Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (3,455)

Search Parameters:
Keywords = non-RES

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
16 pages, 694 KB  
Review
Nucleus Reuniens-Elicited Delta Oscillations Disable the Prefrontal Cortex in Schizophrenia
by Robert P. Vertes and Stephanie B. Linley
Cells 2025, 14(19), 1545; https://doi.org/10.3390/cells14191545 - 3 Oct 2025
Abstract
Schizophrenia (SZ) is a severe mental disorder associated with an array of symptoms characterized as positive, negative and cognitive dysfunctions. While SZ is a multifaceted disorder affecting several regions of the brain, altered thalamocortical systems have emerged as a leading contributor to SZ. [...] Read more.
Schizophrenia (SZ) is a severe mental disorder associated with an array of symptoms characterized as positive, negative and cognitive dysfunctions. While SZ is a multifaceted disorder affecting several regions of the brain, altered thalamocortical systems have emerged as a leading contributor to SZ. Specifically, it has been shown that: (1) the thalamus is functionally disconnected from the prefrontal cortex (PFC) in SZ; (2) neural activity and blood flow to the PFC are greatly diminished in SZ (hypofrontality); and (3) delta oscillations are abnormally present in the PFC during the waking state in SZ. We suggest that the abnormal delta oscillations drive the other PFC signs of SZ. Specifically, decreases in energy required to maintain delta, would initiate the reduced PFC perfusion of SZ (hypofrontality), and contribute to the ‘mismatched’ thalamic and PFC activity of SZ. As SZ involves glutamate (NMDAR) hypofunction and dopamine hyperfunction, both NMDAR antagonists and dopamine agonists produce marked increases in delta oscillations in nucleus reuniens (RE) of the thalamus and its target structures, including the PFC. This would suggest that RE is a primary source for the elicitation of PFC delta activity, and the presence of delta during waking (together with associated signs) would indicate that the prefrontal cortex is disabled (or non-functional) in schizophrenia. Full article
Show Figures

Figure 1

16 pages, 13271 KB  
Article
Smartphone-Based Estimation of Cotton Leaf Nitrogen: A Learning Approach with Multi-Color Space Fusion
by Shun Chen, Shizhe Qin, Yu Wang, Lulu Ma and Xin Lv
Agronomy 2025, 15(10), 2330; https://doi.org/10.3390/agronomy15102330 - 2 Oct 2025
Abstract
To address the limitations of traditional cotton leaf nitrogen content estimation methods, which include low efficiency, high cost, poor portability, and challenges in vegetation index acquisition owing to environmental interference, this study focused on emerging non-destructive nutrient estimation technologies. This study proposed an [...] Read more.
To address the limitations of traditional cotton leaf nitrogen content estimation methods, which include low efficiency, high cost, poor portability, and challenges in vegetation index acquisition owing to environmental interference, this study focused on emerging non-destructive nutrient estimation technologies. This study proposed an innovative method that integrates multi-color space fusion with deep and machine learning to estimate cotton leaf nitrogen content using smartphone-captured digital images. A dataset comprising smartphone-acquired cotton leaf images was processed through threshold segmentation and preprocessing, then converted into RGB, HSV, and Lab color spaces. The models were developed using deep-learning architectures including AlexNet, VGGNet-11, and ResNet-50. The conclusions of this study are as follows: (1) The optimal single-color-space nitrogen estimation model achieved a validation set R2 of 0.776. (2) Feature-level fusion by concatenation of multidimensional feature vectors extracted from three color spaces using the optimal model, combined with an attention learning mechanism, improved the validation R2 to 0.827. (3) Decision-level fusion by concatenating nitrogen estimation values from optimal models of different color spaces into a multi-source decision dataset, followed by machine learning regression modeling, increased the final validation R2 to 0.830. The dual fusion method effectively enabled rapid and accurate nitrogen estimation in cotton crops using smartphone images, achieving an accuracy 5–7% higher than that of single-color-space models. The proposed method provides scientific support for efficient cotton production and promotes sustainable development in the cotton industry. Full article
(This article belongs to the Special Issue Crop Nutrition Diagnosis and Efficient Production)
Show Figures

