Search Results (492)

Background/Objectives: The “small-n-large-p” dilemma in mammography artificial intelligence (AI)—where the number of candidate imaging features far exceeds the number of labeled cases—commonly results in model overfitting, unstable feature selection, and poor generalization across clinical settings. This study aims to reassess the internal performance of the HiTopology-GOA-CSA (Grasshopper Optimization Algorithm–Crow Search Algorithm) feature-selection framework for mammography using a larger real Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) cohort and a stricter leakage-aware evaluation strategy. Methods: In this retrospective computational study using public anonymized datasets, an expanded internal cohort of 98 CBIS-DDSM mass cases (49 benign, 49 malignant) was assembled from digital imaging and communications in medicine (DICOM) region of interest (ROI) series. A total of 1074 features were extracted per case, including 88 handcrafted radiomic descriptors and 986 EfficientNet-B5 deep features. HiTopology-GOA-CSA selected 102 features, corresponding to 91% feature reduction. Two internal evaluation modes were compared: Mode A, which matched the original pilot methodology by performing feature selection once on the full cohort before cross-validation, and Mode B, which used strict nested feature selection within training folds. Performance was assessed with 5-fold stratified cross-validation using a multilayer perceptron (MLP) classifier. Results: On the expanded cohort, Mode A achieved an area under the receiver operating characteristic curve (AUC) of 0.726 (95% CI: 0.594–0.858), sensitivity of 0.658, specificity of 0.651, and F1-score of 0.644. Under the stricter nested evaluation, Mode B achieved AUC of 0.683 (95% CI: 0.549–0.817), sensitivity of 0.598, specificity of 0.631, and F1-score of 0.595. Mean pairwise Jaccard similarity across nested folds was 0.604, indicating moderate feature stability. Benchmark comparisons showed that the proposed method was competitive but did not outperform standard baselines; LASSO logistic regression achieved the highest AUC of 0.739, while the proposed HiTopology-GOA-CSA + MLP achieved an AUC of 0.683. Real external validation on the locked VinDr-Mammo subset (n = 25) remained near-random (AUC of 0.500 [95% CI: 0.304–0.696]), with complete prediction collapse (sensitivity of 1.000, specificity of 0.000). Conclusions: The framework demonstrated feasibility for structured feature selection and stress testing in a small-cohort mammography AI setting; however, external validation revealed near-random discrimination and prediction collapse, indicating limited generalizability. These findings emphasize the need for benchmark comparisons, transparent uncertainty reporting, patient-level validation, and larger multicenter datasets before clinical translation. Full article

Background/Objectives: Primary thyroid lymphoma (PTL), including diffuse large B-cell lymphoma (DLBCL) and mucosa-associated lymphoid tissue (MALT) lymphoma, share substantial overlap in ultrasound appearance with Hashimoto’s thyroiditis (HT), making preoperative differentiation challenging. This study aims to develop and validate a deep learning model based on B-mode ultrasound (BMUS) and color Doppler ultrasound (CDUS) for image-level differentiation of DLBCL, MALT lymphoma, and HT. Methods: This retrospective single-center study included 1294 ultrasound images from 290 patients (313 lesions) who underwent preoperative ultrasound examination at West China Hospital between September 2002 and September 2024. All images from the same lesion were assigned to the same data partition, and the dataset was split at the lesion level into training and test sets at an 8:2 ratio. A Frequency-Adaptive WT-ResNet model incorporating wavelet transform convolution and a frequency-adaptive gating mechanism was developed. The primary analysis was performed at the image level. The performance of the model was compared with that of three ultrasound physicians with different levels of experience. Grad-CAM was used for visual interpretation. An exploratory external validation was performed using an independent dataset from Sun Yat-sen Memorial Hospital. Results: In the test set, the model achieved a macro-average AUC of 0.927 (95% CI: 0.889–0.960), with class-specific AUCs of 0.899 for DLBCL, 0.946 for MALT lymphoma, and 0.937 for HT. The macro-average balanced accuracy was 0.866, compared with 0.827 for that of the best-performing senior physician. The exploratory validation set yielded a macro-average AUC of 0.796 (95% CI: 0.686–0.888), with class-specific AUCs of 0.806 for DLBCL, 0.825 for HT, and 0.756 for MALT lymphoma. Grad-CAM showed that the model focused on lesion-internal echotexture and lesion-transition regions with class-dependent patterns. Conclusions: A deep learning model based on BMUS and CDUS showed promising performance for image-level differentiation of DLBCL, MALT lymphoma and HT in a single-center retrospective cohort. The model outperformed three ultrasound physicians and may serve as a potential decision-support tool. However, the exploratory external validation results should be interpreted as preliminary, and larger multicenter cohorts remain necessary to confirm model generalizability. Full article

