independent, multi-centre validation is required before clinical application.
Electroencephalography (EEG) is a key method for detecting virtual reality motion sickness (VRMS), but multi-lead recordings and high-dimensional features increase processing complexity, device cost, and user burden. This study proposes a SHapley Additive exPlanations (SHAP)-based single-lead modeling and feature-screening framework to reduce the number of EEG leads and feature dimensions for lightweight VRMS detection. Six classical deep-learning EEG decoding models were used to assess the contribution of each lead via SHAP values and identify the optimal single lead. Handcrafted features were then extracted and selected using a correlation–SHAP strategy, and XGBoost was adopted for final classification. FT11 showed competitive and relatively consistent performance across the evaluated models and was selected as the target lead after integrating SHAP-based lead importance, single-lead classification performance, frequency-band differences, and physiological relevance. Under the window-level tenfold cross-validation protocol used in this study, the proposed model achieved an accuracy of 87.53
This research presents a compact multi-band spiral antenna designed for frequency-dependent hyperthermia therapy in head and neck cancers. The antenna is designed on a low-cost FR4 substrate with overall dimensions of 70 × 70 × 1.6 mm3 and is optimized to cover the 915 MHz, 1.8 GHz, and 2.45 GHz frequency bands. Its geometry enables stable tri-band resonance with excellent impedance matching, ensuring efficient energy transfer into biological tissues. The antenna’s performance is evaluated through S-parameter analysis, specific absorption rate (SAR) distribution, penetration depth (PD), and effective field size (EFS) using homogeneous and heterogeneous phantoms, as well as the Katja voxel model with and without a tumor. The thermal simulations confirm that therapeutic temperatures of 41–45 °C are achieved with low input powers between 2.5–6 W. At 2.45 GHz, the antenna provides localized heating for superficial tumors (≤ 3 cm), at 1.8 GHz it is effective for intermediate tumor depths (3–3.6 cm), and at 915 MHz it achieves deeper penetration for tumors located beyond 3.6 cm. Experimental validation using head-simulating liquid and ex vivo chicken tissue demonstrates good agreement with simulation results, confirming reliable and efficient heating. The proposed applicator offers a practical and versatile solution, enabling personalized hyperthermia therapy across a wide range of tumor depths in head and neck cancer treatment.
Automated four-grade Mayo Endoscopic Score (MES) classification is challenging because inflammatory severity depends not only on subtle local mucosal changes, but also on the collective spatial pattern of abnormalities that may be separated across the visible field. We present UC-DiffuMambaNet, a hybrid architecture that integrates dual-scale severity-evidence propagation, two-dimensional contextual coordination, and hierarchical ordinal prediction. The Severity Mamba Mixer first strengthens informative mucosal features through locally gated multi-scale enhancement and then processes them with parallel short- and long-retention selective state-space branches. This design preserves local feature continuity while linking separated severity cues over complementary contextual ranges. Medical Window Attention subsequently coordinates fine intra-window structure with communication across windows, complementing state propagation with explicit two-dimensional spatial context. Finally, an Auxiliary Hierarchical Classification Head refines ordered MES assessment through feedback-guided hierarchical prediction. Across three independent seeds, UC-DiffuMambaNet achieved ACC/QWK/Macro-F1 of 91.26