Figure 1

26 pages, 5861 KB  
Article
Robust Industrial Surface Defect Detection Using Statistical Feature Extraction and Capsule Network Architectures
by Azeddine Mjahad and Alfredo Rosado-Muñoz
Sensors 2025, 25(19), 6063; https://doi.org/10.3390/s25196063 - 2 Oct 2025
Abstract
Automated quality control is critical in modern manufacturing, especially for metallic cast components, where fast and accurate surface defect detection is required. This study evaluates classical Machine Learning (ML) algorithms using extracted statistical parameters and deep learning (DL) architectures including ResNet50, Capsule Networks, [...] Read more.
Automated quality control is critical in modern manufacturing, especially for metallic cast components, where fast and accurate surface defect detection is required. This study evaluates classical Machine Learning (ML) algorithms using extracted statistical parameters and deep learning (DL) architectures including ResNet50, Capsule Networks, and a 3D Convolutional Neural Network (CNN3D) using 3D image inputs. Using the Dataset Original, ML models with the selected parameters achieved high performance: RF reached 99.4 ± 0.2% precision and 99.4 ± 0.2% sensitivity, GB 96.0 ± 0.2% precision and 96.0 ± 0.2% sensitivity. ResNet50 trained with extracted parameters reached 98.0 ± 1.5% accuracy and 98.2 ± 1.7% F1-score. Capsule-based architectures achieved the best results, with ConvCapsuleLayer reaching 98.7 ± 0.2% accuracy and 100.0 ± 0.0% precision for the normal class, and 98.9 ± 0.2% F1-score for the affected class. CNN3D applied on 3D image inputs reached 88.61 ± 1.01% accuracy and 90.14 ± 0.95% F1-score. Using the Dataset Expanded with ML and PCA-selected features, Random Forest achieved 99.4 ± 0.2% precision and 99.4 ± 0.2% sensitivity, K-Nearest Neighbors 99.2 ± 0.0% precision and 99.2 ± 0.0% sensitivity, and SVM 99.2 ± 0.0% precision and 99.2 ± 0.0% sensitivity, demonstrating consistent high performance. All models were evaluated using repeated train-test splits to calculate averages of standard metrics (accuracy, precision, recall, F1-score), and processing times were measured, showing very low per-image execution times (as low as 3.69×104 s/image), supporting potential real-time industrial application. These results indicate that combining statistical descriptors with ML and DL architectures provides a robust and scalable solution for automated, non-destructive surface defect detection, with high accuracy and reliability across both the original and expanded datasets. Full article
(This article belongs to the Special Issue AI-Based Computer Vision Sensors & Systems—2nd Edition)
Show Figures

Figure 1

22 pages, 16895 KB  
Article
Surface Characterization of Hot-Rolled AISI 440C Round Wire at the Different Steps of the Typical Production Process
by Alessio Malandruccolo, Stefano Rossi and Cinzia Menapace
Metals 2025, 15(10), 1102; https://doi.org/10.3390/met15101102 - 2 Oct 2025
Abstract
This study investigates the surface characteristics and corrosion behavior of a high-C martensitic stainless steel (AISI 440C) at different stages of its manufacturing process. As a class, these steels prioritize high mechanical properties and wear resistance over superior corrosion resistance. Hot working operations, [...] Read more.
This study investigates the surface characteristics and corrosion behavior of a high-C martensitic stainless steel (AISI 440C) at different stages of its manufacturing process. As a class, these steels prioritize high mechanical properties and wear resistance over superior corrosion resistance. Hot working operations, such as rolling, create a surface oxide scale that must be removed via pickling to restore the material’s inherent corrosion resistance. This process also eliminates the underlying Cr-depleted layer, allowing for the re-establishment of a protective passive film. Using potentiodynamic polarization curves and micrographic analysis, the material’s behavior in different conditions, as-rolled, with a post-heat treatment oxide scale, and in a bare, oxide-free state, has been assessed. The results showed that the material lacks stable passive behavior under all conditions. The as-rolled and heat-treated conditions both exhibited active behavior and formed thick, non-adherent corrosion products. The oxide layer formed after heat treatment performed the worst, showing a significant increase in corrosion current density. These findings confirm the material’s susceptibility to corrosion in Cl ion-rich environments, highlighting the need for limited storage in such conditions and rapid pickling after thermal processing to mitigate surface damage. Full article
(This article belongs to the Section Corrosion and Protection)
Show Figures