Magnetic anomaly detection is vulnerable to environmental noise and insufficient prior target information, making non-periodic anomaly signals difficult to detect at low-signal-to-noise-ratio (SNR) conditions. This paper proposes a detection method based on a multi-parameter-constrained mirror dual-branch biased monostable stochastic resonance (SR) system. Nonlinear odd-order bias terms are introduced into the conventional biased monostable potential function to build a multi-parameter-controllable SR model. This improves regulation of potential-well width, depth, and wall morphology, enhancing noise-energy utilization and responses to non-periodic features. Considering peak-type, valley-type, and bipolar anomaly morphologies, a mirror dual-branch SR structure is developed to cooperatively detect features with different polarities. To preserve temporal waveforms and time–frequency structures during parameter optimization, a composite metric combining the correlation coefficient and wavelet-domain image structural similarity index is constructed. Multi-fidelity robust Bayesian optimization is used to obtain a unified robust parameter set for the magnetic anomaly signal family. Experiments with simulated colored noise and measured geomagnetic noise show that the proposed method effectively recovers magnetic anomaly features under strong noise. At −19 dB SNR, its detection probability remains above 80%. Compared with orthogonal basis function decomposition, empirical mode decomposition, and complete ensemble empirical mode decomposition with adaptive noise, the method achieves better noise suppression, feature preservation, and detection performance under low-SNR conditions. Full article

This study investigates the coupling between flow dynamics, acoustic response, and convective heat transfer in a rectangular impinging jet striking on a heated slotted plate at two closely spaced Reynolds numbers (Re = 3550 and Re = 3750). Velocity fields were obtained using Particle Image Velocimetry (PIV), and coherent structures were analyzed using Proper Orthogonal Decomposition (POD) while acoustic measurements were used to characterize the tonal behavior. Infrared thermography was employed to determine local and mean Stanton numbers. The mean Stanton number increased by 6.6% when the Reynolds number increased from Re = 3550 to Re = 3750, while the sound pressure level decreased from 78 dB to 71 dB. At Re = 3550, the acoustic spectrum exhibited multi-tone behavior associated with distributed modal energy. In contrast, at Re = 3750, a single dominant frequency governed the flow dynamics. The energy of the first POD mode nearly doubled when passing from Re = 3550 to Re = 3750. The cross-correlation coefficients between the first POD mode and the acoustic field increase from 0.76 to 0.93 when changing from Re = 3550 to Re = 3750. These findings show that the dominant vortex mode which contains nearly 20% of the fluctuating energy (for Re = 3750), significant influences the energy transfer from the dynamic field to the acoustic field resulting in a strong noise reduction. Simultaneously, convective heat transfer increases, highlighting the key role of coherent flow organization on both acoustic and thermal behavior of the system. Full article