Graphical abstract

21 pages, 3036 KB  
Article
Infrared Thermography and Deep Learning Prototype for Early Arthritis and Arthrosis Diagnosis: Design, Clinical Validation, and Comparative Analysis
by Francisco-Jacob Avila-Camacho, Leonardo-Miguel Moreno-Villalba, José-Luis Cortes-Altamirano, Alfonso Alfaro-Rodríguez, Hugo-Nathanael Lara-Figueroa, María-Elizabeth Herrera-López and Pablo Romero-Morelos
Technologies 2025, 13(10), 447; https://doi.org/10.3390/technologies13100447 - 2 Oct 2025
Abstract
Arthritis and arthrosis are prevalent joint diseases that cause pain and disability, and their early diagnosis is crucial for preventing irreversible damage. Conventional diagnostic methods such as X-ray, ultrasound, and MRI have limitations in early detection, prompting interest in alternative techniques. This work [...] Read more.
Arthritis and arthrosis are prevalent joint diseases that cause pain and disability, and their early diagnosis is crucial for preventing irreversible damage. Conventional diagnostic methods such as X-ray, ultrasound, and MRI have limitations in early detection, prompting interest in alternative techniques. This work presents the design and clinical evaluation of a prototype device for non-invasive early diagnosis of arthritis (inflammatory joint disease) and arthrosis (osteoarthritis) using infrared thermography and deep neural networks. The portable prototype integrates a Raspberry Pi 4 microcomputer, an infrared thermal camera, and a touchscreen interface, all housed in a 3D-printed PLA enclosure. A custom Flask-based application enables two operational modes: (1) thermal image acquisition for training data collection, and (2) automated diagnosis using a pre-trained ResNet50 deep learning model. A clinical study was conducted at a university clinic in a temperature-controlled environment with 100 subjects (70% with arthritic conditions and 30% healthy). Thermal images of both hands (four images per hand) were captured for each participant, and all patients provided informed consent. The ResNet50 model was trained to classify three classes (healthy, arthritis, and arthrosis) from these images. Results show that the system can effectively distinguish healthy individuals from those with joint pathologies, achieving an overall test accuracy of approximately 64%. The model identified healthy hands with high confidence (100% sensitivity for the healthy class), but it struggled to differentiate between arthritis and arthrosis, often misclassifying one as the other. The prototype’s multiclass ROC (Receiver Operating Characteristic) analysis further showed excellent discrimination between healthy vs. diseased groups (AUC, Area Under the Curve ~1.00), but lower performance between arthrosis and arthritis classes (AUC ~0.60–0.68). Despite these challenges, the device demonstrates the feasibility of AI-assisted thermographic screening: it is completely non-invasive, radiation-free, and low-cost, providing results in real-time. In the discussion, we compare this thermography-based approach with conventional diagnostic modalities and highlight its advantages, such as early detection of physiological changes, portability, and patient comfort. While not intended to replace established methods, this technology can serve as an early warning and triage tool in clinical settings. In conclusion, the proposed prototype represents an innovative application of infrared thermography and deep learning for joint disease screening. With further improvements in classification accuracy and broader validation, such systems could significantly augment current clinical practice by enabling rapid and non-invasive early diagnosis of arthritis and arthrosis. Full article
(This article belongs to the Section Assistive Technologies)
Show Figures

Graphical abstract

26 pages, 1647 KB  
Article
Deep Learning-Based Mpox Skin Lesion Detection and Real-Time Monitoring in a Smart Healthcare System
by Huda Alghoraibi, Nuha Alqurashi, Sarah Alotaibi, Renad Alkhudaydi, Bdoor Aldajani, Joud Batawil, Lubna Alqurashi, Azza Althagafi and Maha A. Thafar
Diagnostics 2025, 15(19), 2505; https://doi.org/10.3390/diagnostics15192505 - 1 Oct 2025
Abstract
Background/Objectives: Mpox, a viral disease marked by distinctive skin lesions, has emerged as a global health concern, underscoring the need for scalable, accessible, and accurate diagnostic tools to strengthen public health responses. This study introduces ITMA’INN, an AI-driven healthcare system designed to detect [...] Read more.
Background/Objectives: Mpox, a viral disease marked by distinctive skin lesions, has emerged as a global health concern, underscoring the need for scalable, accessible, and accurate diagnostic tools to strengthen public health responses. This study introduces ITMA’INN, an AI-driven healthcare system designed to detect Mpox from skin lesion images using advanced deep learning. Methods: The system integrates three key components: an AI model pipeline, a cross-platform mobile application, and a real-time public health dashboard. We leveraged transfer learning on publicly available datasets to evaluate pretrained deep learning models. Results: For binary classification (Mpox vs. non-Mpox), Vision Transformer, MobileViT, Transformer-in-Transformer, and VGG16 achieved peak performance, each with 97.8% accuracy and F1-score. For multiclass classification (Mpox, chickenpox, measles, hand-foot-mouth disease, cowpox, and healthy skin), ResNetViT and ViT Hybrid models attained 92% accuracy (F1-scores: 92.24% and 92.19%, respectively). The lightweight MobileViT was deployed in a mobile app that enables users to analyze skin lesions, track symptoms, and locate nearby healthcare centers via GPS. Complementing this, the dashboard equips health authorities with real-time case monitoring, symptom trend analysis, and intervention guidance. Conclusions: By bridging AI diagnostics with mobile technology and real-time analytics, ITMA’INN advances responsive healthcare infrastructure in smart cities, contributing to the future of proactive public health management. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Show Figures

Figure 1

15 pages, 2112 KB  
Article
Radiomics-Based Preoperative Assessment of Muscle-Invasive Bladder Cancer Using Combined T2 and ADC MRI: A Multicohort Validation Study
by Dmitry Kabanov, Natalia Rubtsova, Aleksandra Golbits, Andrey Kaprin, Valentin Sinitsyn and Mikhail Potievskiy
J. Imaging 2025, 11(10), 342; https://doi.org/10.3390/jimaging11100342 - 1 Oct 2025
Abstract
Accurate preoperative staging of bladder cancer on MRI remains challenging because visual reads vary across observers. We investigated a multiparametric MRI (mpMRI) radiomics approach to predict muscle invasion (≥T2) and prospectively tested it on a validation cohort. Eighty-four patients with urothelial carcinoma underwent [...] Read more.
Accurate preoperative staging of bladder cancer on MRI remains challenging because visual reads vary across observers. We investigated a multiparametric MRI (mpMRI) radiomics approach to predict muscle invasion (≥T2) and prospectively tested it on a validation cohort. Eighty-four patients with urothelial carcinoma underwent 1.5-T mpMRI per VI-RADS (T2-weighted imaging and DWI-derived ADC maps). Two blinded radiologists performed 3D tumor segmentation; 37 features per sequence were extracted (LifeX) using absolute resampling. In the training cohort (n = 40), features that differed between non-muscle-invasive and muscle-invasive tumors (Mann–Whitney p < 0.05) underwent ROC analysis with cut-offs defined by the Youden index. A compact descriptor combining GLRLM-LRLGE from T2 and GLRLM-SRLGE from ADC was then fixed and applied without re-selection to a prospective validation cohort (n = 44). Histopathology within 6 weeks—TURBT or cystectomy—served as the reference. Eleven T2-based and fifteen ADC-based features pointed to invasion; DWI texture features were not informative. The descriptor yielded AUCs of 0.934 (training) and 0.871 (validation) with 85.7% sensitivity and 96.2% specificity in validation. Collectively, these findings indicate that combined T2/ADC radiomics can provide high diagnostic accuracy and may serve as a useful decision support tool, after multicenter, multi-vendor validation. Full article
(This article belongs to the Topic Machine Learning and Deep Learning in Medical Imaging)
Show Figures

Figure 1

19 pages, 7222 KB  
Article
Multi-Channel Spectro-Temporal Representations for Speech-Based Parkinson’s Disease Detection
by Hadi Sedigh Malekroodi, Nuwan Madusanka, Byeong-il Lee and Myunggi Yi
J. Imaging 2025, 11(10), 341; https://doi.org/10.3390/jimaging11100341 - 1 Oct 2025
Abstract
Early, non-invasive detection of Parkinson’s Disease (PD) using speech analysis offers promise for scalable screening. In this work, we propose a multi-channel spectro-temporal deep-learning approach for PD detection from sentence-level speech, a clinically relevant yet underexplored modality. We extract and fuse three complementary [...] Read more.
Early, non-invasive detection of Parkinson’s Disease (PD) using speech analysis offers promise for scalable screening. In this work, we propose a multi-channel spectro-temporal deep-learning approach for PD detection from sentence-level speech, a clinically relevant yet underexplored modality. We extract and fuse three complementary time–frequency representations—mel spectrogram, constant-Q transform (CQT), and gammatone spectrogram—into a three-channel input analogous to an RGB image. This fused representation is evaluated across CNNs (ResNet, DenseNet, and EfficientNet) and Vision Transformer using the PC-GITA dataset, under 10-fold subject-independent cross-validation for robust assessment. Results showed that fusion consistently improves performance over single representations across architectures. EfficientNet-B2 achieves the highest accuracy (84.39% ± 5.19%) and F1-score (84.35% ± 5.52%), outperforming recent methods using handcrafted features or pretrained models (e.g., Wav2Vec2.0, HuBERT) on the same task and dataset. Performance varies with sentence type, with emotionally salient and prosodically emphasized utterances yielding higher AUC, suggesting that richer prosody enhances discriminability. Our findings indicate that multi-channel fusion enhances sensitivity to subtle speech impairments in PD by integrating complementary spectral information. Our approach implies that multi-channel fusion could enhance the detection of discriminative acoustic biomarkers, potentially offering a more robust and effective framework for speech-based PD screening, though further validation is needed before clinical application. Full article
(This article belongs to the Special Issue Celebrating the 10th Anniversary of the Journal of Imaging)
Show Figures