Private cloud object stores provide infrastructure isolation but leave application-layer data exposed to insider threats and compromised credentials. This paper presents an engineering integration of an Add-Rotate-XOR (ARX) block cipher and multi-bit Least Significant Bit (LSB) steganography into an end-to-end pipeline for private MinIO object storage. The cipher, KREA v2, is a SPECK-64/128 derived ARX construction with three application-driven choices: CRC32 key whitening, byte-aligned rotations ($\alpha =7$, $\beta =2$), and deterministic CTR-mode nonces. Mixed Integer Linear Programming (MILP) trail analysis matches SPECK-64/128’s minimum-trail weights through rounds 1–4. KREA v2 ciphertext meets standard keystream-quality preconditions (NIST SP 800-22 battery, 49.98% mean avalanche, Shannon entropy 7.9992–7.9998 bits/byte across realistic XML, JSON, video, and HTTP/2 payloads). Modified LSB (MLSB) embeds 3 bits per RGB channel with an XOR watermark at 37–38 dB Peak Signal-to-Noise Ratio (PSNR), providing $3\times$ standard-LSB capacity. Steganalysis uses chi-square and RS detectors plus a Convolutional Neural Network (CNN) detector (Yedroudj-Net) trained on 8000 BOSSBase-1.01 cover/stego pairs; CNN area under the ROC curve is ≥0.999 against the watermarked variant. The MinIO pipeline runs at 355.1 ms (68.6% network I/O) with 100% message fidelity. The XOR watermark increases RS detectability above 75% capacity; a 200-image ablation cuts median RS detection (0.289 to 0.000) and mean (0.342 to 0.130) in a sparse-keystream variant, prioritised for follow-on full-scale evaluation. The architecture is offered as a documented engineering integration with explicit security caveats and threat-model boundaries, not as a production-hardened cryptographic primitive. Full article

Vision Transformers (ViTs) have achieved remarkable success; however, their internal decision-making mechanisms remain largely opaque. The Dynamic Accumulated Attention Map (DAAM) has emerged as a prominent interpretability tool that visualizes model focus by aggregating attention weights across successive blocks. Nevertheless, the fidelity of these maps, specifically the extent to which they accurately reflect the underlying pixels that drive the final classification, is often taken for granted. In this study, we evaluate the fidelity of DAAM using both supervised Data-efficient Image Transformers (DeiT) and self-supervised Self-distillation with no labels (DINO) models under strategic spatial perturbations. Our analysis reveals a critical failure mode in DINO under severe background noise at a Signal-to-Noise Ratio ($\mathrm{SNR}=-20$ dB): while the DAAM visualization paradoxically maintains a sharp and “accurate” focus on the target object, the model’s actual output suffers from total class flipping, shifting from the correct label to an entirely unrelated category. Statistical results on 1000 ImageNet samples confirm this decoupling of visualization and decision influence; DINO’s robustness accuracy plummets to 2.70%, yet its attention maps remain anchored to the salient object. These findings demonstrate that the accumulated saliency provided by DAAM can be a misleading indicator of model logic, as it may highlight regions that the model “observes” but no longer correctly “interprets.” We conclude that interpretability frameworks must transcend spatial heatmaps and incorporate causal fidelity metrics to avoid the pitfalls of deceptive visualization. Full article

This paper presents a column-parallel adaptive-gain single-slope (SS) analog-to-digital converter (ADC) for high-speed high-dynamic-range (HDR) CMOS image sensors. Conventional adaptive-gain approaches often rely on dual-ramp generation or duplicated column circuits, which increase area and power overhead. In contrast, the proposed architecture achieves adaptive-gain operation using a single global ramp shared across all columns. A reconfigurable capacitive attenuation network embedded inside each column comparator locally scales the ramp at the comparator input, enabling seamless transition between high-gain operation for low-level signals and unity-gain operation for large signals within a single exposure and readout cycle. To suppress mode-dependent offsets while maintaining low noise, a configurable dual-source-follower ramp buffer symmetrically buffers the ramp and reference voltages during auto-zeroing and is reconfigured as a full-sized buffer during unity-gain conversion. Switching-induced column offsets are compensated using optical black pixels and lightweight digital processing. The ADC is implemented in a 110 nm CMOS image sensor process and validated through post-layout simulations including extracted parasitics and Monte Carlo mismatch analysis. The core ADC consumes 36.8 µW per column. Simulation results demonstrate linearity error below 1% without missing codes and show that the proposed AG_x8-to-AG_x1 configuration extends the effective dynamic range up to 78.3 dB. Full article