Figure 1

23 pages, 347 KB  
Article
Comparative Analysis of Foundational, Advanced, and Traditional Deep Learning Models for Hyperpolarized Gas MRI Lung Segmentation: Robust Performance in Data-Constrained Scenarios
by Ramtin Babaeipour, Matthew S. Fox, Grace Parraga and Alexei Ouriadov
Bioengineering 2025, 12(10), 1062; https://doi.org/10.3390/bioengineering12101062 - 30 Sep 2025
Abstract
This study investigates the comparative performance of foundational models, advanced large-kernel architectures, and traditional deep learning approaches for hyperpolarized gas MRI segmentation across progressive data reduction scenarios. Chronic obstructive pulmonary disease (COPD) remains a leading global health concern, and advanced imaging techniques are [...] Read more.
This study investigates the comparative performance of foundational models, advanced large-kernel architectures, and traditional deep learning approaches for hyperpolarized gas MRI segmentation across progressive data reduction scenarios. Chronic obstructive pulmonary disease (COPD) remains a leading global health concern, and advanced imaging techniques are crucial for its diagnosis and management. Hyperpolarized gas MRI, utilizing helium-3 (3He) and xenon-129 (129Xe), offers a non-invasive way to assess lung function. We evaluated foundational models (Segment Anything Model and MedSAM), advanced architectures (UniRepLKNet and TransXNet), and traditional deep learning models (UNet with VGG19 backbone, Feature Pyramid Network with MIT-B5 backbone, and DeepLabV3 with ResNet152 backbone) using four data availability scenarios: 100%, 50%, 25%, and 10% of the full training dataset (1640 2D MRI slices from 205 participants). The results demonstrate that foundational and advanced models achieve statistically equivalent performance across all data scenarios (p > 0.01), while both significantly outperform traditional architectures under data constraints (p < 0.001). Under extreme data scarcity (10% training data), foundational and advanced models maintained DSC values above 0.86, while traditional models experienced catastrophic performance collapse. This work highlights the critical advantage of architectures with large effective receptive fields in medical imaging applications where data collection is challenging, demonstrating their potential to democratize advanced medical imaging analysis in resource-limited settings. Full article
(This article belongs to the Special Issue Artificial Intelligence-Based Medical Imaging Processing)
Show Figures

Figure 1

22 pages, 1471 KB  
Article
Rift Valley Fever Virus Transmission During an Unreported Outbreak Among People and Livestock in South-Central Tanzania
by Robert D. Sumaye, Ana Pérola D. Brandão, Frank Chilanga, Goodluk Paul, Grace W. Mwangoka, Woutrina A. Smith, Abel B. Ekiri, Christopher Kilonzo, Solomon Mwakasungula, George Makingi, Amina A. Kinyogori, Walter S. Magesa, Aziza J. Samson, Catherine Mkindi, Peter Pazia, Feisal Hassan, Thabit A. Mbaga, Robinson H. Mdegela, Honorati Masanja, Deborah Cannon, Aridith Gibbons, John D. Klena, Joel M. Montgomery, Stuart T. Nichol, Lucija Jurisic, Alexandre Tremeau-Bravard, Hezron Nonga, Jamie Sebastian, Saba Zewdie, Leah Streb, Anna C. Fagre, Nicholas A. Bergren, Daniel A. Hartman, David J. Wolking, Rebekah C. Kading, Jonna A. K. Mazet and Brian H. Birdadd Show full author list remove Hide full author list
Viruses 2025, 17(10), 1329; https://doi.org/10.3390/v17101329 - 30 Sep 2025
Abstract
Rift Valley fever (RVF) is a re-emerging vector-borne zoonotic disease that causes outbreaks in humans and animals across Africa. To better understand RVF at human–animal interfaces, a prospective longitudinal survey of people, livestock, and mosquitoes was conducted from 2016 to 2018, in two [...] Read more.
Rift Valley fever (RVF) is a re-emerging vector-borne zoonotic disease that causes outbreaks in humans and animals across Africa. To better understand RVF at human–animal interfaces, a prospective longitudinal survey of people, livestock, and mosquitoes was conducted from 2016 to 2018, in two regions of Tanzania, with distinct climatic zones (Iringa and Morogoro). Molecular and serological tools for testing (RT-qPCR and IgM/IgG ELISA) for RVF virus (RVFV) were used to assess infection and exposure in people and animals. Mosquitoes were collected quarterly from 10 sentinel locations. In total, 1385 acutely febrile humans, 4449 livestock, and 3463 mosquito pools were tested. In humans, IgM seroprevalence was 3.75% (n = 52/1385), and overall seroprevalence (IgM and/or IgG positive) was 8.30% (n = 115/1385). People from Iringa had a higher exposure risk than those from Morogoro (aOR 2.63), and livestock owners had an increased risk compared to non-owners (aOR 2.51). In livestock, IgM seroprevalence was 1.09%, while overall seroprevalence was 10.11%. A total of 68.4% of herds had at least one seropositive animal. Sentinel animal follow-up revealed that the probability of seroconversion was significantly higher in Morogoro. Low-level RVFV RNA was detected in 8 human and 22 mosquito pools. These findings indicate active transmission among vectors, livestock, and people during the study period, highlighting the need for One Health surveillance approaches for RVFV and other arboviruses. Full article
(This article belongs to the Special Issue Rift Valley Fever Virus: New Insights into a One Health Archetype)
Show Figures

Figure 1

13 pages, 1111 KB  
Article
Resting HRV Sample Entropy Predicts the Magnitude of Post-Exercise Vagal Withdrawal in Young Adults
by Valters Vegelis, Ieva Anna Miezaja, Indra Mikelsone and Antra Jurka
Medicina 2025, 61(10), 1766; https://doi.org/10.3390/medicina61101766 - 30 Sep 2025
Abstract
Background and Objectives: Acute exercise lowers vagal HRV, yet it is unclear who will show the largest drop and whether simple questionnaires can identify them. To test whether resting HRV complexity (Sample Entropy) predicts the magnitude of acute vagal withdrawal and whether this [...] Read more.
Background and Objectives: Acute exercise lowers vagal HRV, yet it is unclear who will show the largest drop and whether simple questionnaires can identify them. To test whether resting HRV complexity (Sample Entropy) predicts the magnitude of acute vagal withdrawal and whether this physiology-based marker has greater practical utility than self-report activity/sleep measures for screening and recovery decisions. Materials and Methods: In a single-arm pre–post experimental study, twenty-nine students (20.4 ± 0.5 y; 13 males, 16 females) completed one morning visit (08:00–12:00 h). After a 2 min resting ECG and a Sustained Attention to Response Task (SART), participants cycled 15 min at 0.85 × (220 − age) bpm following a 5 min 25 W warm-up. HRV was re-recorded within ~2 min and SART ~5 min post exercise. The IPAQ defined low/medium/high activity tertiles. Correlations related baseline measures to change scores. Results: RMSSD decreased by −12.93 ms [−25.71, −2.03] (p = 0.003, r = 0.60) and SDNN by −14.91 ms [−22.30, 7.66] (p = 0.011, r = 0.51). Reaction time shortened slightly (−8.77 ms [−59.33, 30.40], p = 0.35). Activity tertiles did not differ in ΔRMSSD, ΔSDNN, or ΔRT (all p > 0.10). Sample Entropy predicted autonomic change (ΔRMSSD r = 0.43, p = 0.034; ΔSDNN r = 0.59, p = 0.002), whereas the PSQI and IPAQ did not. Equivalence tests showed non-significant tertile differences were not within our predefined equivalence bounds. Conclusions: Individuals with more complex resting HRV were more likely to show a larger immediate vagal withdrawal after moderate cycling. Questionnaires did not identify these responders. Non-linear HRV may aid practical screening/monitoring, whereas self-reports alone appear insufficient. Generalizability is limited by the homogeneous young adult sample. Full article
(This article belongs to the Section Sports Medicine and Sports Traumatology)
Show Figures