Background: Human cadaveric models provide a controlled experimental setting to investigate the anatomical basis and mechanical behaviour underlying musculoskeletal ultrasound findings. In recent years, both B-mode ultrasound and shear wave elastography have been applied in cadaveric studies to explore muscle architecture, aponeurotic structures, and passive mechanical properties under standardized conditions. Objective: The aim of this scoping review was to map and synthesize cadaveric studies using ultrasound and shear wave elastography to investigate lower-limb muscles and their aponeurotic structures, with emphasis on methodological applications, anatomical insights, and limitations relevant to clinical interpretation. Material and Methods: A scoping review was conducted according to PRISMA-ScR principles. Studies were included if ultrasound imaging (B-mode and/or shear wave elastography) was applied directly to human cadaveric lower-limb muscles or aponeurotic structures. Data were extracted and synthesized descriptively by anatomical region and ultrasound technique. Results: A total of 11 studies met the inclusion criteria and were included in the final qualitative synthesis, all of which applied ultrasound imaging, with or without shear wave elastography, directly to human cadaveric muscle tissue Among these, seven studies specifically investigated lower-limb skeletal muscles and their aponeurotic structures using ultrasound-based techniques to describe muscle architecture, internal connective tissue anatomy, or passive mechanical behaviour. These studies focused on the quadriceps femoris, hamstrings, adductor longus, and the gastrocnemius–soleus complex. The remaining four studies were considered relevant and therefore included in the scoping review because, although they did not focus on a specific lower-limb muscle group, they addressed key methodological factors influencing ultrasound and elastography-derived measurements in cadaveric muscle tissue. These investigations examined the effects of tissue layering, specimen-related characteristics, and measurement conditions, thereby providing essential methodological context for the interpretation of ultrasound-based outcomes across different anatomical regions. Conclusions: Cadaveric ultrasound studies provide essential anatomical context for interpreting musculoskeletal ultrasound, while cadaveric shear wave elastography supports controlled exploration of passive muscle mechanics. At the same time, these studies highlight important methodological sensitivities that should be acknowledged before translating elastography findings to clinical decision-making. Full article

Early pregnancy diagnosis is a key component of reproductive management in swine production systems. Accurate identification of pregnant and non-pregnant sows within the first 30 days after insemination allows timely reproductive decisions and reduces non-productive days. The present systematic review evaluates the diagnostic efficiency of ultrasonographic and progesterone-based methods used for early detection of pregnancy in sows. A structured literature search was conducted in accordance with the PRISMA Statement guidelines, using major scientific databases. Studies evaluating pregnancy diagnosis in sows within the first 30 days after insemination were included. Diagnostic approaches were analyzed with respect to methodological design, timing of examination, biological sample matrix, and reported indicators of diagnostic accuracy. Ultrasonographic techniques have evolved from early acoustic detection in A-mode to real-time imaging in B-mode and more recently algorithm-assisted interpretation of ultrasound images. Real-time ultrasonography allows direct visualization of gestational structures; in one study, diagnostic accuracy above 95% was reported after approximately 23–24 days of pregnancy under optimal examination conditions. Progesterone-based analyses evaluate luteal endocrine activity and are particularly useful for early identification of non-pregnant animals after luteolysis. The diagnostic efficiency of hormonal assays depends strongly on the timing of sampling and the biological matrix used for analysis, including plasma, serum, dried blood spots, saliva, or feces. The comparative analysis shows that ultrasonography provides morphological confirmation of pregnancy, whereas progesterone analyses serve mainly as functional indicators of luteal activity. These methods play complementary roles in reproductive management. Ultrasonography remains the most reliable method for confirming pregnancy, while progesterone-based analyses are valuable tools for early reproductive screening and identification of non-pregnant sows. Full article