Figure 1

21 pages, 5230 KB  
Article
Attention-Guided Differentiable Channel Pruning for Efficient Deep Networks
by Anouar Chahbouni, Khaoula El Manaa, Yassine Abouch, Imane El Manaa, Badre Bossoufi, Mohammed El Ghzaoui and Rachid El Alami
Mach. Learn. Knowl. Extr. 2025, 7(4), 110; https://doi.org/10.3390/make7040110 - 29 Sep 2025
Abstract
Deploying deep learning (DL) models in real-world environments remains a major challenge, particularly under resource-constrained conditions where achieving both high accuracy and compact architectures is essential. While effective, Conventional pruning methods often suffer from high computational overhead, accuracy degradation, or disruption of the [...] Read more.
Deploying deep learning (DL) models in real-world environments remains a major challenge, particularly under resource-constrained conditions where achieving both high accuracy and compact architectures is essential. While effective, Conventional pruning methods often suffer from high computational overhead, accuracy degradation, or disruption of the end-to-end training process, limiting their practicality for embedded and real-time applications. We present Dynamic Attention-Guided Pruning (DAGP), a Dynamic Attention-Guided Soft Channel Pruning framework that overcomes these limitations by embedding learnable, differentiable pruning masks directly within convolutional neural networks (CNNs). These masks act as implicit attention mechanisms, adaptively suppressing non-informative channels during training. A progressively scheduled L1 regularization, activated after a warm-up phase, enables gradual sparsity while preserving early learning capacity. Unlike prior methods, DAGP is retraining-free, introduces minimal architectural overhead, and supports optional hard pruning for deployment efficiency. Joint optimization of classification and sparsity objectives ensures stable convergence and task-adaptive channel selection. Experiments on CIFAR-10 (VGG16, ResNet56) and PlantVillage (custom CNN) achieve up to 98.82% FLOPs reduction with accuracy gains over baselines. Real-world validation on an enhanced PlantDoc dataset for agricultural monitoring achieves 60 ms inference with only 2.00 MB RAM on a Raspberry Pi 4, confirming efficiency under field conditions. These results illustrate DAGP’s potential to scale beyond agriculture to diverse edge-intelligent systems requiring lightweight, accurate, and deployable models. Full article
Show Figures

Figure 1

13 pages, 1587 KB  
Article
Glioma Grading by Integrating Radiomic Features from Peritumoral Edema in Fused MRI Images and Automated Machine Learning
by Amir Khorasani
J. Imaging 2025, 11(10), 336; https://doi.org/10.3390/jimaging11100336 - 27 Sep 2025
Abstract
We aimed to investigate the utility of peritumoral edema-derived radiomic features from magnetic resonance imaging (MRI) image weights and fused MRI sequences for enhancing the performance of machine learning-based glioma grading. The present study utilized the Multimodal Brain Tumor Segmentation Challenge 2023 (BraTS [...] Read more.
We aimed to investigate the utility of peritumoral edema-derived radiomic features from magnetic resonance imaging (MRI) image weights and fused MRI sequences for enhancing the performance of machine learning-based glioma grading. The present study utilized the Multimodal Brain Tumor Segmentation Challenge 2023 (BraTS 2023) dataset. Laplacian Re-decomposition (LRD) was employed to fuse multimodal MRI sequences. The fused image quality was evaluated using the Entropy, standard deviation (STD), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) metrics. A comprehensive set of radiomic features was subsequently extracted from peritumoral edema regions using PyRadiomics. The Boruta algorithm was applied for feature selection, and an optimized classification pipeline was developed using the Tree-based Pipeline Optimization Tool (TPOT). Model performance for glioma grade classification was evaluated based on accuracy, precision, recall, F1-score, and area under the curve (AUC) parameters. Analysis of fused image quality metrics confirmed that the LRD method produces high-quality fused images. From 851 radiomic features extracted from peritumoral edema regions, the Boruta algorithm selected different sets of informative features in both standard MRI and fused images. Subsequent TPOT automated machine learning optimization analysis identified a fine-tuned Stochastic Gradient Descent (SGD) classifier, trained on features from T1Gd+FLAIR fused images, as the top-performing model. This model achieved superior performance in glioma grade classification (Accuracy = 0.96, Precision = 1.0, Recall = 0.94, F1-Score = 0.96, AUC = 1.0). Radiomic features derived from peritumoral edema in fused MRI images using the LRD method demonstrated distinct, grade-specific patterns and can be utilized as a non-invasive, accurate, and rapid glioma grade classification method. Full article
(This article belongs to the Topic Machine Learning and Deep Learning in Medical Imaging)
Show Figures

Figure 1

15 pages, 2312 KB  
Article
Impact Absorption Behaviour of 3D-Printed Lattice Structures for Sportswear Applications
by Mei-ki Chan, Sik-cheung Hung, Kit-lun Yick, Yue Sun, Joanne Yip and Sun-pui Ng
Polymers 2025, 17(19), 2611; https://doi.org/10.3390/polym17192611 - 26 Sep 2025
Abstract
Lattice structures have been widely studied in various fields due to their lightweight and high-energy absorption capabilities. In this study, we propose the use of lattice structures in the design of sports protective equipment for contact sports athletes. A total of six specimens [...] Read more.
Lattice structures have been widely studied in various fields due to their lightweight and high-energy absorption capabilities. In this study, we propose the use of lattice structures in the design of sports protective equipment for contact sports athletes. A total of six specimens were additively manufactured either with a bending-dominated rhombic dodecahedron (RD) structure or stretch-dominated re-entrant (RE) structure. Elastic resin was used to investigate the specimens’ compressive strength and energy absorption, impact reduction, and flexural properties in comparison with those of conventional foam and rigid polyethylene (PU). Despite having a lower relative density, the RE structure exhibits greater stiffness, showing up to 40% greater hardness and averaging 30.5% higher bending rigidity compared with the RD structure. However, it unexpectedly shows less stability and strength under uniaxial loading, which is 3 to 6 times weaker when compared with the non-auxetic RD structure. Although conventional PU has higher loading than 3D-printed lattices, the lattice shows excellent bendability, which is only 1.5 to 3 times stiffer than that of foam. The 3D-printed lattice in this study shows an optimal improvement of 43% in terms of impact absorption compared with foam and a 2.3% improvement compared with PU. Amongst the six different unit cell dimensions and structures studied, the RD lattice with a cell size of 5 mm is the most promising candidate; it has superior elasticity, compressive strength, and impact resistance performance whether it is under low- or high-impact conditions. The findings of this study provide a basis for the development of 3D-printed lattice sports protective chest equipment, which is more comfortable and offers improved protection for contact sports players. Full article
Show Figures

Figure 1

25 pages, 8509 KB  
Article
Dynamic Evolution and Driving Mechanisms of Cultivated Land Non-Agriculturalization in Sichuan Province
by Yaowen Xu, Qian Li, Youhan Wang, Na Zhang, Julin Li, Kun Zeng and Liangsong Wang
Sustainability 2025, 17(19), 8643; https://doi.org/10.3390/su17198643 - 25 Sep 2025
Abstract
Given that the increasing non-agricultural conversion of cultivated land (NACCL) endangers food security, studying the spatial and temporal variation characteristics and driving mechanisms of NACCL in Sichuan Province can offer a scientific foundation for developing local farmland preservation measures and controlling further conversion. [...] Read more.
Given that the increasing non-agricultural conversion of cultivated land (NACCL) endangers food security, studying the spatial and temporal variation characteristics and driving mechanisms of NACCL in Sichuan Province can offer a scientific foundation for developing local farmland preservation measures and controlling further conversion. Guided by the theoretical framework of land use transition, this study utilizes land use datasets spanning multiple periods between 2000 and 2023. Comprehensively considering population scale factors, natural geographical factors, and socioeconomic factors, the county-level annual NACCL rate is calculated. Following this, the dynamic evolution and underlying driving forces of NACCL across 183 counties in Sichuan Province are examined through temporal and spatial dimensions, utilizing analytical tools including Nonparametric Kernel Density Estimation (KDE) and the Geographical Detector model with Optimal Parameters (OPGD). The study finds that: (1) Overall, NACCL in Sichuan Province exhibits phased temporal fluctuations characterized by “expansion—contraction—re-expansion—strict control,” with cultivated land mainly being converted into urban land, and the differences among counties gradually narrowing. (2) In Sichuan Province, the spatial configuration of NACCL is characterized by the expansion of high-value agglomerations alongside the dispersed and stable distribution of low-value areas. (3) Analysis through the OPGD model indicates that urban construction land dominates the NACCL process in Sichuan Province, and the driving dimension evolves from single to synergistic. The findings of this study offer a systematic examination of the spatiotemporal evolution and underlying drivers of NACCL in Sichuan Province. This analysis provides a scientific basis for formulating region-specific farmland protection policies and supports the optimization of territorial spatial planning systems. The results hold significant practical relevance for promoting the sustainable use of cultivated land resources. Full article
Show Figures

Figure 1

Back to TopTop