In this work, we propose ARTEMIS, a novel and highly interpretable deep learning pipeline for the automatic classification of Chest X-ray (CXR) and Computed Tomography (CT) images into different categories related to important clinical outcomes: COVID-19 infection, Community-Acquired Pneumonia (CAP) cases, and Normal cases. Unlike existing models based on the static feature enhancement step, ARTEMIS proposes a learnable preprocessing component that dynamically adapts the image contrast and sharpness in training mode, facilitating adaptive optimization. Our hybrid network combines EfficientNet-B0 backbone with built-in SE attention with the optional lightweight Transformer encoder block to jointly learn local radiological features and global relationships between pixels. Comprehensive experiments have been conducted on five different datasets, which comprise four publicly available ones and one novel CT dataset annotated by radiologists, including X-ray and CT modalities. Experimental results show strong robustness and generalization with macro F1-scores greater than 96% on public datasets and 99.39% accuracy on our new CT dataset. To interpret the decision-making process, Grad-CAM++ is employed to generate class-discriminative saliency maps; the highlighted regions are systematically validated against established radiological criteria by a board-certified radiologist, confirming that model decisions are grounded in clinically meaningful pulmonary findings rather than imaging artifacts. Full article

The hydrogen embrittlement (HE) behavior of an Fe–18Mn–8Al–1C–5Ni lightweight steel containing a fine and uniformly distributed B2 phase and κ-carbide was investigated by slow strain rate tensile testing with in situ hydrogen charging. Hydrogen charging reduces the elongation from 28.2% to 11.2%, while preserving an ultimate tensile strength above 1100 MPa and yielding an HE index of 60.2%. A thermal desorption analysis reveals a multi-peak desorption curve corresponding to diffusible hydrogen, hydrogen reversibly trapped at κ-carbides, and hydrogen strongly bound at the B2/γ interfaces, revealing a hierarchical hydrogen trapping behavior. Electron backscatter diffraction and electron channeling contrast imaging analyses near the fracture head region further reveal that localized hydrogen enrichment at the B2/γ boundaries induces severe stress concentration and interfacial weakening, shifting the fracture mode from ductile micro-void coalescence in air to hydrogen assisted intergranular and interphase cracking. This study clarifies the distinct roles of coherent κ-carbide and B2/γ interfaces in hydrogen trapping and crack initiation, offering a microstructure-based perspective for designing high-strength, HE resistant lightweight steels. Full article

This study presents a multi-analytical investigation of two Baroque gilded terracotta sculptures—Hercules and the Nemean Lion (Hercules A) and Hercules and the Lernaean Hydra (Hercules B)—attributed to Lorenzo Vaccaro (1655–1706) and preserved at the Museo Civico Gaetano Filangieri in Naples. This research aimed to reconstruct the original manufacturing technique, characterize materials introduced by successive restoration interventions, and identify active degradation mechanisms. A systematic diagnostic approach integrating UV fluorescence imaging, digital optical microscopy, portable energy-dispersive X-ray fluorescence spectroscopy (EDXRF), Raman spectroscopy, Fourier-transform infrared spectroscopy in attenuated total reflectance mode (FTIR-ATR), scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDS), and spectrocolorimetry was applied. The original gilding system—comprising a ferruginous silico-aluminous terracotta substrate, a calcium sulfate ground, a lead-white imprimitura, an iron-rich bole, and a thin gold leaf—is consistent with documented Baroque mission gilding practices in Southern Italy. Analytical evidence further documented extensive non-original interventions, including copper-based artificial patination, bronze powder (porporina) integration, poly (vinyl acetate) adhesives, and acrylic protective coatings. Raman spectroscopy identified the in situ conversion of intentionally applied tenorite (CuO) to malachite (Cu₂CO₃(OH)₂) as an active degradation pathway. Spectrocolorimetric measurements quantified chromatic alterations of up to ΔE = 52 attributable to accumulated surface deposits. The proposed integrated methodology constitutes a replicable diagnostic framework for investigating gilded terracotta artefacts in museum collections. Full article

Orthopaedic disorders represent a significant clinical challenge in avian medicine, affecting both pet and wild birds. B-mode ultrasound (US) examination is well established in small-animal and equine medicine; it has seen limited application in avian medicine thus far. This study aimed to assess the diagnostic efficacy of B-mode US in comparison to radiography (RX) for orthopaedic avian disorders. A total of 55 birds from six orders were assessed clinically, radiologically, and sonographically. Statistical analysis was conducted for the overall cohort (n = 55) and for a fracture subgroup (n = 51). Cohen’s kappa was used to examine diagnostic agreement. Sensitivity, specificity, and positive and negative predictive values were also computed. Additionally, Fisher’s exact test was employed to evaluate the representativeness and interpretability of both techniques. In the overall cohort, US demonstrated higher sensitivity (97.6%) and specificity (100%) than RX (sensitivity 70.7%, specificity 85.7%). In the fracture subgroup, US demonstrated superior sensitivity (97.3%) compared with RX (75.7%) while maintaining high specificity (100%). The agreement between imaging findings and the clinical reference standard was substantial to good (κ = 0.64 for the total cohort, p < 0.05; κ = 0.74 for the fracture subgroup, p < 0.05). No significant differences were identified between the two modalities in terms of representability and interpretability. However, these findings should be interpreted with caution, as US examinations were performed following RX assessment on a non-blinded basis, which may have introduced observational bias. Despite these limitations, B-mode US appears to provide valuable additional diagnostic information and may serve as a complementary imaging modality in the evaluation of avian orthopaedic conditions. In particular, it may be useful for assessing shoulder girdle injuries, inflammatory conditions of the shoulder joint, and fractures of the sternum and keel, as well as for monitoring bone healing following surgical or conservative treatment. Full article

N-Methyl-D-aspartate (NMDA) receptors are ligand- and voltage-gated ion channels essential for synaptic plasticity, learning, and memory. The GluN2B subunit, highly expressed in the forebrain and spinal cord, is implicated in multiple neurological and psychiatric disorders, making it an attractive target for positron emission tomography (PET) imaging. However, the development of selective GluN2B PET radioligands remains challenging. Here, we describe the design, synthesis, and evaluation of eighteen 3-alkylaryl derivatives of 7-methoxy-2,3,4,5-tetrahydro-1H-benzo[d]azepin-1-ol, including enantiomerically resolved compounds, as candidate PET radioligands. Structure–activity relationship studies show that binding affinity is largely insensitive to electronic and steric variation at the terminal aryl group but strongly dependent on alkyl linker length, with a four-carbon chain providing optimal affinity. Binding affinity does not correlate with calculated lipophilicity, suggesting hydrophobicity is not the primary determinant of receptor interaction. Absolute configuration was established using vibrational circular dichroism and infrared spectroscopy, and docking studies provided insight into enantiomer-specific binding modes. Two ligands, L3 and L6, and their enantiomers exhibited high GluN2B affinity, favorable physicochemical properties, and suitability for carbon-11 labeling. Separate PET imaging studies confirmed strong and specific brain binding of the radiolabeled compounds. These findings establish this scaffold as a promising platform for GluN2B PET ligand development. Full article

Background/Objectives: Transabdominal ultrasonography (TUS) is widely used for the detection of gallbladder lesions (GBLs), but differentiating malignant lesions from non-malignant lesions remains challenging. Microvascular flow imaging (MVFI), including superb microvascular imaging, detective flow imaging, and B-flow, enables visualization of low-flow vessels without contrast agents. This study aimed to characterize MVFI vascular features of GBLs and evaluate their reproducibility. Methods: We retrospectively analyzed 42 patients with GBLs who underwent TUS between March 2022 and December 2025. Two blinded readers independently assessed B-mode and MVFI findings. The evaluated MVFI findings included vascular flow detection, number of basal vessels, vessel shape, vessel thickness, and vessel irregularity. Interobserver agreement was assessed using Cohen’s kappa coefficient, and imaging findings were compared between invasive malignant and non-malignant lesions. Results: Of the 42 lesions, 10 were invasive malignant and 32 were non-malignant. Vascular signals were detected in all invasive malignant lesions and in 21 of 32 non-malignant lesions. Multiple basal vessels and vessel dilation were more frequently observed in invasive malignant lesions. Interobserver agreement was excellent for the number of basal vessels (κ = 0.91) and good for vessel thickness (κ = 0.72), indicating that these findings were more reproducible than other MVFI features. Conclusions: MVFI enables visualization of intralesional vascular features in GBLs. Multiple basal vessels and vessel dilation were associated with invasive malignancy and showed favorable reproducibility. These findings may serve as candidate imaging markers for future prospective validation. Full article